Data-driven complex network framework for risk dynamics and stability evaluations in renewable-integrated power systems

Tariq Ali; Muzna Sarwar; Farrukh Jamal; Mohammad Hijji; Husam S. Samkari; Mohammed F. Allehyani; M. Ammad ud Din; Muhammad Ayaz; Tariq Ali; Muzna Sarwar; Farrukh Jamal; Mohammad Hijji; Husam S. Samkari; Mohammed F. Allehyani; M. Ammad ud Din; Muhammad Ayaz

doi:10.3934/math.2026781

AIMS Mathematics

2026, Volume 11, Issue 6: 19177-19216. doi: 10.3934/math.2026781

Previous Article Next Article

Research article Special Issues

Data-driven complex network framework for risk dynamics and stability evaluations in renewable-integrated power systems

1.
Artificial Intelligence and Sensing Technology Research Center (AIST), University of Tabuk, Tabuk 71491, Saudi Arabia
2.
Faculty of Computers and Information Technology, University of Tabuk, Tabuk, 71491, Saudi Arabia
3.
Department of Statistics, Faculty of Computing, Islamia University of Bahawalpur, Pakistan
4.
Department of Statistics, Faculty of Science, University of Tabuk, Tabuk, Saudi Arabia
5.
Department of Electrical Engineering, University of Tabuk, Tabuk, 47713, Saudi Arabia
6.
Lab-STICC, UMR 6285-CNRS, ENSTA, Institut Polytechnique de Paris, 29200 Brest, France

Received: 23 February 2026 Revised: 06 May 2026 Accepted: 25 May 2026 Published: 30 June 2026
MSC : 34A08, 68T07

The integration of renewable energy sources into modern power systems introduces stability and resilience challenges due to their intermittent and stochastic behavior. To address these issues, this study proposes an artificial intelligence (AI)-driven statistical complex network (AI-SCN) framework for stability assessments in renewable-integrated power grids. The framework models the grid as a weighted complex network, where the nodes represent generation, storage, and load units, and the edges capture electrical and statistical dependencies. By integrating network topology metrics with data-driven AI models, AI-SCN enables accurate stability margin estimation and resilience quantification under varying renewable penetration levels. Simulations on the Institute of Electrical and Electronics Engineers (IEEE) 39-bus and IEEE 118-bus systems show that AI-SCN outperforms conventional and long short-term memory (LSTM)-based approaches, achieving root mean square error (RMSE) values of 0.0185 and 0.0219, respectively, representing improvements of 40.7% and 58.9%. Furthermore, recovery time is reduced from 12.8 s to 8.4 s, demonstrating the system's enhanced recovery efficiency. These results confirm that AI-SCN offers a scalable and adaptive framework for improving stability and resilience in renewable-dominant power systems.
- complex network,
- power system stability,
- energy integration,
- resilience assessment,
- machine learning,
- computational complexity
Citation: Tariq Ali, Muzna Sarwar, Farrukh Jamal, Mohammad Hijji, Husam S. Samkari, Mohammed F. Allehyani, M. Ammad ud Din, Muhammad Ayaz. Data-driven complex network framework for risk dynamics and stability evaluations in renewable-integrated power systems[J]. AIMS Mathematics, 2026, 11(6): 19177-19216. doi: 10.3934/math.2026781

Related Papers:

Abstract

The integration of renewable energy sources into modern power systems introduces stability and resilience challenges due to their intermittent and stochastic behavior. To address these issues, this study proposes an artificial intelligence (AI)-driven statistical complex network (AI-SCN) framework for stability assessments in renewable-integrated power grids. The framework models the grid as a weighted complex network, where the nodes represent generation, storage, and load units, and the edges capture electrical and statistical dependencies. By integrating network topology metrics with data-driven AI models, AI-SCN enables accurate stability margin estimation and resilience quantification under varying renewable penetration levels. Simulations on the Institute of Electrical and Electronics Engineers (IEEE) 39-bus and IEEE 118-bus systems show that AI-SCN outperforms conventional and long short-term memory (LSTM)-based approaches, achieving root mean square error (RMSE) values of 0.0185 and 0.0219, respectively, representing improvements of 40.7% and 58.9%. Furthermore, recovery time is reduced from 12.8 s to 8.4 s, demonstrating the system's enhanced recovery efficiency. These results confirm that AI-SCN offers a scalable and adaptive framework for improving stability and resilience in renewable-dominant power systems.

