
In obesity studies, several researchers have been applying machine learning tools to identify factors affecting human body weight. However, a proper review of strength, limitations and evaluation metrics of machine learning algorithms in obesity is lacking. This study reviews the status of application of machine learning algorithms in obesity studies and to identify strength and weaknesses of these methods. A scoping review of paper focusing on obesity was conducted. PubMed and Scopus databases were searched for the application of machine learning in obesity using different keywords. Only English papers in adult obesity between 2014 and 2019 were included. Also, only papers that focused on controllable factors (e.g., nutrition intake, dietary pattern and/or physical activity) were reviewed in depth. Papers on genetic or childhood obesity were excluded. Twenty reviewed papers used machine learning algorithms to identify the relationship between the contributing factors and obesity. Regression algorithms were widely applied. Other algorithms such as neural network, random forest and deep learning were less exploited. Limitations regarding data priori assumptions, overfitting and hyperparameter optimization were discussed. Performance metrics and validation techniques were identified. Machine learning applications are positively impacting obesity research. The nature and objective of a study and available data are key factors to consider in selecting the appropriate algorithms. The future research direction is to further explore and take advantage of the modern methods, i.e., neural network and deep learning, in obesity studies.
Citation: Mohammad Alkhalaf, Ping Yu, Jun Shen, Chao Deng. A review of the application of machine learning in adult obesity studies[J]. Applied Computing and Intelligence, 2022, 2(1): 32-48. doi: 10.3934/aci.2022002
[1] | Liping Wang, Runqi Liu, Yangyang Shi . Dynamical analysis of a nonlocal delays spatial malaria model with Wolbachia-infected male mosquitoes release. Electronic Research Archive, 2025, 33(5): 3177-3200. doi: 10.3934/era.2025139 |
[2] | Yan Geng, Jinhu Xu . Modelling and analysis of a delayed viral infection model with follicular dendritic cell. Electronic Research Archive, 2024, 32(8): 5127-5138. doi: 10.3934/era.2024236 |
[3] | Jing Yang, Shaojuan Ma, Dongmei Wei . Dynamical analysis of SIR model with Gamma distribution delay driven by Lévy noise and switching. Electronic Research Archive, 2025, 33(5): 3158-3176. doi: 10.3934/era.2025138 |
[4] | Jitendra Singh, Maninder Singh Arora, Sunil Sharma, Jang B. Shukla . Modeling the variable transmission rate and various discharges on the spread of Malaria. Electronic Research Archive, 2023, 31(1): 319-341. doi: 10.3934/era.2023016 |
[5] | Xudong Hai, Chengxu Chen, Qingyun Wang, Xiaowei Ding, Zhaoying Ye, Yongguang Yu . Effect of time-varying delays' dynamic characteristics on the stability of Hopfield neural networks. Electronic Research Archive, 2025, 33(3): 1207-1230. doi: 10.3934/era.2025054 |
[6] | Rui Ma, Xin-You Meng . Dynamics of an eco-epidemiological model with toxicity, treatment, time-varying incubation. Electronic Research Archive, 2025, 33(5): 3074-3110. doi: 10.3934/era.2025135 |
[7] | Miaomiao Gao, Yanhui Jiang, Daqing Jiang . Threshold dynamics of a stochastic SIRS epidemic model with transfer from infected individuals to susceptible individuals and log-normal Ornstein-Uhlenbeck process. Electronic Research Archive, 2025, 33(5): 3037-3064. doi: 10.3934/era.2025133 |
[8] | Jorge Rebaza . On a model of COVID-19 dynamics. Electronic Research Archive, 2021, 29(2): 2129-2140. doi: 10.3934/era.2020108 |
[9] | Erhui Li, Qingshan Zhang . Global dynamics of an endemic disease model with vaccination: Analysis of the asymptomatic and symptomatic groups in complex networks. Electronic Research Archive, 2023, 31(10): 6481-6504. doi: 10.3934/era.2023328 |
[10] | Wenjie Zuo, Mingguang Shao . Stationary distribution, extinction and density function for a stochastic HIV model with a Hill-type infection rate and distributed delay. Electronic Research Archive, 2022, 30(11): 4066-4085. doi: 10.3934/era.2022206 |
In obesity studies, several researchers have been applying machine learning tools to identify factors affecting human body weight. However, a proper review of strength, limitations and evaluation metrics of machine learning algorithms in obesity is lacking. This study reviews the status of application of machine learning algorithms in obesity studies and to identify strength and weaknesses of these methods. A scoping review of paper focusing on obesity was conducted. PubMed and Scopus databases were searched for the application of machine learning in obesity using different keywords. Only English papers in adult obesity between 2014 and 2019 were included. Also, only papers that focused on controllable factors (e.g., nutrition intake, dietary pattern and/or physical activity) were reviewed in depth. Papers on genetic or childhood obesity were excluded. Twenty reviewed papers used machine learning algorithms to identify the relationship between the contributing factors and obesity. Regression algorithms were widely applied. Other algorithms such as neural network, random forest and deep learning were less exploited. Limitations regarding data priori assumptions, overfitting and hyperparameter optimization were discussed. Performance metrics and validation techniques were identified. Machine learning applications are positively impacting obesity research. The nature and objective of a study and available data are key factors to consider in selecting the appropriate algorithms. The future research direction is to further explore and take advantage of the modern methods, i.e., neural network and deep learning, in obesity studies.
A competitive market will be introduced for all commodities, including electricity in the future. The monopoly electricity market has now been reorganized into three distinct entities: generation companies (GENCOs), transmission companies (TRANSCOs), and distribution companies (DISCOs) [1,2]. Competition will be introduced between GENCOs and DISCOs to increase the efficiency of generation and consumption. The grid is operated by a separate entity, the system operator.
A power grid is generally managed by one entity for economic reasons and for better control of the flow of power. Electricity demand is growing faster than the expansion of the grid. In addition, a large number of bilaterally or multilaterally agreed power contracts are increasing congestion on transmission lines [3]. Line congestion [4], can occur if all transactions are not properly controlled. It forces transmission capacity improvement or transmission network expansion. Congestion management is defined as the recommended measures to reduce line congestion. Land acquisition and installation costs are the most important limitations in the development of transmission networks. Additionally, depending on the deal, the increase in bandwidth may only be temporary during the duration of the deal, justifying capacity expansion as the best alternative to expansion.
Trade agreements that lead to increased currents lead to increased line losses, jeopardizing system stability and security. Therefore, it is required to make the best use of the transmission capacity already installed. This can be easily done by just installing the FACTS device [5,6,7]. There are two reasons for the increased use of these FACTS devices. First, recent advances in power electronic switching devices have made them cheaper and more efficient [8]. Identifying the location and size of these devices is critical for optimal performance and minimal cost. Various methods are available to select the optimal location and size of FACTS devices in the energy system [9,10,11]. Reference [12] recommends a sensitivity-based method for choosing the best location for TCSC and also examines the impact of line impedance on congestion mitigation. The TCSC location is optimized to reduce line congestion in the event of contingencies in [13]. Reference [14] deals with congestion mitigation and improved voltage stability in liberalized electricity markets using several FACTS devices. Minimizing the total congestion cost using FACTS devices is described in [15]. Differential evolution algorithms are applied to improve safety and reduce overload in power systems under conditions of single-line faults in [16]. Management of congestion using Bee colony optimization and cost minimization is also done in [17]. TCSC is placed at best locations for maximizing social benefit and reducing congestion in transmission lines in [18]. A genetic algorithm is used for finding the optimal location of TCSC to solve a transmission line congestion problem in [19].
In most of the studies on congestion management, the cause of congestion considered is the outage of transmission lines. The other equally important causes of line congestion like bilateral and multilateral transactions in deregulated power markets are not sufficiently addressed in the literature. The research gap of transmission congestion caused by increased load, bilateral transaction, and multilateral transaction in deregulated power networks is addressed in this work.
A new method based on whale optimization algorithm is proposed here to determine the optimal location and rating of TCSC and SVC devices.
The main contributions of this work are as follows: 1. The WOA, which is a recent optimization algorithm, is proposed. The algorithm exhibits better searching ability and convergence speed. 2. A comparison of the proposed WOA with some state-of the-art algorithms demonstrates the superior performance of the algorithm. The WOA tops the rank on the performance comparison with these algorithms. 3.Three different causes of congestion are taken in this study, viz, increase in load, bilateral transaction and multilateral transaction. 4. Experimental results of the CM task reveal that series and shunt connected combination of FACTS devices perform better than when they are used individually.
In Section 2 static power injection modeling of TCSC and SVC are presented. In Section 3 the objective function of minimizing congestion, loss, and voltage deviation is discussed. Searching behaviur and modelling of WOA algorithm are described in section 4. In section 5, the results and discussion are presented. Finally, in section 6, the work is concluded, and future scope is proposed.
SVC devices can be operated as reactive power sources and sinks. This can be modeled as an ideal reactive power source/sink on bus i (2.1).
ΔQis=ΔQSVC | (2.1) |
The main purpose of the SVC is usually to keep the weak bus voltage near its nominal value. It can be installed in the middle of the transmission line. The reactive power associated with SVC can be mathematically expressed as Equation (2.2) [20].
QSVC=Vi(Vi−Vr)/Xsl | (2.2) |
where, Xsl is the equivalent slope reactance denoted by p.u. Vr is the magnitude of the reference voltage. The SVC is modelled as a variable susceptance connected to bus i as shown in Figure 1.
A TCSC device is connected in series with a line and changes its reactance to change the power flow level [21]. It can act like a capacitor to generate reactive power, or it can act like an inductor to absorb reactive power. Its low cost compared to the cost of other FACTS devices makes it suitable for congestion management problems. Figure 2 shows the π model of a line between bus i and bus j.
If Vi∠δi and Vj∠δj are the polar forms of voltages at buses i and j. Active and reactive power flow from bus-i to bus-j can be given by Equations (2.3) and (2.4), respectively.
Pij=V2iGij−ViVj(Gijcosδij+Bijsinδij) | (2.3) |
Qij=−V2i(Bij+Bsh)−ViVj(Gijsinδij+Bijcosδij) | (2.4) |
Power flows in the reverse direction, i.e, from bus j to bus i are given by Equations (2.5) and (2.6).
Pji=V2jGij−ViVj(Gij coδij+Bijsinδij) | (2.5) |
Qji=−V2j(Bij+Bsh)−ViVj(Gijsinδij+Bijcosδij) | (2.6) |
The TCSC insertion can be viewed as a variable reactance in series with the transmission line. Figure 3 shows a transmission line model with a TCSC. In steady state, TCSC can be modelled as a static capacitor/inductor with impedance jxTCSC.
The TCSC implementation modifies the power flow from bus i to bus j as given by Equations (2.7) and (2.8).
P′ij=V2iG′ij−ViVj(G′ijcosδij+B′ijsinδij) | (2.7) |
Q′ij=−V2i(B′ij+B′sh)−ViVj(G′ijsinδij+B′ijcosδij) | (2.8) |
where, G′ij=rijr2ij+(xij−xTCSC)2 B′ij=−(xij−xTCSC)(r2ij+(xij−xTCSC)2)
The congestion management problem is considered a static problem and uses the static model of FACTS devices that injects current at the ends of the line. According to this model, a TCSC device can be modelled as a PQ injection into a specific node. Figure 4 is the power injection model for the TCSC device.
The active and reactive power injections of bus i and bus j after inserting TCSC are given by Equations (2.9) to (2.12).
