Manuscript Topics

The transformation of traditional cities into smart, digitally connected ecosystems has brought with it an urgent need to manage energy demand with greater precision, sustainability, and resilience. As urban populations grow and digital infrastructure becomes more embedded in everyday life, accurate energy demand forecasting is essential to ensure the efficient allocation of resources, maintain the reliability of power systems, and support long-term environmental goals. With the proliferation of data from smart meters, IoT devices, and connected energy systems, artificial intelligence (AI) offers a powerful means to address the complexity and variability inherent in modern energy consumption. This Special Issue invites cutting-edge research that explores AI-powered forecasting systems and methodologies designed to meet the diverse and dynamic energy needs of smart cities. The use of AI, particularly machine learning and deep learning, is rapidly transforming how energy demand is modelled and predicted. Traditional statistical models like ARIMA or linear regression often fall short in dealing with the nonlinear, high-dimensional, and time-varying nature of urban energy data. In contrast, advanced AI models such as Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Transformer-based architectures have demonstrated superior performance in extracting complex spatio-temporal patterns, enabling short-, medium-, and long-term forecasts that adapt to shifting urban conditions.

This Special Issue places particular emphasis on the application of AI in forecasting energy demand across multiple subsystems of the smart city ecosystem. These include, but are not limited to, residential and commercial buildings, industrial zones, public infrastructure, and critical utilities. Specific sectors such as transportation especially in relation to electric vehicle charging infrastructure air-conditioning and HVAC systems, public lighting, and renewable energy sources represent high-priority domains where AI-based forecasting can significantly enhance operational efficiency and grid stability. The integration of external, dynamic factors such as real-time weather data, human mobility patterns, population density, and socio-economic activities further underscores the need for intelligent, context-aware forecasting tools that evolve with the urban landscape. In addition to sector-specific forecasting, the issue welcomes studies that explore real-time prediction systems, adaptive learning frameworks, and multi-source data fusion strategies. The deployment of edge AI and federated learning also presents novel approaches to handling data privacy, decentralization, and low-latency analytics crucial considerations in the smart city context. Submissions that address demand-side management, dynamic pricing models, and policy-aware forecasting approaches are also encouraged, especially those that facilitate behavioural energy adjustments and inform strategic planning for infrastructure development, such as optimal siting of substations and storage units. Interdisciplinary contributions that bridge AI, energy systems engineering, urban informatics, and behavioural sciences are particularly valuable. Ultimately, this Special Issue seeks to advance the theoretical foundations and practical implementations of AI-driven energy demand forecasting, contributing to the broader vision of intelligent, adaptive, and sustainable urban energy systems. Researchers, practitioners, and policymakers are invited to share innovative methodologies, case studies, frameworks, and review articles that reflect the evolving role of artificial intelligence in shaping energy-smart cities of the future.

Topics of interest include, but are not limited to:

• AI-Based Energy Forecasting for Electric Vehicle Charging Infrastructure
• Deep Learning Models for HVAC (Heating, Ventilation, Air Conditioning) Energy Demand in Smart Buildings
• Energy Demand Forecasting for Smart Lighting Systems Using Sensor Fusion and AI
• Adaptive Multi-Sector Urban Energy Prediction using Federated Learning and Edge AI
• Spatio-Temporal Forecasting of Urban Power Demand Using Transformer and LSTM Architectures
• Forecasting Renewable Energy Consumption and Integration in Smart Urban Grids
• Smart Grid Resilience Enhancement through Hybrid AI Models (CNN, LSTM, GNN)
• Real-Time Energy Load Forecasting for Urban Transportation Systems
• AI-Powered Dynamic Pricing Models Based on Predictive Energy Analytics
• Geospatial and Behavioural Data-Driven Energy Demand Modeling
• Forecasting Urban Energy Demand During Public Events and Emergency Scenarios
• Scalable AI Architectures for Sector-Specific Energy Forecasting (e.g., Commercial vs. Residential)
• AI-Enabled Energy Efficiency Optimization for Street Lighting and Public Infrastructure
• Blockchain and AI-Driven Decentralized Energy Forecasting in Urban Environments
• Predictive Modeling of Industrial Energy Usage Patterns in Smart Cities

Instruction for Authors
https://www.aimspress.com/aimse/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/