The energy crisis is a major problem faced by countries across the globe. At present, 84% of the world’s enormous energy demand is met through burning fossil fuels, and only 16% through renewable energy resources. The emissions caused by this are the primary cause of the deteriorating environment, and so the energy sector has shifted its focus towards renewable energy resources. With the integration of various renewable energy systems with the existing power grid, the development of smart grid networks has encountered various operational challenges. Hence, smart grid networks require a smart power management solution to efficiently tackle the source and demand.

Power management has always posed new research challenges and much research is still required for sustainable power management in smart grid networks. The solution for sustainable power management could potentially be achieved through federated learning (FL). Federated learning is a branch of machine learning techniques that have been recognized in recent years for their applications in decentralized data training and providing impressive solutions for complex engineering problems. In renewable energy-based smart grid networks, federated learning tends to identify the main cause of the power ratio between supply and demand and optimize the balance between the supply and the demand in an efficient way to reduce the peak load during unexpected periods. This thereby creates a hassle-free power management solution for the smart grid network.

The aim of this Special Issue is to act as a common platform to bring together relevant original research and review articles that consider the importance of sustainable power management in smart grid networks, as well as discussing the role of federated learning for energy management in renewable energy-based smart grids and comprehensive solutions and future directions. We invite contributions from both academia and industry on recent developments that can help tackle the challenges associated with sustainable power management.

Potential topics include but are not limited to the following:

• Federated learning approaches for power management in smart grids
• Privacy protection in prosumer energy management based on federated learning
• Identification of electricity consumer characteristics using federated learning
• Federated learning and blockchain-enabled sustainable energy trade
• Energy management algorithms for smart grid networks
• Federated learning approaches for cyber-secure frameworks for smart grids
• Empowering sustainable energy infrastructures
• Recent advances in smart grid technology
• Empowering prosumer communities in smart grids using federated learning
• Electrical load forecasting using edge computing and federated learning
• Secure and efficient federated learning for smart grids
• Grid resilience enhancement services using soft computing techniques
• Internet of Things enabling for monitoring and controlling renewable energy systems and smart grids and micro-grids
• Autonomous energy generation and control
• Advanced metering infrastructures