P′i=V2iΔGij−ViVj(ΔGijcosδij+ΔBijsinδij) | (2.9) |
P′j=V2jΔGij−ViVj(ΔGijcosδij+ΔBijsinδij) | (2.10) |
Q′i=−V2iΔBij−ViVj(ΔGijsinδij+ΔBijcosδij) | (2.11) |
Q′j=−V2jΔBij−ViVj(ΔGijsinδij+ΔBijcosδij) | (2.12) |
where, ΔGij=(xTCSCrij(xTCSC−2xij))r2ij+x2ij[r2ij+(xij−xTCSC)2] ΔGij=−xTCSC(r2ij−x2ij+xTCSCxijr2ij+x2ij[r2ij+(xij−xTCSC)2]
In a deregulated environment, TRANSCO, GENCO, and DISCO are different organizations. In all kinds of deregulated power system models there are grid operators to maintain coordination between them. This is usually an independent system operator (ISO). In a competitive electricity market, market participants are given sufficient freedom to interact with each other. Here, both buyers (DISCO) and sellers (GENCO) try to buy and sell power to maximize their profits. Transmission bottlenecks occur in deregulated electricity markets when transmission capacity is not sufficient to allow all transmissions simultaneously. Overloads should be mitigated as soon as possible because they cause tripping of the overloaded line and the possible cascaded trips of other lines, and possibly voltage stability problems. Therefore, removing bottlenecks quickly, systematically, and efficiently is critical in maintaining market efficiency. FACTS devices may be an alternative solution for reducing flow in heavily loaded lines.
The main purpose of this work is to eliminate overloading of the lines by adjusting the design variables of generator bus voltage, transformer tap changes, and reactive power outputs of installed SVC and TCSC devices. Changes in the values of design variables affect the level of power system losses and voltage excursions. To explain these effects, three objectives are considered. i.e, minimize power flow violations, reduce power loss, and control voltage deviations.
Transmission lines are designed to transmit power within their thermal limits. Congestion management eliminates these overruns by minimizing active power over flows. This is our first objective here.
f1=NL∑k=1|Pk−Pkrat)| | (3.1) |
where Pk is the power flow at the kth line, and Pkrat is the maximum power flow limit of the line.
For economical and efficient operations, the ISO should ensure minimum transmission loss, which is considered as the second objective.
f2=NL∑k=1Gk(V2i+V2j−2|Vi||Vj|cosδi−δj) | (3.2) |
where Gk is the conductance of the kth line. Vi and Vj are the sending end and receiving end voltage magnitudes of the kth line. δi and δj are the sending end and receiving end voltage angles of the kth line.
The objective of power engineers is to ensure quality power at consumer end the voltage variations at load buses adversely affect the quality of power. This can be eliminated by considering voltage deviation as the third objective.
f3=NPQ∑k=1|(Vk−Vkref)| | (3.3) |
where Vk is the voltage of the kth bus. Vkref is the reference voltage at bus k. It is taken as 1.0 p.u. in this work.
The congestion management problem is formulated as an optimization problem with multiple goals: minimizing power flow violation in transmission lines, reducing transmission losses, and minimizing voltage drift on load buses.
The weighted aggregated method is employed to convert the multi-objective modeling to single objective model as [22].
F=w1f1+w2f2+w3f3 | (3.4) |
For determining the weight factors of multi-objective optimisation, since the power flow violation is the main concern, its corresponding weight factor is set as the highest value (0.6). The weights of other two objectives, i.e, loss and voltage deviation are set as 0.2.
i.e, C1 = 0.6, C2 = 0.2, C3 = 0.2.
The system must satisfy the real and reactive power flow constraints which are given by power flow equations as equality constraints.
PGi−PDi−NB∑j=1ViVjYijcosδij+γj−γi)=0 | (3.5) |
QGi−QDi−NB∑j=1ViVjYijsinδij+γj−γi)=0 | (3.6) |
where, PGi, QGi are the active and reactive power of ith generator, and PDi, QDi are the active and reactive power of the ith load bus.
Generator constraints:
Generator voltage and reactive power of ith bus lies between their upper and lower limits as given below:
Vmini≤Vi≤Vmaxii=1,2,....NG | (3.7) |
QminGi≤QGi≤QmaxGii=1,2,....NG | (3.8) |
where, Vmini, Vmaxi are the minimum and maximum voltages of the ith generating unit, and QminGi, QmaxGi are the minimum and maximum reactive power of the ith generating unit.
Transmission line constraints:
Real power flow limit of a line is given as:
Pi≤Pmaxii=1,2,...,NL | (3.9) |
where, Pi is the apparent power flow of the ith branch, and Pmaxi is the maximum apparent power flow limit of the ith branch.
Transformer taps constraints:
Transformer tap settings are bounded between upper and lower limit as given below:
Tmini≤Ti≤Tmaxii=1,2,....NT | (3.10) |
where, Tmini, Tmaxi are the minimum and maximum tap setting limits of the ith transformer.
Shunt compensator constraints:
Shunt compensation is restricted by their limits as follows:
SVCmini≤SVCi≤SVCmaxii=1,2,....NSVC | (3.11) |
where, SVCmini, SVCmaxi are the minimum and maximum VAR injection limits of the ith shunt capacitor.
Series compensator constraints:
Series compensation is restricted by their limits as follows:
TCSCmini≤TCSCi≤TCSCmaxii=1,2,....NTCSC | (3.12) |
where, TCSCmini, TCSCmaxi are the minimum and maximum reactance limits of the ith series compensator of TCSC.
Whales rarely sleep because they need to breathe on the surface. Whales are always on alert to help them think, learn, judge, communicate, and even become emotional through their spindle cells [23]. Most whale species are able to live in families throughout their lives. Humpback whales are one of the largest animals with a specialized hunting behavior called bubble net feeding. Bubble net feeding is a specialized activity found only in humpback whales and is mathematically modelled in the next section to find the optimal solution in the search space. Algorithms inspired by nature are mimicked by organisms, such as foraging and survival mechanisms. The whale optimization algorithm was developed based on whale survival mechanisms in the deep sea.
The WOA brings the current best candidate closer to the best solution. Once the best solution is found, other candidates will try to update their positions. This update action is represented by Equations (4.1) and (4.2).
→D=|→C⋅→X∗(t)−→X(t)| | (4.1) |
→X(t+1)=→X∗(t)−→A⋅→D | (4.2) |
where t is the current iteration number, A and C are the coefficients, X∗ is the best solution so far, and X is the position vector. || stands for size only, and the period (·) is the element-wise multiplication operator.
The A and C vectors are computed as follows:
→A=2→a.→r−→a | (4.3) |
→C=2.→r | (4.4) |
The value of a is decreased linearly starting from 2 to 0 through the iterations and r is a random vector in (0, 1). The position (X, Y) of a whale is updated based on the position of the best history so far (X*, Y*). Positions around the current best position are obtained by adjusting the values of A and C vectors.
There are two ways to model the behavior of a humpback's bubble web: the retracting enveloping mechanism and the spiral update position. We will use the former method here. This behavior is achieved by reducing the value of a. Note that the range of variation of A is also reduced by a. That is, A is a random value in the interval (–a, a), and a decreases from 1 to 0 with iteration. If the random values for A are set to (1, 1), the whale's new position can be defined between its original position and the current optimal agent's position.
Approaches using variations of the A vector are also used here to hunt for prey (reconnaissance). In fact, whales randomly seek each other's positions. Therefore, the value of A is chosen among values greater than 1 and less than -1 to prevent the search agent from straying too far from the reference whale. This notion and the |A|>1 condition indicate search and allow the algorithm to perform a global search. The mathematical model is given by Equation (4.5).
→D=|→C.→Xrand−→X| | (4.5) |
→Xt+1=→Xrand−→A.→D | (4.6) |
where →Xrand is a random whale chosen from the current population.
The WOA algorithm begins with a set of randomly selected solutions. Each search agent is updated for its their position with respect to either a random search agent or the current best solution. A random search agent is chosen when |A|>1, while the best solution is selected when |A|<1 for updating the position of the search agents. The WOA algorithm starts with a set of randomly chosen solutions. Each search agent is updated with respect to its position relative to either the random search agent or the current best solution. If |A|>1, a random search agent is chosen. The optimal solution is chosen for |A|<1. Update the search agent location.
The implementation procedure for the WOA is explained below.
Step 1: Read the test system line and bus data and solve the system line flow problem using the NR load flow method for the current system state.
Step 2: Initialize the whales, and set the population size NP to 30 and the number of iterations to 300. Each whale is a set of control-variable values taken within the lower and upper bounds.
Step 3: Set as control variables such as generator bus voltage, transformer tap position, SVC, and TCSC device position and size.
Step 4: Randomly generate a population of whales and initialize an iteration counter.
Step 5: Run NR Power Flow to calculate objective values for each whale. Perform this procedure for all 30 whales to complete the iterations.
Step 6: Once the objective values for all whales have been computed, sort the whales in ascending order of objective function value. The first whale is the current best with the smallest objective function value.
Step 7: Update whales using Equations. (4.2)-(4.6).
Step 8: Run the NR tide analysis to calculate the updated whale population target.
Step 9: Identify the best current whales. Compare this best whale to the best whale ever saved. If this whale is better, keep this as the best solution or go back to step 7.
Step 10: When the stop is achieved, exit the program and return the result.
The proposed WOA-based congestion handling method is implemented in an IEEE 30 bus test system case. The system has 6 generators at nodes 1, 2, 5, 8, 11, and 13, 24 load nodes, and 41 branches [24]. Bus 1 is the reference bus, and the data is 100 MVA based. Three different transmission congestion cases are used in the simulation study: 35 % increased load, two-way transactions, and multilateral transactions. Table 1 shows the three congestion cases and the power trading volume for each case. The minimum and maximum values of the control variables of generator voltage magnitude and transformer tap change position are within 0.9 p.u. and 1.0 p.u. The SVC VAR output can be in the (0-10) MVAR range. TCSC reactance is measured between 20 % capacitive and 70 % inductance of the line. The proposed algorithm is run 50 times in the three different cases, and the best and worst results are compared with other algorithms. The time of execution in each case is also compared.
Case | Cause of congestion | |
Case 1 | 35 % overload at all the load buses. | |
Case 2 | 11.5 MW of bilateral power transaction between GENCO 13 and DISCO 26 | |
Case 3 | GENCOS Generator 8-11MW Generator 11-10 MW Total 21 MW |
DISCOS Load bus 21-8 MW Load bus 29-13 MW Total 21 MW |
The total active power load of the system increases to 135%, resulting in increased MW flow through all lines. The most affected power flow is that of line 1, which carries a load of 131.2674 MW. The nominal power of this transmission line is 130 MW, but there is 1.2674 MW of surplus power. To ensure the security of a system that wires the Slack bus to the rest of the network, congestion must be mitigated. System control variables and TCSC and SVC parameters are controlled using the proposed congestion management algorithm. TCSC and SVC devices are optimally placed to provide maximum congestion relief. For comparison, Table 2 shows the power flow through various lines in the system during and after congestion handling. From the power flow, we can see that the overloaded lines are released, and the flow of all lines is adjusted so that the power is below capacity.