References

[1]	L. Meegahapola, A. Sguarezi, J. S. Bryant, M. C. Gu, E. R. Conde D, R. B. A. Cunha, Power system stability with power-electronic converter interfaced renewable power generation: present issues and future trends, Energies, 13 (2020), 3441. https://doi.org/10.3390/en13133441 doi: 10.3390/en13133441
[2]	A. Hadavi, M. T. Hagh, S. G. Zadeh, Critical inertia thresholds for frequency stability in renewable energy-integrated power systems, Int. J. Electr. Power Energy Syst., 169 (2025), 110733. https://doi.org/10.1016/j.ijepes.2025.110733 doi: 10.1016/j.ijepes.2025.110733
[3]	B. Z. Ghavidel, Y. Liao, Review of sub-synchronous oscillation (SSO): from historical challenges to modern inverter-based re-newable energy sources, Int. J. Emerg. Electr. Power Syst., 27 (2026), 211–237. https://doi.org/10.1515/ijeeps-2025-0054 doi: 10.1515/ijeeps-2025-0054
[4]	Q. F. Chen, S. Q. Bu, C. Y. Chung, Small-signal stability criteria in power electronics-dominated power systems: a comparative review, J. Mod. Power Syst. Clean Energy, 12 (2024), 1003–1018. https://doi.org/10.35833/MPCE.2023.000526 doi: 10.35833/MPCE.2023.000526
[5]	V. Radisavljevic-Gajic, D. Karagiannis, Z. Gajic, Linear, nonlinear, and distributed-parameter observers used for (renewable) energy processes and systems–an overview, Energies, 17 (2024), 2700. https://doi.org/10.3390/en17112700 doi: 10.3390/en17112700
[6]	C. C. Chu, H. H. C. Iu, Complex networks theory for modern smart grid applications: a survey, IEEE J. Emerg. Sel. Top. Circuits Syst., 7 (2017), 177–191. https://doi.org/10.1109/JETCAS.2017.2692243 doi: 10.1109/JETCAS.2017.2692243
[7]	J. V. Milanovic, W. T. Zhu, Modeling of interconnected critical infrastructure systems using complex network theory, IEEE Trans. Smart Grid, 9 (2018), 4637–4648. https://doi.org/10.1109/TSG.2017.2665646 doi: 10.1109/TSG.2017.2665646
[8]	A. M. Amani, M. Jalili, Power grids as complex networks: resilience and reliability analysis, IEEE Access, 9 (2021), 119010–119031. https://doi.org/10.1109/ACCESS.2021.3107492 doi: 10.1109/ACCESS.2021.3107492
[9]	T. Ali, M. Ayaz, H. S. Samkari, M. Hijji, M. F. Allehyani, E. H. M. Aggoune, Multi-objective optimization and load-flow analysis in complex power distribution networks, Fractal Fract., 10 (2026), 82. https://doi.org/10.3390/fractalfract10020082 doi: 10.3390/fractalfract10020082
[10]	A. Wadood, B. M. Khan, H. Albalawi, B. S. Khan, H. Park, B. O Kang, Fractional calculus and adaptive balanced artificial protozoa optimizers for multi-distributed energy resources planning in smart distribution networks, Fractal Fract., 10 (2026), 101. https://doi.org/10.3390/fractalfract10020101 doi: 10.3390/fractalfract10020101
[11]	Q. Zhang, G. H. Shi, Y. Li, S. Q. Jia, The research progress on the application of artificial intelligence in power system stability: from data perception to intelligent control, Adv. Resour. Res., 5 (2025), 2454–2482. https://doi.org/10.50908/arr.5.4_2454 doi: 10.50908/arr.5.4_2454
