AI-Driven Optimization in Intelligent Process Control for Power and Energy Systems

Dear Colleagues,

Aims and Scope

The increasing complexity, decentralization, and dynamism of modern power and energy systems have presented formidable challenges for traditional process control and optimization frameworks. Rigid, model-based control systems are often inadequate to respond to the nonlinear, time-varying, and data-intensive nature of energy processes today. This Special Issue aims to explore advanced AI-driven optimization and intelligent control approaches that can enable higher adaptability, efficiency, and autonomy in the management of energy systems.

We seek high-quality contributions that investigate how artificial intelligence (AI)—including reinforcement learning, neural networks, swarm intelligence, and hybrid symbolic-neural architectures—can be harnessed to address real-time decision-making, predictive control, and process-level optimization in power and energy systems. This Special Issue provides an interdisciplinary platform for innovations that push the boundaries of energy automation, digitalization, and intelligent system design.

Background and Significance

The global transition to low-carbon, decentralized energy infrastructures has led to the proliferation of smart grids, renewable generation, microgrids, and cyber-physical energy systems. As a result, the operational landscape of power and energy systems is increasingly characterized by nonlinearity, stochasticity, high dimensionality, and interconnectivity. Traditional control strategies, which rely on deterministic models and fixed heuristics, often fall short in such complex settings.

Artificial intelligence offers a transformative pathway forward. Techniques such as deep reinforcement learning, neural-symbolic control systems, metaheuristic optimization, and federated learning enable power and energy systems to adapt, learn, and self-optimize in real-time, even under uncertainty and incomplete information. By embedding AI capabilities into the process control loop, systems can autonomously adjust to disturbances, optimize performance metrics, and coordinate distributed energy resources with minimal human intervention.

This Special Issue invites contributions that bridge theory and practice, offering novel control and optimization paradigms grounded in AI, with applications across power generation, transmission, distribution, energy storage, and load management. Emphasis is placed on the engineering implementation, scalability, and robustness of intelligent process control architectures.

Topics of Interest

Topics include, but are not limited to:

• Deep reinforcement learning for real-time control of power and energy processes;
• AI-based modeling and predictive control in nonlinear and uncertain environments;
• Swarm intelligence and metaheuristics for distributed energy resource coordination;
• AI-enhanced stability control in microgrids and autonomous power subsystems;
• Federated and privacy-preserving learning in distributed control frameworks;
• Intelligent fault detection, diagnosis, and reconfiguration of power systems;
• Hybrid models combining symbolic AI with process dynamics for interpretable control;
• Digital twins for real-time optimization and simulation of energy processes;
• Adaptive process automation and self-tuning control strategies using AI;
• Multi-objective optimization in energy systems using evolutionary algorithms;
• Cyber-physical security enhancement using AI-driven anomaly detection;
• Data-driven system identification and process learning for smart grids;
• Intelligent control of energy storage systems and renewable integration;
• Edge and cloud-based AI architectures for scalable energy control.

Dr. Lefeng Cheng
Dr. Xiaoshun Zhang
Dr. Huaizhi Wang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• intelligent process control
• AI in energy systems
• deep reinforcement learning
• energy system automation
• neural-symbolic control
• adaptive optimization
• swarm intelligence
• distributed control systems
• predictive control in smart grids
• cyber-physical energy systems
• digital twin in power engineering
• AI for microgrids
• process-level energy optimization
• data-driven control
• self-learning energy systems