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 131.2674 | 127.1166 | 128.2412 | 125.1989 | 22 | 9.8363 | 8.1865 | 8.7090 | 8.6592 |
2 | 77.7204 | 75.0097 | 75.8193 | 74.2556 | 23 | 5.2405 | 3.6808 | 4.2064 | 5.1400 |
3 | 45.1248 | 43.2307 | 43.2015 | 42.7181 | 24 | 8.5512 | 10.2505 | 9.7927 | 8.8475 |
4 | 72.8314 | 69.4883 | 69.6251 | 68.8218 | 25 | 11.9157 | 13.7223 | 13.2309 | 11.8875 |
5 | 74.1643 | 74.1887 | 74.4739 | 73.6354 | 26 | 6.6694 | 11.5236 | 11.4966 | 11.2112 |
6 | 59.3274 | 57.8368 | 58.0393 | 56.8173 | 27 | 28.9593 | 29.1638 | 27.9801 | 22.4926 |
7 | 63.3811 | 64.4707 | 65.7898 | 64.8420 | 28 | 10.8002 | 9.1367 | 8.4401 | 7.3881 |
8 | 7.93120 | 12.8620 | 15.2268 | 12.2036 | 29 | 1.7056 | 3.8475 | 2.9429 | 4.1995 |
9 | 37.5064 | 36.5992 | 36.3548 | 37.1752 | 30 | 10.5278 | 4.4165 | 3.6045 | 3.3333 |
10 | 22.1891 | 22.9065 | 23.4902 | 27.6507 | 31 | 10.6332 | 9.0324 | 8.3738 | 7.3340 |
11 | 25.4170 | 23.1346 | 21.7937 | 21.5930 | 32 | 5.6166 | 3.3569 | 2.2172 | 2.8031 |
12 | 18.3791 | 17.6891 | 17.2740 | 15.4786 | 33 | 4.2880 | 0.8294 | 3.9745 | 3.7617 |
13 | 47.4478 | 27.0789 | 20.3210 | 27.9462 | 34 | 5.8192 | 5.7996 | 5.7937 | 5.7936 |
14 | 46.4785 | 46.9837 | 42.1148 | 43.9273 | 35 | 3.5019 | 6.4873 | 9.4731 | 9.3541 |
15 | 42.8541 | 38.7400 | 37.0566 | 36.9979 | 36 | 30.9965 | 25.3566 | 24.6979 | 24.8266 |
16 | 53.8331 | 37.2635 | 38.4911 | 48.4069 | 37 | 8.8276 | 8.9778 | 8.7456 | 8.7457 |
17 | 12.0257 | 10.3300 | 10.2700 | 10.7133 | 38 | 10.0438 | 9.8753 | 9.9441 | 9.9443 |
18 | 29.0165 | 23.1251 | 22.8826 | 21.3487 | 39 | 5.1140 | 6.0776 | 5.0914 | 5.0914 |
19 | 13.6922 | 9.3345 | 9.2472 | 9.2246 | 40 | 1.7674 | 2.9780 | 2.8456 | 2.4313 |
20 | 3.2679 | 1.5180 | 1.4580 | 2.2925 | 41 | 20.3357 | 2.0586 | 2.7997 | 23.9190 |
21 | 8.1316 | 4.2744 | 4.1385 | 3.9422 | - | - | - | - | - |
SVC and TCSC devices are deployed to optimize power flow patterns to alleviate congestion and minimize load node power loss and total voltage deviation. These benefits are shown in Table 3. The line loss during congestion was 15.2375 MW, but after congestion management the loss is reduced to 13.162 MW. A loss reduction of 2.0755 MW is achieved. To prove the strength of the proposed WOA-based method, the losses and voltage deviations reported by FFA and PSO are also presented in Table 3.
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 15.2375 | 13.3491 | 13.3481 | 13.162 |
Voltage deviation (p.u.) | 0.9000 | 0.4368 | 0.3423 | 0.3327 |
The best and worst values of objectives yielded by PSO, FFA, and WOA algorithms are given in Table 4. The values of reported by WOA are better than those of the other algorithms. The less execution time taken by WOA proves its speed of calculations. This indicates that the proposed method is less time expensive.
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 13.3491 | 13.3481 | 13.162 |
Worst | 13.8762 | 13.6539 | 13.4356 | |
Voltage deviation (p.u.) | Best | 0.4368 | 0.3423 | 0.3327 |
Worst | 0.5789 | 0.4735 | 0.3465 | |
Execution time (Sec) | 124.68 | 122.53 | 120.34 |
Design variables are adjusted during the optimization process to get the best values for line overload, loss and voltage difference objectives. The best set of control variables corresponding to the best global results is shown in Table 5. These values are recommended for operating the power system under healthy conditions.
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0866 | 1.0901 | 1.0822 |
V2(p.u.) | 1.0688 | 1.0611 | 1.0565 |
V5(p.u.) | 1.0380 | 1.0292 | 1.0301 |
V8(p.u.) | 1.0333 | 1.0243 | 1.0234 |
V11(p.u.) | 1.0690 | 1.0124 | 1.0664 |
V13(p.u.) | 1.0612 | 1.0644 | 1.0806 |
T11(p.u.) | 1.0033 | 0.9839 | 1.0144 |
T12(p.u.) | 1.0081 | 0.9489 | 1.0876 |
T15(p.u.) | 1.0513 | 1.0433 | 1.0876 |
T36(p.u.) | 1.0302 | 0.9454 | 0.9519 |
SVC1(p.u.) | 1.0074 | 3.2545 | 8.8528 |
SVC2(p.u.) | 8.8143 | 1.5495 | 8.9837 |
TCSC1(p.u.) | 0.2000 | -0.2768 | -0.2483 |
TCSC2 (p.u.) | 0.1627 | -0.3371 | 0.1804 |
As shown in Table 6, two SVCs and two TCSCs are proposed for different bus and line locations by the three algorithms. The location is ideal for case 1 congestion management.
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 4 | 13 | 21 |
SVC2 | 29 | 28 | 19 |
TCSC1 | 37 | 22 | 17 |
TCSC2 | 21 | 28 | 25 |
The convergence quality of the proposed WOA algorithm is depicted in Figure 5 and it is clear from the Figure that the WOA algorithm is faster than the remaining two algorithms. Comparing the change in objective values over iterations, reported by the three algorithms, it is obvious that WOA better maintains the objective value.
In this case, bi-directional transactions are performed between buses 13 and 26. This transaction is done using bus 13 as the GENCO and bus 26 as his DISCO bus for power transactions. The contract provides for a power deal of 11.5 MW, resulting in 16 MW capacity line no. 34 getting overloaded. The power flow during this transaction is 16.1233 MW. The proposed WOA-based method is utilized to remove the congestion caused by line no. 34. The post-line flows obtained by the PSO, FFA, and WOA algorithms after line congestion are shown in Table 7.
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 57.0233 | 58.8873 | 56.6586 | 57.8673 | 22 | 8.3147 | 7.0358 | 7.1936 | 6.7068 |
2 | 43.6815 | 43.6303 | 44.0706 | 42.7216 | 23 | 4.8852 | 3.6846 | 3.8941 | 3.6183 |
3 | 31.0181 | 29.9268 | 29.4216 | 29.8110 | 24 | 5.2431 | 6.6591 | 6.6733 | 6.3522 |
4 | 40.6146 | 40.1990 | 40.7333 | 39.5424 | 25 | 7.6561 | 9.1047 | 9.1003 | 8.8002 |
5 | 45.4808 | 46.1908 | 46.0554 | 46.7183 | 26 | 2.6326 | 7.1752 | 8.4684 | 7.4627 |
6 | 39.6320 | 39.5434 | 38.9485 | 38.5417 | 27 | 21.9695 | 19.7922 | 22.3958 | 21.5405 |
7 | 39.8581 | 42.4776 | 42.9750 | 42.1190 | 28 | 11.3091 | 8.5998 | 8.9210 | 7.8082 |
8 | 2.3672 | 9.1103 | 8.6955 | 8.9257 | 29 | 1.5164 | 2.6761 | 1.4691 | 2.0758 |
9 | 25.7829 | 22.0543 | 22.0906 | 21.5574 | 30 | 10.8513 | 7.0932 | 7.4625 | 6.1584 |
10 | 24.7471 | 13.9963 | 14.2904 | 18.7578 | 31 | 11.1538 | 8.5580 | 8.8641 | 7.7619 |
11 | 15.7261 | 13.2819 | 14.2110 | 13.0692 | 32 | 8.0211 | 5.5036 | 6.0923 | 4.5671 |
12 | 12.4440 | 12.0949 | 11.8807 | 11.1906 | 33 | 9.8490 | 7.0819 | 7.5262 | 5.1054 |
13 | 43.3236 | 23.4617 | 25.2978 | 22.4414 | 34 | 16.1233 | 14.8868 | 16.0375 | 12.8579 |
14 | 34.9827 | 34.0180 | 32.9252 | 33.0242 | 35 | 7.0327 | 9.6894 | 10.2188 | 11.6211 |
15 | 22.6015 | 18.8723 | 19.8619 | 19.8234 | 36 | 29.2238 | 23.4491 | 23.8081 | 23.5225 |
16 | 51.3706 | 31.2894 | 31.1382 | 41.8936 | 37 | 6.4457 | 6.4123 | 6.4136 | 6.4103 |
17 | 9.7744 | 8.3627 | 8.2823 | 8.1735 | 38 | 7.3265 | 7.2860 | 7.2875 | 7.2836 |
18 | 25.0675 | 20.4409 | 21.1225 | 19.6811 | 39 | 3.7625 | 3.7533 | 3.7537 | 3.7528 |
19 | 12.4633 | 9.3543 | 9.8376 | 9.8049 | 40 | 5.0213 | 3.4364 | 3.9863 | 3.2971 |
20 | 3.2225 | 2.0372 | 2.5218 | 1.8469 | 41 | 17.9584 | 20.0304 | 19.8285 | 20.5734 |
21 | 8.2686 | 5.6617 | 6.5755 | 6.2436 | - | - | - | - | - |
Table 8 shows additional benefits of minimizing the loss levels and voltage deviations reported by the algorithm. The actual power loss achieved by the WOA during this bilateral transaction period was 6.193 MW, which is lower than the loss levels indicated by the two other algorithms. It is clear that the proposed method alleviates congestion and greatly minimizes line loss. The total voltage deviation under overload was 0.7370 and was reduced to 0.1678 by the WOA algorithm. Meanwhile, 0.2172 and 0.1747 are the voltage deviations obtained by the PSO and FFA algorithms.
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 7.1254 | 6.6698 | 6.5439 | 6.1930 |
Voltage deviation (p.u.) | 0.7370 | 0.2172 | 0.1747 | 0.1678 |
The statistical analysis of objective values obtained by the different algorithms are shown in Table 9 for comparison. The best and worst values of WOA are better than those of PSO and FFA algorithms. The execution time taken by WOA is less than the time taken by PSO and FFA algorithms. This proves the fast convergence quality of WOA.
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.6698 | 6.5439 | 6.1930 |
Worst | 6.9875 | 6.8976 | 6.5432 | |
Voltage deviation (p.u.) | Best | 0.217 | 0.1747 | 0.1678 |
Worst | 0.245 | 0.1954 | 0.1726 | |
Execution time (Sec) | 203.68 | 200.83 | 117.34 |
Generator voltage magnitude, transformer tap-changer settings, SVC and TCSC parameters are all optimized by the PSO, FFA, and WOA algorithms. Control variables are adjusted during the optimization process, taking into account upper and lower bounds. The well-matched control variables corresponding to the best results are shown in Table 10.
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0491 | 1.0323 | 1.0381 |
V2(p.u.) | 1.0314 | 1.0215 | 1.0219 |
V5(p.u.) | 1.0075 | 1.0053 | 1.0107 |
V8(p.u.) | 0.9992 | 0.9982 | 0.9990 |
V11(p.u.) | 0.9761 | 1.0472 | 1.0347 |
V13(p.u.) | 1.0330 | 1.0117 | 1.0582 |
T11(p.u.) | 0.9869 | 1.0130 | 1.0043 |
T12(p.u.) | 0.9591 | 0.9572 | 0.9983 |
T15(p.u.) | 0.9681 | 0.9651 | 1.0452 |
T36(p.u.) | 0.9625 | 0.9587 | 0.9345 |
SVC1(p.u.) | 9.3156 | 6.7702 | 2.3240 |
SVC2(p.u.) | 7.9593 | 6.0915 | 2.5471 |
TCSC1(p.u.) | 0.2000 | -0.2537 | -0.2810 |
TCSC2 (p.u.) | 0.2000 | -0.2276 | 0.1533 |
Table 11 shows the best bus and line locations identified for SVC and TCSCs in relieving congestion in this case that are different for different algorithms. when SVC and TCSC devices are located at the positions (bus and line numbers), the line overload, line loss and load bus voltages are optimized, and this helps the power system to be free from stressed conditions.