[12]	T. Ali, S. Yasin, U. Draz, H. S. Samkari, M. Hijji, M. F. Allehyani, et al., Fractional-order dynamic modeling of renewable-dominant power systems using long-memory load and generation data, Fractal Fract., 10 (2026), 183. https://doi.org/10.3390/fractalfract10030183 doi: 10.3390/fractalfract10030183
[13]	C. Feng, L. B. Huang, X. Q. He, Y. Wang, F. Dörfler, C. Q. Kang, Hybrid oscillation damping and inertia management for distributed energy resources, IEEE Trans. Power Syst., 40 (2025), 5041–5056. https://doi.org/10.1109/TPWRS.2025.3562811 doi: 10.1109/TPWRS.2025.3562811
[14]	S. Q. Wang, Z. H. Zhao, Y. L. Li, The research progress on power system restoration and resilience analysis: key technologies and future development trends, Adv. Resour. Res., 5 (2025), 2528–2558. https://doi.org/10.50908/arr.5.4_2528 doi: 10.50908/arr.5.4_2528
[15]	S. Ćosić, I. Vokony, Advancements in AI-driven approaches for grid stability monitoring, In: 2025 10th International Youth Conference on Energy (IYCE), Budapest, Hungary, 2025, 1–7. https://doi.org/10.1109/IYCE66046.2025.11155020
[16]	A. Saxena, R. Shankar, E. F. El-Saadany, M. Kumar, O. Al Zaabi, K. Al Hosani, Intelligent load forecasting and renewable energy integration for enhanced grid reliability, IEEE Trans. Ind. Appl., 60 (2024), 8403–8417. https://doi.org/10.1109/TIA.2024.3436471 doi: 10.1109/TIA.2024.3436471
[17]	A. Waheed, J. Y. Li, A hybrid machine learning approach for real-time reliability evaluation of power systems, Phys. Scr., 100 (2025), 076016. https://doi.org/10.1088/1402-4896/ade644 doi: 10.1088/1402-4896/ade644
[18]	S. K. A. Zaidi, K. S. A. Islam, M. T. Abbas, T. Abbas, Hybrid ML-based fault detection in renewable-integrated power grids, Spectrum Eng. Sci., 3 (2025), 520–527.
[19]	P. Dineshkumar, Machine learning-based predictive stability assessment for renewable-rich power systems, Natl. J. Intell. Power Syst. Technol., 2 (2026), 23–33.
[20]	K. Zeriouh, M. Amara, AI-driven frameworks for strategic risk management: a systematic review and model for organizational resilience and decision support, J. Intell. Manag. Decision, 4 (2025), 224–234. https://doi.org/10.56578/jimd040304 doi: 10.56578/jimd040304
[21]	Y. Sanjalawe, S. Al-E' Mari, S. Fraihat, S. N. Makhadmeh, E. Alzubi, AI-powered smart grids in the 6G era: a comprehensive survey on security and intelligent energy systems, IEEE Open J. Commun. Soc., 6 (2025), 7677–7719. https://doi.org/10.1109/OJCOMS.2025.3609144 doi: 10.1109/OJCOMS.2025.3609144
[22]	M. Rouholamini, C. S. Wang, S. Magableh, X. S. Wang, Resiliency of electric power distribution networks: a review, J. Infrastruct. Preserv. Resil., 6 (2025), 39. https://doi.org/10.1186/s43065-025-00154-y doi: 10.1186/s43065-025-00154-y
[23]	O. Lordan, J. M. Sallan, P. Simo, Study of the topology and robustness of airline route networks from the complex network approach: a survey and research agenda, J. Transp. Geogr., 37 (2014), 112–120. https://doi.org/10.1016/j.jtrangeo.2014.04.015 doi: 10.1016/j.jtrangeo.2014.04.015
