Optimization and Machine Learning for Analysis and Control of Integrated Energy Systems

Dear Colleagues,

This Special Issue aims to explore cutting-edge developments at the intersection of optimization theory and machine learning as applied to the analysis and control of integrated energy systems (IESs). As modern energy infrastructures evolve to incorporate higher shares of intermittent renewable generation, multi-energy vector coupling, and distributed energy resources, they present unprecedented challenges in terms of operational complexity, uncertainty management, and control stability. Traditional analytical methods often prove inadequate in addressing these challenges, creating a pressing need for more sophisticated computational approaches. A further dimension of growing importance is the inclusion of industrial plants together with residential and commercial buildings within IESs, where the coexistence of electricity, heating, and cooling demands across multiple temperature levels creates both complexity and novel opportunities for optimization, waste-heat recovery, and cross-sectoral energy exchange.

We invite original research contributions that advance the state-of-the-art in applying optimization and machine learning techniques to IESs. The scope encompasses both theoretical developments and practical applications, with particular interest in the following:

• Novel optimization frameworks that integrate physical constraints with machine learning predictions for improved energy system planning and operation.
• Advanced machine learning architectures (including deep learning, reinforcement learning, and hybrid approaches) for the enhanced forecasting of renewable generation, load patterns, and energy market dynamics.
• Data-driven approaches for uncertainty quantification and robust decision-making in energy system operations.
• Reinforcement learning and adaptive control strategies for real-time optimization of complex, multi-energy systems.
• Distributed and decentralized optimization algorithms for coordinated control in systems with numerous stakeholders.
• Digital twin technologies combining optimization and ML for system monitoring, fault detection, and predictive maintenance, enabling the early identification of component degradation, optimal scheduling of maintenance actions, and minimization of unplanned downtime and operational costs.
• Optimization and control of IESs including industrial, residential, and commercial facilities, with emphasis on energy exchange, waste-heat utilization, and operational cost reduction.

We encourage submissions that demonstrate rigorous methodological innovation while addressing practical implementation challenges. Case studies showcasing successful applications in real-world energy systems are particularly welcome, as are contributions that provide open datasets or benchmark problems for the research community.

This Special Issue seeks to foster dialog between the optimization, machine learning, and energy system communities, with the ultimate goal of developing more intelligent, efficient, and resilient energy infrastructures for the future. Both fundamental research and applied studies are within the scope, provided they offer novel insights or demonstrate significant improvements over existing approaches.

Dr. Ranran Li
Dr. Luca Silvestri
Prof. Dr. Antonio Ficarella
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. Applied Sciences is an international peer-reviewed open access semimonthly 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.

• integrated energy systems (IES)
• machine learning (ML)
• optimization techniques
• energy system control
• reinforcement learning
• predictive modeling
• renewable energy integration
• smart grid optimization
• demand response
• distributed energy management
• deep learning for energy systems
• model predictive control (MPC)
• predictive maintenance in energy systems
• industrial energy system integration