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 21 | 26 | 23 |
SVC2 | 25 | 15 | 19 |
TCSC1 | 13 | 40 | 19 |
TCSC2 | 15 | 4 | 9 |
Figure 6 shows how the algorithm behaves in converging to the optimal goal value of the problem in this congestion managing problem caused by bilateral transaction. The proposed WOA method achieves the best results in fewer iterations and retains them throughout the optimization process.
In the multilateral transaction considered in this case, buses 8 and 11 use GENCO to sell 11 MW and 10 MW of electricity, respectively. DISCO is located on buses 21 and 29 with distributed power of 8 MW and 13 MW, respectively. This multilateral transaction causes congestion on branch 37, which has a capacity of 16 MW, but it is overloaded due to a power flow of 16.2977 MW. Table 12 compares line flows during and after congestion management.
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 56.5202 | 57.8191 | 58.0784 | 57.6420 | 22 | 7.2961 | 6.1769 | 5.9659 | 6.2039 |
2 | 43.9787 | 43.7776 | 44.6104 | 43.3757 | 23 | 3.9619 | 3.4775 | 3.7910 | 2.8469 |
3 | 31.4777 | 30.6419 | 31.3852 | 30.5404 | 24 | 6.3395 | 6.9598 | 7.1139 | 7.3705 |
4 | 40.8836 | 40.6835 | 41.2298 | 40.2889 | 25 | 8.7636 | 9.3934 | 9.4446 | 9.8572 |
5 | 45.1716 | 46.0254 | 45.7397 | 45.6811 | 26 | 4.3122 | 8.1862 | 9.3348 | 7.5598 |
6 | 38.7853 | 38.8103 | 38.4267 | 38.6532 | 27 | 28.1567 | 26.5213 | 26.9289 | 27.1962 |
7 | 34.0998 | 40.3718 | 38.9514 | 36.5221 | 28 | 10.8685 | 7.1685 | 8.1045 | 8.8196 |
8 | 1.9086 | 9.2172 | 3.1440 | 0.2566 | 29 | 1.4134 | 1.9080 | 2.7821 | 0.8442 |
9 | 25.8442 | 22.0831 | 23.7882 | 25.0715 | 30 | 10.1178 | 5.4462 | 5.4113 | 6.1364 |
10 | 22.4069 | 13.9856 | 6.1048 | 7.2179 | 31 | 10.7265 | 7.1441 | 8.0559 | 8.7329 |
11 | 14.6906 | 13.3366 | 13.3710 | 11.9650 | 32 | 5.9264 | 3.8187 | 3.2626 | 3.9279 |
12 | 13.5454 | 10.3683 | 13.2505 | 13.0898 | 33 | 7.4464 | 6.9079 | 4.3595 | 3.8564 |
13 | 48.4644 | 28.8257 | 29.2884 | 31.0595 | 34 | 4.2746 | 4.2621 | 4.2644 | 4.2649 |
14 | 43.4359 | 43.8016 | 41.2053 | 40.2306 | 35 | 2.9917 | 9.9742 | 6.2947 | 4.7208 |
15 | 29.2591 | 25.9076 | 26.0431 | 26.3193 | 36 | 33.0062 | 30.3584 | 27.8713 | 25.9812 |
16 | 46.5368 | 39.8101 | 20.2248 | 31.1723 | 37 | 16.2977 | 15.4280 | 15.8463 | 14.5274 |
17 | 9.3830 | 7.8217 | 7.6213 | 8.2148 | 38 | 11.2768 | 10.8759 | 11.0532 | 11.0848 |
18 | 23.4450 | 18.3971 | 17.8870 | 19.4660 | 39 | 0.5275 | 0.5958 | 0.5447 | 2.9151 |
19 | 10.7910 | 7.4358 | 6.9576 | 7.9322 | 40 | 6.4117 | 5.7153 | 5.5762 | 5.2771 |
20 | 2.9020 | 1.5656 | 1.7314 | 1.7333 | 41 | 19.7638 | 25.5606 | 22.9897 | 21.0860 |
21 | 6.7331 | 3.7340 | 3.7371 | 4.1038 | - | - | - | - | - |
Other goals for minimizing losses and voltage deviation are shown in Table 13. The total system loss is minimized by WOA from 6.9355 MW to 6.1216 MW. This loss reduction is an indicator of the effective congestion management achieved by the proposed WOA approach. As shown in Table 13, the deviation of the load bus voltage from the nominal value is minimal, confirming the suitability of the proposed approach for alleviating congestion on transmission lines.
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 6.9355 | 6.1561 | 6.1261 | 6.1216 |
Voltage deviation (p.u.) | 0.7313 | 0.2249 | 0.2036 | 0.1999 |
Objective values of voltage deviation and loss produced by the algorithms used are given in Table 14 for comparison. The best and worst values of loss and voltage deviation reported by WOA are encouraging when compared to that of the values by PSO and FFA algorithms. The time taken by WOA for achieving the best results is less than the time required by PSO and FFA algorithms. This shows the speed of convergence of WOA.
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.1561 | 6.1261 | 6.1216 |
Worst | 7.0456 | 6.5683 | 6.1593 | |
Voltage deviation (p.u.) | Best | 0.2249 | 0.2036 | 0.1999 |
Worst | 0.3657 | 0.3197 | 0.2034 | |
Execution time (Sec) | 156.63 | 153.68 | 150.23 |
Best control variable values, corresponding to congestion management in this case, are shown in Table 15. It is maintained that all the variables are taking values within the respective limits. It is recommended that these values are the highly suitable for relieving congestion and minimizing loss and voltage deviation.
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0436 | 1.0582 | 1.0236 |
V2(p.u.) | 1.0363 | 1.0425 | 1.0200 |
V5(p.u.) | 1.0210 | 1.0113 | 0.9881 |
V8(p.u.) | 1.0102 | 1.0169 | 0.9999 |
V11(p.u.) | 1.0283 | 1.0177 | 1.0364 |
V13(p.u.) | 1.0639 | 1.0205 | 1.0554 |
T11(p.u.) | 0.9808 | 1.0222 | 1.0263 |
T12(p.u.) | 1.0864 | 0.9858 | 0.9508 |
T15(p.u.) | 1.0814 | 1.0113 | 1.0021 |
T36(p.u.) | 0.9156 | 0.9508 | 0.9762 |
SVC1(p.u.) | 2.4780 | 6.4882 | 6.9114 |
SVC2(p.u.) | 5.1137 | 4.5855 | 4.5718 |
TCSC1(p.u.) | 0.1826 | -0.1952 | 0.1972 |
TCSC2 (p.u.) | 0.1114 | -0.2854 | -0.0458 |
From the information about the locations, identified by the three algorithms, for the FACTS devices for this case is as given in Table 16.
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 12 | 19 | 29 |
SVC2 | 18 | 23 | 22 |
TCSC1 | 12 | 7 | 37 |
TCSC2 | 16 | 20 | 33 |
Figure 7 shows the convergence characteristics of WOA. It is clear that WOA outperforms the two other algorithms in this multilateral transaction case. The proposed algorithm further optimizes the desired value and prevents the algorithm from easily being trapped in local minima.
This work employs a novel biologically-inspired WOA to find the optimal location and size of SVC and TCSC controllers in the grid to alleviate congestion. Parallel-connected SVCs and series-connected TCSC compensators were used for congestion management. For SVC and TCSC allocation issues, appropriate location and size of the FACTS controllers that remove line flow violation, minimize loss, and minimize voltage excursions in the load bus are considered. The results show that WOA produces low ratings for SVC and TCSC controllers, ensuring low capital cost of the devices. Therefore, the WOA method can be used as an efficient technique to solve the optimal allocation of FACTS compensators in congestion management problems. Comparing the results obtained from other algorithms, the PSO and FFA algorithms, and their convergence properties, it is clear that the WOA-based method outperforms the others.
The work can be enhanced in the future by considering other FACTS devices like SSSC, STATCOM, UPFC or by using the multi objective optimization approaches.
The authors declare they have not used artificial intelligence (AI) tools in the creation of this article.