[24]	P. Linardatos, V. Papastefanopoulos, S. Kotsiantis, Explainable AI: a review of machine learning interpretability methods, Entropy, 23 (2021), 18. https://doi.org/10.3390/e23010018 doi: 10.3390/e23010018
[25]	Y. Tang, J. Kurths, W. Lin, E. Ott, L. Kocarev, Introduction to focus issue: When machine learning meets complex systems: networks, chaos, and nonlinear dynamics, Chaos, 30 (2020), 063151. https://doi.org/10.1063/5.0016505 doi: 10.1063/5.0016505
[26]	M. Ayaz, T. Ali, M. Hijji, I. Baig, T. Alhmiedat, E. H. M. Aggoune, Predictive modeling of complex networks using deep learning and fractional dynamics, AIMS Math., 10 (2025), 26717–26743. https://doi.org/10.3934/math.20251175 doi: 10.3934/math.20251175
[27]	F. Li, Y. Z. Cai, L. Su, H. Shen, S. Y. Xu, $\mathcal{H}_{\infty}$ state estimation for two-time-scale Markov jump complex networks under analog fading channels: a hidden-Markov-model-based method, IEEE Trans. Circuits Syst. I Regul. Pap., 71 (2024), 3833–3842. https://doi.org/10.1109/TCSI.2024.3372548 doi: 10.1109/TCSI.2024.3372548
[28]	F. Li, Y. N. Wang, H. Shen, Dual event-triggered synchronization of two-time-scale jumping neural networks and its application in image encryption and decryption, IEEE Trans. Netw. Sci. Eng., 12 (2025), 943–954. https://doi.org/10.1109/TNSE.2024.3521429 doi: 10.1109/TNSE.2024.3521429
[29]	H. Shen, C. J. Peng, H. C. Yan, S. Y. Xu, Data-driven near optimization for fast sampling singularly perturbed systems, IEEE Trans. Automat. Control, 69 (2024), 4689–4694. https://doi.org/10.1109/TAC.2024.3352703 doi: 10.1109/TAC.2024.3352703
[30]	N. Zhao, D. Lun, H. Y. Zhang, X. D. Zhao, I. J. Rudas, Composite anti-disturbance control for networked systems with disturbances and actuator attacks via event-triggered output feedback, IEEE Trans. Cybernet., 56 (2026), 393–403. https://doi.org/10.1109/TCYB.2025.3609819 doi: 10.1109/TCYB.2025.3609819
[31]	T. Wu, J. H. Wang, Artificial intelligence for operation and control: the case of microgrids, Electr. J., 34 (2021), 106890. https://doi.org/10.1016/j.tej.2020.106890 doi: 10.1016/j.tej.2020.106890
[32]	P. M. Peruman, K. Ayyar, Power quality disturbance identification using hybrid deep learning in renewable energy systems, Sci. Rep., 15 (2025), 44592. https://doi.org/10.1038/s41598-025-28291-0 doi: 10.1038/s41598-025-28291-0
[33]	R. K. Priya, N. Karuppiah, H. Subhadra, P. K. Balachandran, Deep learning empowered cyber-physical intelligence system for resilient renewable aware IoT integrated smart grid systems, Eng. Res. Express, 8 (2026), 065211. https://doi.org/10.1088/2631-8695/ae4f5a doi: 10.1088/2631-8695/ae4f5a
[34]	P. Sarajcev, A. Kunac, G. Petrovic, M. Despalatovic, Artificial intelligence techniques for power system transient stability assessment, Energies, 15 (2022), 507. https://doi.org/10.3390/en15020507 doi: 10.3390/en15020507
[35]	H. Xiang, X. L. Li, X. Liao, W. Cui, F. K. Liu, D. H. Li, Artificial intelligence in renewable energy systems: applications and security challenges, Energies, 18 (2025), 1931. https://doi.org/10.3390/en18081931 doi: 10.3390/en18081931

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)