The field of energy management and predictive control is moving towards more efficient and sustainable solutions. Researchers are exploring innovative approaches to optimize energy storage, consumption, and production, with a focus on reducing reliance on fossil fuels and minimizing environmental impact. One notable trend is the development of advanced control systems that can dynamically interact with energy storage systems, buildings, and other components to maximize energy efficiency. Another area of research is the application of data-driven predictive control methods, such as those using neural networks, to optimize energy management in various contexts, including greenhouse climate regulation and virtual power plants. These advances have the potential to significantly reduce energy consumption, lower costs, and promote sustainable development.

Noteworthy papers include: The paper on sequential operation of residential energy hubs presents a novel 2-stage economic model predictive controller for electrified buildings. The study on data-driven greenhouse climate regulation demonstrates the effectiveness of GRU-based predictive control in reducing temperature and humidity violations. The comparison of renewable-based virtual power plants and electrical storage systems provides valuable insights into their technical performance, market strategies, and economic outcomes.