The authors have no conflict of interest
[1] | WHO, Obesity and Overweight, World Health Organization, 2020. Available from: https://wwwwhoint/news-room/fact-sheets/detail/obesity-and-overweight. |
[2] |
A. Hruby, J. E. Manson, L. Qi, V. S. Malik, E. B. Rimm, Q. Sun, W. C. Willett, F. B. Hu, Determinants and consequences of obesity, Am. J. Public Health, 106 (2016), 1656-1662. https://doi.org/https://doi.org/10.2105/AJPH.2016.303326 doi: 10.2105/AJPH.2016.303326
![]() |
[3] | WHO, The top 10 causes of death, World Health Organization, 2018. Available from: https://wwwwhoint/news-room/fact-sheets/detail/the-top-10-causes-of-death. |
[4] | WHO, 10 facts on obesity, World Health Organization, 2017. Available from: https://wwwwhoint/features/factfiles/obesity/en/.. |
[5] |
J. Cawley, C. Meyerhoefer, The medical care costs of obesity: An instrumental variables approach, J. Health Econ., 31 (2012), 219-230. https://doi.org/10.1016/j.jhealeco.2011.10.003 doi: 10.1016/j.jhealeco.2011.10.003
![]() |
[6] |
L. Angrisani, A. Santonicola, P. Iovino, G. Formisani, H. Buchwald, N. Scopinaro, Bariatric Surgery Worldwide 2013, Obes. Surg., 25 (2015), 1822-1832. https://doi.org/10.1007/s11695-015-1657-z doi: 10.1007/s11695-015-1657-z
![]() |
[7] | T. Bhurosy, R. Jeewon, Overweight and obesity epidemic in developing countries: A problem with diet, physical activity, or socioeconomic status? Scientific World Journal, 2014 (2014). https://doi.org/10.1155/2014/964236 |
[8] | E. Alpaydin, Introduction to Machine Learning, Cambridge: MIT press, 2014. |
[9] | N. S. Rajliwall, R. Davey, G. Chetty, Machine learning based models for cardiovascular risk prediction, International Conference on Machine Learning and Data Engineering 2018, (iCMLDE), (2018), 142-148. https://doi.org/10.1109/iCMLDE.2018.00034 |
[10] |
J. B. Heaton, N. G. Polson, J. H. Witte, Deep learning for finance: deep portfolios, Appl. Stoch. Model. Bus., 33 (2017), 3-12. https://doi.org/10.1002/asmb.2209 doi: 10.1002/asmb.2209
![]() |
[11] | J. Kim, J. Canny, Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention, Proceedings of the IEEE International Conference on Computer Vision, (2017), 2942-2950. https://doi.org/10.1109/ICCV.2017.320 |
[12] |
D. Gruson, T. Helleputte, P. Rousseau, D. Gruson, Data science, artificial intelligence, and machine learning: Opportunities for laboratory medicine and the value of positive regulation, Clin. Biochem., 69 (2019), 1-7. https://doi.org/10.1016/j.clinbiochem.2019.04.013 doi: 10.1016/j.clinbiochem.2019.04.013
![]() |
[13] |
D. Panaretos, E. Koloverou, A. C. Dimopoulos, G. M. Kouli, M. Vamvakari, G. Tzavelas, C. Pitsavos, D. B. Panagiotakos, A comparison of statistical and machine-learning techniques in evaluating the association between dietary patterns and 10-year cardiometabolic risk (2002-2012): The ATTICA study, Brit. J. Nutr., 120 (2018), 326-334. https://doi.org/10.1017/S0007114518001150 doi: 10.1017/S0007114518001150
![]() |
[14] | H. C. Koh, G. Tan, Data Mining Applications in Healthcare, Journal of Healthcare Information Management, 19 (2011), 64-72. |
[15] |
K. Kourou, T. P. Exarchos, K. P. Exarchos, M. V. Karamouzis, D. I. Fotiadis, Machine learning applications in cancer prognosis and prediction, Comput. Struct. Biotec., 13 (2015), 8-17. https://doi.org/10.1016/j.csbj.2014.11.005 doi: 10.1016/j.csbj.2014.11.005
![]() |
[16] |
V. Gulshan, L. Peng, M. Coram, M. C. Stumpe, D. Wu, A. Narayanaswamy, S. Venugopalan, K. Widner, et al., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA - Journal of the American Medical Association, 316 (2016), 2402-2410. https://doi.org/10.1001/jama.2016.17216 doi: 10.1001/jama.2016.17216
![]() |
[17] | Y. Xing, J. Wang, Z. Zhao, Combination data mining methods with new medical data to predicting outcome of Coronary Heart Disease, International Conference on Convergence Information Technology, (ICCIT) 2007, (2007), 868-872. https://doi.org/10.1109/ICCIT.2007.4420369 |
[18] | P. Fränti, S. Sieranoja, K. Wikströ m, T. Laatikainen, Clustering diagnoses from 58M patient visits in Finland during 2015-2018, JMIR Medical Informatics, (2022). https://doi.org/10.2196/35422 |
[19] |
Z. Obermeyer, E. J. Emanuel, Predicting the Future: Big Data, Machine Learning, and Clinical Medicine, The New England journal of medicine, 375 (2016), 1216-1219. https://doi.org/doi:10.1056/NEJMp1606181 doi: 10.1056/NEJMp1606181
![]() |
[20] |
M. A. Morris, E. Wilkins, K. A. Timmins, M. Bryant, M. Birkin, C. Griffiths, Can big data solve a big problem? Reporting the obesity data landscape in line with the Foresight obesity system map, Int. J. Obesity, 42 (2018), 1963-1976. https://doi.org/10.1038/s41366-018-0184-0 doi: 10.1038/s41366-018-0184-0
![]() |
[21] |
C. Y. J. Peng, K. L. Lee, G. M. Ingersoll, An introduction to logistic regression analysis and reporting, J. Educ. Res., 96 (2002), 3-14. https://doi.org/10.1080/00220670209598786 doi: 10.1080/00220670209598786
![]() |
[22] | D. Dietrich, B. Heller, Y. Beibei, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Indianapolis: Wiley, 2015. |
[23] |
H. O. Alanazi, A. H. Abdullah, K. N. Qureshi, A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care, J. Med. Syst., 41 (2017), 1-10. https://doi.org/10.1007/s10916-017-0715-6 doi: 10.1007/s10916-017-0715-6
![]() |
[24] |
Y. Y. Song, L. U. Ying, Decision tree methods: applications for classification and prediction, Shanghai Archives of Psychiatry, 27 (2015), 130-135. https://doi.org/10.11919/j.issn.1002-0829.215044 doi: 10.11919/j.issn.1002-0829.215044
![]() |
[25] |
M. Pal, Random forest classifier for remote sensing classification, Int. J. Remote Sens., 26 (2005), 217-222. https://doi.org/10.1080/01431160412331269698 doi: 10.1080/01431160412331269698
![]() |
[26] | S. V. Vishwanathan, M. N. Murty, SSVM: A simple SVM algorithm, International Joint Conference on Neural Networks (IJCNN) 2002, 3 (2002), 2393-2398. https://doi.org/10.1109/IJCNN.2002.1007516 |
[27] |
Y. Qu, B. Fang, W. Zhang, R. Tang, M. Niu, H. Guo, Y. Yu, X. He, Product-Based Neural Networks for User Response Prediction over Multi-Field Categorical Data, ACM T. Inform. Syst., 37 (2019), 1-35. https://doi.org/10.1145/3233770 doi: 10.1145/3233770
![]() |
[28] | T. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2016), 785-794. https://doi.org/10.1145/2939672.2939785 |
[29] |
A. T. C. Goh, Back-propagation neural networks for modeling complex systems, Artificial Intelligence in Engineering, 9 (1995), 143-151. https://doi.org/10.1016/0954-1810(94)00011-S doi: 10.1016/0954-1810(94)00011-S
![]() |
[30] |
Y. Lecun, Y. Bengio, G. Hinton, Deep learning, Nature, 521 (2015), 436-444. https://doi.org/10.1038/nature14539 doi: 10.1038/nature14539
![]() |
[31] |
A. K. Jain, M. N. Murty, P. J. Flynn, Data clustering: A review, ACM Comput. Surv., 31 (1999), 264-323. https://doi.org/10.1145/331499.331504 doi: 10.1145/331499.331504
![]() |
[32] |
H. Arksey, L. O'Malley, Scoping studies: towards a methodological framework, Int. J. Soc. Res. Method., 8 (2005), 19-32. https://doi.org/10.1080/1364557032000119616 doi: 10.1080/1364557032000119616
![]() |
[33] |
H. So, L. McLaren, G. C. Currie, The relationship between health eating and overweight/obesity in Canada: cross-sectional study using the CCHS, Obesity Science and Practice, 3 (2017), 399-406. https://doi.org/10.1002/osp4.123 doi: 10.1002/osp4.123
![]() |
[34] | N. Daud, N. L. Mohd Noor, S. A. Aljunid, N. Noordin, N. I. M. F. Teng, Predictive Analytics: The Application of J48 Algorithm on Grocery Data to Predict Obesity, 2018 IEEE Conference on Big Data and Analytics, ICBDA, (2018), 1-6. https://doi.org/10.1109/ICBDAA.2018.8629623 |
[35] |
J. F. Easton, H. Román Sicilia, C. R. Stephens, Classification of diagnostic subcategories for obesity and diabetes based on eating patterns, Nutr. Diet., 76 (2019), 104-109. https://doi.org/10.1111/1747-0080.12495 doi: 10.1111/1747-0080.12495
![]() |
[36] |
J. Dunstan, M. Aguirre, M. Bastías, C. Nau, T. A. Glass, F. Tobar, Predicting nationwide obesity from food sales using machine learning, Health Inform. J., 26 (2019), 652-663. https://doi.org/10.1177/1460458219845959 doi: 10.1177/1460458219845959
![]() |
[37] |
N. Kanerva, J. Kontto, M. Erkkola, J. Nevalainen, S. Mannisto, Suitability of random forest analysis for epidemiological research: Exploring sociodemographic and lifestyle-related risk factors of overweight in a cross-sectional design, Scand. J. Public Health, 46 (2018), 557-564. https://doi.org/10.1177/1403494817736944 doi: 10.1177/1403494817736944
![]() |
[38] |
