Data Driven and Intelligent Control Algorithms for Modern Microgrid Control and Management

The rapid integration of renewable energy resources, electric vehicles, energy storage systems, and flexible loads is transforming conventional distribution networks into dynamic and increasingly controllable microgrids. Microgrids can coordinate distributed energy resources and loads while operating in both grid-connected and islanded modes, creating new opportunities for improved flexibility, resilience, and decarbonisation. Advances in sensing, communication, and edge-computing technologies are generating large volumes of operational data that can support machine learning, artificial intelligence, and other data-driven approaches to forecasting, state estimation, energy management, and control. However, the deployment of these methods remains challenging because of system non-linearity, uncertainty, high dimensionality, limited observability, cybersecurity risks, and the interoperability and coordination requirements of heterogeneous devices. Recent studies have demonstrated the potential of deep learning, reinforcement learning, distributed optimisation, federated learning, and physics-informed neural networks to improve situational awareness and adaptive decision-making. Nevertheless, questions remain regarding the reliability, explainability, scalability, transferability, and safety of data-driven methods under changing operating conditions and severe disturbances. Further investigation is therefore needed to develop control architectures that combine data-driven intelligence with physical knowledge and operational constraints.This Research Topic aims to advance the understanding and application of data-driven methods for the secure, resilient, and efficient operation of microgrids. It will examine how artificial intelligence and machine learning can be integrated with physics-based models to support safe and stable control, scalable and distributed coordination, explainable decision-making, and real-time energy management. Contributions may address the development and validation of methods for forecasting, state estimation, optimisation, fault detection, islanding operation, and resilience enhancement. Particular attention will be given to approaches capable of managing uncertainty, coordinating diverse distributed energy resources, responding to N-k contingencies, and supporting autonomous or fault-tolerant operation. The Research Topic will also consider whether emerging approaches, including agentic AI and federated learning, can provide trustworthy and interoperable solutions for multi-microgrid and distribution-system applications.To gather further insights into data-driven control, optimisation, resilience, and energy management for grid-connected, islanded, and interconnected microgrids, we welcome articles addressing, but not limited to, the following themes:● Machine learning for renewable-energy forecasting, load forecasting, and distribution-grid state estimation● Distributed optimisation and decentralised energy-management systems● Physics-informed neural networks and hybrid model-based/data-driven control● Reinforcement learning and agentic AI for microgrid optimisation and control● Resilient control architectures and N-k contingency analysis● Interoperable coordination frameworks for distributed energy-resource control● Real-time control, fault detection, fault-tolerant operation, and adaptive protection● Federated learning, privacy-preserving analytics, and edge intelligence for microgrids● Heuristic and metaheuristic optimisation for microgrid energy management● Optimal planning, component sizing, and capacity allocation● Cybersecurity, cyber-physical resilience, and trustworthy artificial intelligence● Peer-to-peer energy trading and multi-microgrid coordination● Low-carbon microgrids and data-driven pathways to decarbonisation Topic editors: Sheroze Liaquat, Muhammad Fahad Zia, GM Shafiullah Source: https://www.frontiersin.org/research-topics/82599/data-driven-and-intelligent-control-algorithms-for-modern-microgrid-control-and-management