K. W. DeGregory, P. Kuiper, T. DeSilvio, J. D. Pleuss, R. Miller, J. W. Roginski, C. B. Fisher, D. Harness, et al., A review of machine learning in obesity, Obes. Rev., 19 (2018), 668-685. https://doi.org/10.1111/obr.12667 doi: 10.1111/obr.12667
![]() |
[39] | D. Kim, W. Hou, F. Wang, C. Arcan, Factors Affecting Obesity and Waist Circumference Among US Adults, Prev. Chronic Dis., 16 (2019). https://doi.org/10.5888/pcd16.180220 |
[40] |
R. L. Figueroa, C. A. Flores, Extracting Information from Electronic Medical Records to Identify the Obesity Status of a Patient Based on Comorbidities and Bodyweight Measures, J. Med. Syst., 40 (2016). https://doi.org/10.1007/s10916-016-0548-8 doi: 10.1007/s10916-016-0548-8
![]() |
[41] |
M. A. Green, M. Strong, F. Razak, S. V. Subramanian, C. Relton, P. Bissell, Who are the obese? A cluster analysis exploring subgroups of the obese, J. Public Health (UK), 38 (2016), 258-264. https://doi.org/10.1093/pubmed/fdv040 doi: 10.1093/pubmed/fdv040
![]() |
[42] |
P. P. Brzan, Z. Obradovic, G. Stiglic, Contribution of temporal data to predictive performance in 30-day readmission of morbidly obese patients, PeerJ, 5 (2017), e3230. https://doi.org/10.7717/peerj.3230 doi: 10.7717/peerj.3230
![]() |
[43] |
A. Kupusinac, E. Stokić, R. Doroslovački, Predicting body fat percentage based on gender, age and BMI by using artificial neural networks, Comput. Meth. Prog. Bio., 113 (2014), 610-619. https://doi.org/10.1016/j.cmpb.2013.10.013 doi: 10.1016/j.cmpb.2013.10.013
![]() |
[44] |
M. Batterham, L. Tapsell, K. Charlton, J. O'shea, R. Thorne, Using data mining to predict success in a weight loss trial, J. Hum. Nutr. Diet., 30 (2017), 471-478. https://doi.org/10.1111/jhn.12448 doi: 10.1111/jhn.12448
![]() |
[45] | Z. Feng, L. Mo, M. Li, A Random Forest-based ensemble method for activity recognition, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2015 EMBS, (2015), 5074-5077. https://doi.org/10.1109/EMBC.2015.7319532 |
[46] |
M. Batterham, E. Neale, A. Martin, L. Tapsell, Data mining: Potential applications in research on nutrition and health, Nutr. Diet., 74 (2017), 3-10. https://doi.org/10.1111/1747-0080.12337 doi: 10.1111/1747-0080.12337
![]() |
[47] |
W. J. Heerman, N. Jackson, M. Hargreaves, S. A. Mulvaney, D. Schlundt, K. A. Wallston, R. L. Rothman, Clusters of Healthy and Unhealthy Eating Behaviors Are Associated With Body Mass Index Among Adults, J. Nutr. Educ. Behav., 49 (2017), 415-421. https://doi.org/10.1016/j.jneb.2017.02.001 doi: 10.1016/j.jneb.2017.02.001
![]() |
[48] | I. Sarasfis, C. Diou, I. Ioakimidis, A. Delopoulos, Assessment of In-Meal Eating Behaviour using Fuzzy SVM, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (2019), 6939-6942. https://doi.org/10.1109/EMBC.2019.8857606 |
[49] |
P. Pouladzadeh, S. Shirmohammadi, A. Bakirov, A. Bulut, A. Yassine, Cloud-based SVM for food categorization, Multimed. Tools Appl., 74 (2015), 5243-5260. https://doi.org/10.1007/s11042-014-2116-x doi: 10.1007/s11042-014-2116-x
![]() |
[50] |
E. J. Heravi, H. Habibi Aghdam, D. Puig, A deep convolutional neural network for recognizing foods, Eighth International Conference on Machine Vision (ICMV), 9875 (2015), 98751D. https://doi.org/10.1117/12.2228875 doi: 10.1117/12.2228875
![]() |
[51] |
E. Disse, S. Ledoux, C. Bétry, C. Caussy, C. Maitrepierre, M. Coupaye, M. Laville, C. Simon, An artificial neural network to predict resting energy expenditure in obesity, Clin. Nutr., 37 (2018), 1661-1669. https://doi.org/10.1016/j.clnu.2017.07.017 doi: 10.1016/j.clnu.2017.07.017
![]() |
[52] |
N. Cesare, P. Dwivedi, Q. C. Nguyen, E. O. Nsoesie, Use of social media, search queries, and demographic data to assess obesity prevalence in the United States, Palgrave Communications, 5 (2019), 1-9. https://doi.org/10.1057/s41599-019-0314-x doi: 10.1057/s41599-019-0314-x
![]() |
[53] | P. Kuhad, A. Yassine, S. Shimohammadi, Using distance estimation and deep learning to simplify calibration in food calorie measurement, IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA, (2015), 1-6. https://doi.org/10.1109/CIVEMSA.2015.7158594 |
[54] |
K. Shameer, K. W. Johnson, B. S. Glicksberg, J. T. Dudley, P. P. Sengupta, Machine learning in cardiovascular medicine: Are we there yet? Heart, 104 (2018), 1156-1164. https://doi.org/10.1136/heartjnl-2017-311198 doi: 10.1136/heartjnl-2017-311198
![]() |
[55] |
B. A. Goldstein, A. M. Navar, R. E. Carter, Moving beyond regression techniques in cardiovascular risk prediction: Applying machine learning to address analytic challenges, Eur. Heart J., 38 (2017), 1805-1814. https://doi.org/10.1093/eurheartj/ehw302 doi: 10.1093/eurheartj/ehw302
![]() |
[56] |
N. Jothi, N. A. A. Rashid, W. Husain, Data Mining in Healthcare - A Review, Procedia Computer Science, 72 (2015), 306-313. https://doi.org/10.1016/j.procs.2015.12.145 doi: 10.1016/j.procs.2015.12.145
![]() |
[57] |
A. L. Beam, I. S. Kohane, Big data and machine learning in health care, JAMA - Journal of the American Medical Association, 319 (2018), 1317-1318. https://doi.org/10.1001/jama.2017.18391 doi: 10.1001/jama.2017.18391
![]() |
[58] |
A. Mozumdar, G. Liguori, Corrective Equations to Self-Reported Height and Weight for Obesity Estimates among U.S. Adults: NHANES 1999-2008, Res. Q. Exercise Sport, 87 (2016), 47-58. https://doi.org/10.1080/02701367.2015.1124971 doi: 10.1080/02701367.2015.1124971
![]() |
[59] |
M. Stommel, C. A. Schoenborn, Accuracy and usefulness of BMI measures based on self-reported weight and height: Findings from the NHANES & NHIS 2001-2006, BMC Public Health, 9 (2009), 1-10. https://doi.org/10.1186/1471-2458-9-421 doi: 10.1186/1471-2458-9-421
![]() |
[60] |
D. Rativa, B. J. T. Fernandes, A. Roque, Height and Weight Estimation from Anthropometric Measurements Using Machine Learning Regressions, IEEE J. Transl. Eng. He., 6 (2018), 1-9. https://doi.org/10.1109/JTEHM.2018.2797983 doi: 10.1109/JTEHM.2018.2797983
![]() |
[61] |
J. A. Sáez, J. Luengo, F. Herrera, Predicting noise filtering efficacy with data complexity measures for nearest neighbor classification, Pattern Recogn., 46 (2013), 355-364. https://doi.org/10.1016/j.patcog.2012.07.009 doi: 10.1016/j.patcog.2012.07.009
![]() |
[62] |
T. Ferenci, L. Kovács, Predicting body fat percentage from anthropometric and laboratory measurements using artificial neural networks, Applied Soft Computing Journal, 67 (2018), 834-839. https://doi.org/10.1016/j.asoc.2017.05.063 doi: 10.1016/j.asoc.2017.05.063
![]() |
[63] |
S. P. Goldstein, F. Zhang, J. G. Thomas, M. L. Butryn, J. D. Herbert, E. M. Forman, Application of Machine Learning to Predict Dietary Lapses During Weight Loss, Journal of Diabetes Science and Technology, 12 (2018), 1045-1052. https://doi.org/10.1177/1932296818775757 doi: 10.1177/1932296818775757
![]() |
1. | Songbai Guo, Qianqian Pan, Jing‐An Cui, P. Damith Nilanga Silva, Global behavior and optimal control of a dengue transmission model with standard incidence rates and self‐protection, 2024, 0170-4214, 10.1002/mma.10351 | |
2. | Liping Wang, Xinyu Wang, Dajun Liu, Xuekang Zhang, Peng Wu, Dynamical analysis of a heterogeneous spatial diffusion Zika model with vector-bias and environmental transmission, 2024, 32, 2688-1594, 1308, 10.3934/era.2024061 |
Case | Cause of congestion | |
Case 1 | 35 % overload at all the load buses. | |
Case 2 | 11.5 MW of bilateral power transaction between GENCO 13 and DISCO 26 | |
Case 3 | GENCOS Generator 8-11MW Generator 11-10 MW Total 21 MW |
DISCOS Load bus 21-8 MW Load bus 29-13 MW Total 21 MW |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 131.2674 | 127.1166 | 128.2412 | 125.1989 | 22 | 9.8363 | 8.1865 | 8.7090 | 8.6592 |
2 | 77.7204 | 75.0097 | 75.8193 | 74.2556 | 23 | 5.2405 | 3.6808 | 4.2064 | 5.1400 |
3 | 45.1248 | 43.2307 | 43.2015 | 42.7181 | 24 | 8.5512 | 10.2505 | 9.7927 | 8.8475 |
4 | 72.8314 | 69.4883 | 69.6251 | 68.8218 | 25 | 11.9157 | 13.7223 | 13.2309 | 11.8875 |
5 | 74.1643 | 74.1887 | 74.4739 | 73.6354 | 26 | 6.6694 | 11.5236 | 11.4966 | 11.2112 |
6 | 59.3274 | 57.8368 | 58.0393 | 56.8173 | 27 | 28.9593 | 29.1638 | 27.9801 | 22.4926 |
7 | 63.3811 | 64.4707 | 65.7898 | 64.8420 | 28 | 10.8002 | 9.1367 | 8.4401 | 7.3881 |
8 | 7.93120 | 12.8620 | 15.2268 | 12.2036 | 29 | 1.7056 | 3.8475 | 2.9429 | 4.1995 |
9 | 37.5064 | 36.5992 | 36.3548 | 37.1752 | 30 | 10.5278 | 4.4165 | 3.6045 | 3.3333 |
10 | 22.1891 | 22.9065 | 23.4902 | 27.6507 | 31 | 10.6332 | 9.0324 | 8.3738 | 7.3340 |
11 | 25.4170 | 23.1346 | 21.7937 | 21.5930 | 32 | 5.6166 | 3.3569 | 2.2172 | 2.8031 |
12 | 18.3791 | 17.6891 | 17.2740 | 15.4786 | 33 | 4.2880 | 0.8294 | 3.9745 | 3.7617 |
13 | 47.4478 | 27.0789 | 20.3210 | 27.9462 | 34 | 5.8192 | 5.7996 | 5.7937 | 5.7936 |
14 | 46.4785 | 46.9837 | 42.1148 | 43.9273 | 35 | 3.5019 | 6.4873 | 9.4731 | 9.3541 |
15 | 42.8541 | 38.7400 | 37.0566 | 36.9979 | 36 | 30.9965 | 25.3566 | 24.6979 | 24.8266 |
16 | 53.8331 | 37.2635 | 38.4911 | 48.4069 | 37 | 8.8276 | 8.9778 | 8.7456 | 8.7457 |
17 | 12.0257 | 10.3300 | 10.2700 | 10.7133 | 38 | 10.0438 | 9.8753 | 9.9441 | 9.9443 |
18 | 29.0165 | 23.1251 | 22.8826 | 21.3487 | 39 | 5.1140 | 6.0776 | 5.0914 | 5.0914 |
19 | 13.6922 | 9.3345 | 9.2472 | 9.2246 | 40 | 1.7674 | 2.9780 | 2.8456 | 2.4313 |
20 | 3.2679 | 1.5180 | 1.4580 | 2.2925 | 41 | 20.3357 | 2.0586 | 2.7997 | 23.9190 |
21 | 8.1316 | 4.2744 | 4.1385 | 3.9422 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 15.2375 | 13.3491 | 13.3481 | 13.162 |
Voltage deviation (p.u.) | 0.9000 | 0.4368 | 0.3423 | 0.3327 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 13.3491 | 13.3481 | 13.162 |
Worst | 13.8762 | 13.6539 | 13.4356 | |
Voltage deviation (p.u.) | Best | 0.4368 | 0.3423 | 0.3327 |
Worst | 0.5789 | 0.4735 | 0.3465 | |
Execution time (Sec) | 124.68 | 122.53 | 120.34 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0866 | 1.0901 | 1.0822 |
V2(p.u.) | 1.0688 | 1.0611 | 1.0565 |
V5(p.u.) | 1.0380 | 1.0292 | 1.0301 |
V8(p.u.) | 1.0333 | 1.0243 | 1.0234 |
V11(p.u.) | 1.0690 | 1.0124 | 1.0664 |
V13(p.u.) | 1.0612 | 1.0644 | 1.0806 |
T11(p.u.) | 1.0033 | 0.9839 | 1.0144 |
T12(p.u.) | 1.0081 | 0.9489 | 1.0876 |
T15(p.u.) | 1.0513 | 1.0433 | 1.0876 |
T36(p.u.) | 1.0302 | 0.9454 | 0.9519 |
SVC1(p.u.) | 1.0074 | 3.2545 | 8.8528 |
SVC2(p.u.) | 8.8143 | 1.5495 | 8.9837 |
TCSC1(p.u.) | 0.2000 | -0.2768 | -0.2483 |
TCSC2 (p.u.) | 0.1627 | -0.3371 | 0.1804 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 4 | 13 | 21 |
SVC2 | 29 | 28 | 19 |
TCSC1 | 37 | 22 | 17 |
TCSC2 | 21 | 28 | 25 |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 57.0233 | 58.8873 | 56.6586 | 57.8673 | 22 | 8.3147 | 7.0358 | 7.1936 | 6.7068 |
2 | 43.6815 | 43.6303 | 44.0706 | 42.7216 | 23 | 4.8852 | 3.6846 | 3.8941 | 3.6183 |
3 | 31.0181 | 29.9268 | 29.4216 | 29.8110 | 24 | 5.2431 | 6.6591 | 6.6733 | 6.3522 |
4 | 40.6146 | 40.1990 | 40.7333 | 39.5424 | 25 | 7.6561 | 9.1047 | 9.1003 | 8.8002 |
5 | 45.4808 | 46.1908 | 46.0554 | 46.7183 | 26 | 2.6326 | 7.1752 | 8.4684 | 7.4627 |
6 | 39.6320 | 39.5434 | 38.9485 | 38.5417 | 27 | 21.9695 | 19.7922 | 22.3958 | 21.5405 |
7 | 39.8581 | 42.4776 | 42.9750 | 42.1190 | 28 | 11.3091 | 8.5998 | 8.9210 | 7.8082 |
8 | 2.3672 | 9.1103 | 8.6955 | 8.9257 | 29 | 1.5164 | 2.6761 | 1.4691 | 2.0758 |
9 | 25.7829 | 22.0543 | 22.0906 | 21.5574 | 30 | 10.8513 | 7.0932 | 7.4625 | 6.1584 |
10 | 24.7471 | 13.9963 | 14.2904 | 18.7578 | 31 | 11.1538 | 8.5580 | 8.8641 | 7.7619 |
11 | 15.7261 | 13.2819 | 14.2110 | 13.0692 | 32 | 8.0211 | 5.5036 | 6.0923 | 4.5671 |
12 | 12.4440 | 12.0949 | 11.8807 | 11.1906 | 33 | 9.8490 | 7.0819 | 7.5262 | 5.1054 |
13 | 43.3236 | 23.4617 | 25.2978 | 22.4414 | 34 | 16.1233 | 14.8868 | 16.0375 | 12.8579 |
14 | 34.9827 | 34.0180 | 32.9252 | 33.0242 | 35 | 7.0327 | 9.6894 | 10.2188 | 11.6211 |
15 | 22.6015 | 18.8723 | 19.8619 | 19.8234 | 36 | 29.2238 | 23.4491 | 23.8081 | 23.5225 |
16 | 51.3706 | 31.2894 | 31.1382 | 41.8936 | 37 | 6.4457 | 6.4123 | 6.4136 | 6.4103 |
17 | 9.7744 | 8.3627 | 8.2823 | 8.1735 | 38 | 7.3265 | 7.2860 | 7.2875 | 7.2836 |
18 | 25.0675 | 20.4409 | 21.1225 | 19.6811 | 39 | 3.7625 | 3.7533 | 3.7537 | 3.7528 |
19 | 12.4633 | 9.3543 | 9.8376 | 9.8049 | 40 | 5.0213 | 3.4364 | 3.9863 | 3.2971 |
20 | 3.2225 | 2.0372 | 2.5218 | 1.8469 | 41 | 17.9584 | 20.0304 | 19.8285 | 20.5734 |
21 | 8.2686 | 5.6617 | 6.5755 | 6.2436 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 7.1254 | 6.6698 | 6.5439 | 6.1930 |
Voltage deviation (p.u.) | 0.7370 | 0.2172 | 0.1747 | 0.1678 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.6698 | 6.5439 | 6.1930 |
Worst | 6.9875 | 6.8976 | 6.5432 | |
Voltage deviation (p.u.) | Best | 0.217 | 0.1747 | 0.1678 |
Worst | 0.245 | 0.1954 | 0.1726 | |
Execution time (Sec) | 203.68 | 200.83 | 117.34 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0491 | 1.0323 | 1.0381 |
V2(p.u.) | 1.0314 | 1.0215 | 1.0219 |
V5(p.u.) | 1.0075 | 1.0053 | 1.0107 |
V8(p.u.) | 0.9992 | 0.9982 | 0.9990 |
V11(p.u.) | 0.9761 | 1.0472 | 1.0347 |
V13(p.u.) | 1.0330 | 1.0117 | 1.0582 |
T11(p.u.) | 0.9869 | 1.0130 | 1.0043 |
T12(p.u.) | 0.9591 | 0.9572 | 0.9983 |
T15(p.u.) | 0.9681 | 0.9651 | 1.0452 |
T36(p.u.) | 0.9625 | 0.9587 | 0.9345 |
SVC1(p.u.) | 9.3156 | 6.7702 | 2.3240 |
SVC2(p.u.) | 7.9593 | 6.0915 | 2.5471 |
TCSC1(p.u.) | 0.2000 | -0.2537 | -0.2810 |
TCSC2 (p.u.) | 0.2000 | -0.2276 | 0.1533 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 21 | 26 | 23 |
SVC2 | 25 | 15 | 19 |
TCSC1 | 13 | 40 | 19 |
TCSC2 | 15 | 4 | 9 |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 56.5202 | 57.8191 | 58.0784 | 57.6420 | 22 | 7.2961 | 6.1769 | 5.9659 | 6.2039 |
2 | 43.9787 | 43.7776 | 44.6104 | 43.3757 | 23 | 3.9619 | 3.4775 | 3.7910 | 2.8469 |
3 | 31.4777 | 30.6419 | 31.3852 | 30.5404 | 24 | 6.3395 | 6.9598 | 7.1139 | 7.3705 |
4 | 40.8836 | 40.6835 | 41.2298 | 40.2889 | 25 | 8.7636 | 9.3934 | 9.4446 | 9.8572 |
5 | 45.1716 | 46.0254 | 45.7397 | 45.6811 | 26 | 4.3122 | 8.1862 | 9.3348 | 7.5598 |
6 | 38.7853 | 38.8103 | 38.4267 | 38.6532 | 27 | 28.1567 | 26.5213 | 26.9289 | 27.1962 |
7 | 34.0998 | 40.3718 | 38.9514 | 36.5221 | 28 | 10.8685 | 7.1685 | 8.1045 | 8.8196 |
8 | 1.9086 | 9.2172 | 3.1440 | 0.2566 | 29 | 1.4134 | 1.9080 | 2.7821 | 0.8442 |
9 | 25.8442 | 22.0831 | 23.7882 | 25.0715 | 30 | 10.1178 | 5.4462 | 5.4113 | 6.1364 |
10 | 22.4069 | 13.9856 | 6.1048 | 7.2179 | 31 | 10.7265 | 7.1441 | 8.0559 | 8.7329 |
11 | 14.6906 | 13.3366 | 13.3710 | 11.9650 | 32 | 5.9264 | 3.8187 | 3.2626 | 3.9279 |
12 | 13.5454 | 10.3683 | 13.2505 | 13.0898 | 33 | 7.4464 | 6.9079 | 4.3595 | 3.8564 |
13 | 48.4644 | 28.8257 | 29.2884 | 31.0595 | 34 | 4.2746 | 4.2621 | 4.2644 | 4.2649 |
14 | 43.4359 | 43.8016 | 41.2053 | 40.2306 | 35 | 2.9917 | 9.9742 | 6.2947 | 4.7208 |
15 | 29.2591 | 25.9076 | 26.0431 | 26.3193 | 36 | 33.0062 | 30.3584 | 27.8713 | 25.9812 |
16 | 46.5368 | 39.8101 | 20.2248 | 31.1723 | 37 | 16.2977 | 15.4280 | 15.8463 | 14.5274 |
17 | 9.3830 | 7.8217 | 7.6213 | 8.2148 | 38 | 11.2768 | 10.8759 | 11.0532 | 11.0848 |
18 | 23.4450 | 18.3971 | 17.8870 | 19.4660 | 39 | 0.5275 | 0.5958 | 0.5447 | 2.9151 |
19 | 10.7910 | 7.4358 | 6.9576 | 7.9322 | 40 | 6.4117 | 5.7153 | 5.5762 | 5.2771 |
20 | 2.9020 | 1.5656 | 1.7314 | 1.7333 | 41 | 19.7638 | 25.5606 | 22.9897 | 21.0860 |
21 | 6.7331 | 3.7340 | 3.7371 | 4.1038 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 6.9355 | 6.1561 | 6.1261 | 6.1216 |
Voltage deviation (p.u.) | 0.7313 | 0.2249 | 0.2036 | 0.1999 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.1561 | 6.1261 | 6.1216 |
Worst | 7.0456 | 6.5683 | 6.1593 | |
Voltage deviation (p.u.) | Best | 0.2249 | 0.2036 | 0.1999 |
Worst | 0.3657 | 0.3197 | 0.2034 | |
Execution time (Sec) | 156.63 | 153.68 | 150.23 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0436 | 1.0582 | 1.0236 |
V2(p.u.) | 1.0363 | 1.0425 | 1.0200 |
V5(p.u.) | 1.0210 | 1.0113 | 0.9881 |
V8(p.u.) | 1.0102 | 1.0169 | 0.9999 |
V11(p.u.) | 1.0283 | 1.0177 | 1.0364 |
V13(p.u.) | 1.0639 | 1.0205 | 1.0554 |
T11(p.u.) | 0.9808 | 1.0222 | 1.0263 |
T12(p.u.) | 1.0864 | 0.9858 | 0.9508 |
T15(p.u.) | 1.0814 | 1.0113 | 1.0021 |
T36(p.u.) | 0.9156 | 0.9508 | 0.9762 |
SVC1(p.u.) | 2.4780 | 6.4882 | 6.9114 |
SVC2(p.u.) | 5.1137 | 4.5855 | 4.5718 |
TCSC1(p.u.) | 0.1826 | -0.1952 | 0.1972 |
TCSC2 (p.u.) | 0.1114 | -0.2854 | -0.0458 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 12 | 19 | 29 |
SVC2 | 18 | 23 | 22 |
TCSC1 | 12 | 7 | 37 |
TCSC2 | 16 | 20 | 33 |
Case | Cause of congestion | |
Case 1 | 35 % overload at all the load buses. | |
Case 2 | 11.5 MW of bilateral power transaction between GENCO 13 and DISCO 26 | |
Case 3 | GENCOS Generator 8-11MW Generator 11-10 MW Total 21 MW |
DISCOS Load bus 21-8 MW Load bus 29-13 MW Total 21 MW |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 131.2674 | 127.1166 | 128.2412 | 125.1989 | 22 | 9.8363 | 8.1865 | 8.7090 | 8.6592 |
2 | 77.7204 | 75.0097 | 75.8193 | 74.2556 | 23 | 5.2405 | 3.6808 | 4.2064 | 5.1400 |
3 | 45.1248 | 43.2307 | 43.2015 | 42.7181 | 24 | 8.5512 | 10.2505 | 9.7927 | 8.8475 |
4 | 72.8314 | 69.4883 | 69.6251 | 68.8218 | 25 | 11.9157 | 13.7223 | 13.2309 | 11.8875 |
5 | 74.1643 | 74.1887 | 74.4739 | 73.6354 | 26 | 6.6694 | 11.5236 | 11.4966 | 11.2112 |
6 | 59.3274 | 57.8368 | 58.0393 | 56.8173 | 27 | 28.9593 | 29.1638 | 27.9801 | 22.4926 |
7 | 63.3811 | 64.4707 | 65.7898 | 64.8420 | 28 | 10.8002 | 9.1367 | 8.4401 | 7.3881 |
8 | 7.93120 | 12.8620 | 15.2268 | 12.2036 | 29 | 1.7056 | 3.8475 | 2.9429 | 4.1995 |
9 | 37.5064 | 36.5992 | 36.3548 | 37.1752 | 30 | 10.5278 | 4.4165 | 3.6045 | 3.3333 |
10 | 22.1891 | 22.9065 | 23.4902 | 27.6507 | 31 | 10.6332 | 9.0324 | 8.3738 | 7.3340 |
11 | 25.4170 | 23.1346 | 21.7937 | 21.5930 | 32 | 5.6166 | 3.3569 | 2.2172 | 2.8031 |
12 | 18.3791 | 17.6891 | 17.2740 | 15.4786 | 33 | 4.2880 | 0.8294 | 3.9745 | 3.7617 |
13 | 47.4478 | 27.0789 | 20.3210 | 27.9462 | 34 | 5.8192 | 5.7996 | 5.7937 | 5.7936 |
14 | 46.4785 | 46.9837 | 42.1148 | 43.9273 | 35 | 3.5019 | 6.4873 | 9.4731 | 9.3541 |
15 | 42.8541 | 38.7400 | 37.0566 | 36.9979 | 36 | 30.9965 | 25.3566 | 24.6979 | 24.8266 |
16 | 53.8331 | 37.2635 | 38.4911 | 48.4069 | 37 | 8.8276 | 8.9778 | 8.7456 | 8.7457 |
17 | 12.0257 | 10.3300 | 10.2700 | 10.7133 | 38 | 10.0438 | 9.8753 | 9.9441 | 9.9443 |
18 | 29.0165 | 23.1251 | 22.8826 | 21.3487 | 39 | 5.1140 | 6.0776 | 5.0914 | 5.0914 |
19 | 13.6922 | 9.3345 | 9.2472 | 9.2246 | 40 | 1.7674 | 2.9780 | 2.8456 | 2.4313 |
20 | 3.2679 | 1.5180 | 1.4580 | 2.2925 | 41 | 20.3357 | 2.0586 | 2.7997 | 23.9190 |
21 | 8.1316 | 4.2744 | 4.1385 | 3.9422 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 15.2375 | 13.3491 | 13.3481 | 13.162 |
Voltage deviation (p.u.) | 0.9000 | 0.4368 | 0.3423 | 0.3327 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 13.3491 | 13.3481 | 13.162 |
Worst | 13.8762 | 13.6539 | 13.4356 | |
Voltage deviation (p.u.) | Best | 0.4368 | 0.3423 | 0.3327 |
Worst | 0.5789 | 0.4735 | 0.3465 | |
Execution time (Sec) | 124.68 | 122.53 | 120.34 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0866 | 1.0901 | 1.0822 |
V2(p.u.) | 1.0688 | 1.0611 | 1.0565 |
V5(p.u.) | 1.0380 | 1.0292 | 1.0301 |
V8(p.u.) | 1.0333 | 1.0243 | 1.0234 |
V11(p.u.) | 1.0690 | 1.0124 | 1.0664 |
V13(p.u.) | 1.0612 | 1.0644 | 1.0806 |
T11(p.u.) | 1.0033 | 0.9839 | 1.0144 |
T12(p.u.) | 1.0081 | 0.9489 | 1.0876 |
T15(p.u.) | 1.0513 | 1.0433 | 1.0876 |
T36(p.u.) | 1.0302 | 0.9454 | 0.9519 |
SVC1(p.u.) | 1.0074 | 3.2545 | 8.8528 |
SVC2(p.u.) | 8.8143 | 1.5495 | 8.9837 |
TCSC1(p.u.) | 0.2000 | -0.2768 | -0.2483 |
TCSC2 (p.u.) | 0.1627 | -0.3371 | 0.1804 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 4 | 13 | 21 |
SVC2 | 29 | 28 | 19 |
TCSC1 | 37 | 22 | 17 |
TCSC2 | 21 | 28 | 25 |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 57.0233 | 58.8873 | 56.6586 | 57.8673 | 22 | 8.3147 | 7.0358 | 7.1936 | 6.7068 |
2 | 43.6815 | 43.6303 | 44.0706 | 42.7216 | 23 | 4.8852 | 3.6846 | 3.8941 | 3.6183 |
3 | 31.0181 | 29.9268 | 29.4216 | 29.8110 | 24 | 5.2431 | 6.6591 | 6.6733 | 6.3522 |
4 | 40.6146 | 40.1990 | 40.7333 | 39.5424 | 25 | 7.6561 | 9.1047 | 9.1003 | 8.8002 |
5 | 45.4808 | 46.1908 | 46.0554 | 46.7183 | 26 | 2.6326 | 7.1752 | 8.4684 | 7.4627 |
6 | 39.6320 | 39.5434 | 38.9485 | 38.5417 | 27 | 21.9695 | 19.7922 | 22.3958 | 21.5405 |
7 | 39.8581 | 42.4776 | 42.9750 | 42.1190 | 28 | 11.3091 | 8.5998 | 8.9210 | 7.8082 |
8 | 2.3672 | 9.1103 | 8.6955 | 8.9257 | 29 | 1.5164 | 2.6761 | 1.4691 | 2.0758 |
9 | 25.7829 | 22.0543 | 22.0906 | 21.5574 | 30 | 10.8513 | 7.0932 | 7.4625 | 6.1584 |
10 | 24.7471 | 13.9963 | 14.2904 | 18.7578 | 31 | 11.1538 | 8.5580 | 8.8641 | 7.7619 |
11 | 15.7261 | 13.2819 | 14.2110 | 13.0692 | 32 | 8.0211 | 5.5036 | 6.0923 | 4.5671 |
12 | 12.4440 | 12.0949 | 11.8807 | 11.1906 | 33 | 9.8490 | 7.0819 | 7.5262 | 5.1054 |
13 | 43.3236 | 23.4617 | 25.2978 | 22.4414 | 34 | 16.1233 | 14.8868 | 16.0375 | 12.8579 |
14 | 34.9827 | 34.0180 | 32.9252 | 33.0242 | 35 | 7.0327 | 9.6894 | 10.2188 | 11.6211 |
15 | 22.6015 | 18.8723 | 19.8619 | 19.8234 | 36 | 29.2238 | 23.4491 | 23.8081 | 23.5225 |
16 | 51.3706 | 31.2894 | 31.1382 | 41.8936 | 37 | 6.4457 | 6.4123 | 6.4136 | 6.4103 |
17 | 9.7744 | 8.3627 | 8.2823 | 8.1735 | 38 | 7.3265 | 7.2860 | 7.2875 | 7.2836 |
18 | 25.0675 | 20.4409 | 21.1225 | 19.6811 | 39 | 3.7625 | 3.7533 | 3.7537 | 3.7528 |
19 | 12.4633 | 9.3543 | 9.8376 | 9.8049 | 40 | 5.0213 | 3.4364 | 3.9863 | 3.2971 |
20 | 3.2225 | 2.0372 | 2.5218 | 1.8469 | 41 | 17.9584 | 20.0304 | 19.8285 | 20.5734 |
21 | 8.2686 | 5.6617 | 6.5755 | 6.2436 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 7.1254 | 6.6698 | 6.5439 | 6.1930 |
Voltage deviation (p.u.) | 0.7370 | 0.2172 | 0.1747 | 0.1678 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.6698 | 6.5439 | 6.1930 |
Worst | 6.9875 | 6.8976 | 6.5432 | |
Voltage deviation (p.u.) | Best | 0.217 | 0.1747 | 0.1678 |
Worst | 0.245 | 0.1954 | 0.1726 | |
Execution time (Sec) | 203.68 | 200.83 | 117.34 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0491 | 1.0323 | 1.0381 |
V2(p.u.) | 1.0314 | 1.0215 | 1.0219 |
V5(p.u.) | 1.0075 | 1.0053 | 1.0107 |
V8(p.u.) | 0.9992 | 0.9982 | 0.9990 |
V11(p.u.) | 0.9761 | 1.0472 | 1.0347 |
V13(p.u.) | 1.0330 | 1.0117 | 1.0582 |
T11(p.u.) | 0.9869 | 1.0130 | 1.0043 |
T12(p.u.) | 0.9591 | 0.9572 | 0.9983 |
T15(p.u.) | 0.9681 | 0.9651 | 1.0452 |
T36(p.u.) | 0.9625 | 0.9587 | 0.9345 |
SVC1(p.u.) | 9.3156 | 6.7702 | 2.3240 |
SVC2(p.u.) | 7.9593 | 6.0915 | 2.5471 |
TCSC1(p.u.) | 0.2000 | -0.2537 | -0.2810 |
TCSC2 (p.u.) | 0.2000 | -0.2276 | 0.1533 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 21 | 26 | 23 |
SVC2 | 25 | 15 | 19 |
TCSC1 | 13 | 40 | 19 |
TCSC2 | 15 | 4 | 9 |
Line no. | MW flow before CM | MW flow after CM | Line no. | MW flow before CM | MW flow after CM | ||||
PSO | FFA | WOA | PSO | FFA | WOA | ||||
1 | 56.5202 | 57.8191 | 58.0784 | 57.6420 | 22 | 7.2961 | 6.1769 | 5.9659 | 6.2039 |
2 | 43.9787 | 43.7776 | 44.6104 | 43.3757 | 23 | 3.9619 | 3.4775 | 3.7910 | 2.8469 |
3 | 31.4777 | 30.6419 | 31.3852 | 30.5404 | 24 | 6.3395 | 6.9598 | 7.1139 | 7.3705 |
4 | 40.8836 | 40.6835 | 41.2298 | 40.2889 | 25 | 8.7636 | 9.3934 | 9.4446 | 9.8572 |
5 | 45.1716 | 46.0254 | 45.7397 | 45.6811 | 26 | 4.3122 | 8.1862 | 9.3348 | 7.5598 |
6 | 38.7853 | 38.8103 | 38.4267 | 38.6532 | 27 | 28.1567 | 26.5213 | 26.9289 | 27.1962 |
7 | 34.0998 | 40.3718 | 38.9514 | 36.5221 | 28 | 10.8685 | 7.1685 | 8.1045 | 8.8196 |
8 | 1.9086 | 9.2172 | 3.1440 | 0.2566 | 29 | 1.4134 | 1.9080 | 2.7821 | 0.8442 |
9 | 25.8442 | 22.0831 | 23.7882 | 25.0715 | 30 | 10.1178 | 5.4462 | 5.4113 | 6.1364 |
10 | 22.4069 | 13.9856 | 6.1048 | 7.2179 | 31 | 10.7265 | 7.1441 | 8.0559 | 8.7329 |
11 | 14.6906 | 13.3366 | 13.3710 | 11.9650 | 32 | 5.9264 | 3.8187 | 3.2626 | 3.9279 |
12 | 13.5454 | 10.3683 | 13.2505 | 13.0898 | 33 | 7.4464 | 6.9079 | 4.3595 | 3.8564 |
13 | 48.4644 | 28.8257 | 29.2884 | 31.0595 | 34 | 4.2746 | 4.2621 | 4.2644 | 4.2649 |
14 | 43.4359 | 43.8016 | 41.2053 | 40.2306 | 35 | 2.9917 | 9.9742 | 6.2947 | 4.7208 |
15 | 29.2591 | 25.9076 | 26.0431 | 26.3193 | 36 | 33.0062 | 30.3584 | 27.8713 | 25.9812 |
16 | 46.5368 | 39.8101 | 20.2248 | 31.1723 | 37 | 16.2977 | 15.4280 | 15.8463 | 14.5274 |
17 | 9.3830 | 7.8217 | 7.6213 | 8.2148 | 38 | 11.2768 | 10.8759 | 11.0532 | 11.0848 |
18 | 23.4450 | 18.3971 | 17.8870 | 19.4660 | 39 | 0.5275 | 0.5958 | 0.5447 | 2.9151 |
19 | 10.7910 | 7.4358 | 6.9576 | 7.9322 | 40 | 6.4117 | 5.7153 | 5.5762 | 5.2771 |
20 | 2.9020 | 1.5656 | 1.7314 | 1.7333 | 41 | 19.7638 | 25.5606 | 22.9897 | 21.0860 |
21 | 6.7331 | 3.7340 | 3.7371 | 4.1038 | - | - | - | - | - |
Parameter | During | After congestion is relieved | ||
PSO | FFA | WOA | ||
Total power loss (MW) | 6.9355 | 6.1561 | 6.1261 | 6.1216 |
Voltage deviation (p.u.) | 0.7313 | 0.2249 | 0.2036 | 0.1999 |
Parameter | Statistical data | PSO | FFA | WOA |
Total power loss (MW) | Best | 6.1561 | 6.1261 | 6.1216 |
Worst | 7.0456 | 6.5683 | 6.1593 | |
Voltage deviation (p.u.) | Best | 0.2249 | 0.2036 | 0.1999 |
Worst | 0.3657 | 0.3197 | 0.2034 | |
Execution time (Sec) | 156.63 | 153.68 | 150.23 |
Parameter | Best value PSO | Best value FFA | Best value WOA |
V1(p.u.) | 1.0436 | 1.0582 | 1.0236 |
V2(p.u.) | 1.0363 | 1.0425 | 1.0200 |
V5(p.u.) | 1.0210 | 1.0113 | 0.9881 |
V8(p.u.) | 1.0102 | 1.0169 | 0.9999 |
V11(p.u.) | 1.0283 | 1.0177 | 1.0364 |
V13(p.u.) | 1.0639 | 1.0205 | 1.0554 |
T11(p.u.) | 0.9808 | 1.0222 | 1.0263 |
T12(p.u.) | 1.0864 | 0.9858 | 0.9508 |
T15(p.u.) | 1.0814 | 1.0113 | 1.0021 |
T36(p.u.) | 0.9156 | 0.9508 | 0.9762 |
SVC1(p.u.) | 2.4780 | 6.4882 | 6.9114 |
SVC2(p.u.) | 5.1137 | 4.5855 | 4.5718 |
TCSC1(p.u.) | 0.1826 | -0.1952 | 0.1972 |
TCSC2 (p.u.) | 0.1114 | -0.2854 | -0.0458 |
Label of SVC, TCSC | Location of SVC and TCSC | ||
PSO | FFA | WOA | |
SVC1 | 12 | 19 | 29 |
SVC2 | 18 | 23 | 22 |
TCSC1 | 12 | 7 | 37 |
TCSC2 | 16 | 20 | 33 |