With the continuous improvement and gradual maturity of renewable energy technology based mainly on solar energy and hydropower, many countries pay attention to distributed power generation with renewable energy as an energy source. On the plus side, compared with the centralized large power grid, the microgrid, as a distributed generation system, can save operation costs, reduce line losses, and achieve emission reduction. Despite this, with the increase of the scale of the micro-grid system, power dispatching becomes a more complex multi-objective optimization problem. This dispatch problem needs to consider environmental impact, economic efficiency, energy losses and system stability in microgrid operations. economic environmental protection, energy loss, and stable operation. At present, there have been many methods for addressing the microgrid power dispatching problems. From the perspective of algorithm design, traditional heuristic algorithms, collaborative game algorithms, and multi-time intervals algorithms that have been used in the literature are usually employed. However, most of them are difficult to solve the multi-objective problems, easy to fall into local optima, and difficult to obtain the solution. An efficient method for solving multi-objective problems for microgrid power dispatching is urgently needed.
Recently, evolutionary multi-objective optimization (EMO) algorithms have received a surge of attention in microgrid applications. Due to the population-based, black-box search/optimization characteristics, EMO algorithms can well deal with complex microgrid power dispatching problems with more than two conflicting objectives. In principle, EMO algorithms utilize the Pareto optimality concept to search for the optimal configurations in the power dispatching process. In this way, a set of Pareto optimal solutions can be obtained in an effective way. In addition, the search of EMO does not require any gradient information of the specific problems, showing strong search robustness. Due to its population-based search, the EMO algorithms can be implemented naturally in parallel, which can increase the computation efficiency when tackling complex distributed power dispatching problems. Therefore, it is of great interest to investigate the role of EMO techniques in solving microgrid power dispatching problems.
This Research Topic focuses on the research of evolutionary multi-objective optimization for microgrid power dispatching problems in terms of theoretical and practical issues. The purpose of this Research Topic will bring together researchers, industry personnel, academicians, and individuals working in these areas and exchange novel ideas and the latest findings. The original papers are solicited on topics of interest that include, but are not limited to the following:
• EMO for machine learning architecture optimization in microgrid
• EMO for energy management in microgrid
• EMO for collaborative control in microgrid
• EMO for intelligent fault detection and classification in microgrid
• Scalable EMO architecture for microgrid
• Data-driven EMO
• Parallelized EMO
• Many-objective EMO
• Large-scale EMO
• New search strategies for EMO algorithms
With the continuous improvement and gradual maturity of renewable energy technology based mainly on solar energy and hydropower, many countries pay attention to distributed power generation with renewable energy as an energy source. On the plus side, compared with the centralized large power grid, the microgrid, as a distributed generation system, can save operation costs, reduce line losses, and achieve emission reduction. Despite this, with the increase of the scale of the micro-grid system, power dispatching becomes a more complex multi-objective optimization problem. This dispatch problem needs to consider environmental impact, economic efficiency, energy losses and system stability in microgrid operations. economic environmental protection, energy loss, and stable operation. At present, there have been many methods for addressing the microgrid power dispatching problems. From the perspective of algorithm design, traditional heuristic algorithms, collaborative game algorithms, and multi-time intervals algorithms that have been used in the literature are usually employed. However, most of them are difficult to solve the multi-objective problems, easy to fall into local optima, and difficult to obtain the solution. An efficient method for solving multi-objective problems for microgrid power dispatching is urgently needed.
Recently, evolutionary multi-objective optimization (EMO) algorithms have received a surge of attention in microgrid applications. Due to the population-based, black-box search/optimization characteristics, EMO algorithms can well deal with complex microgrid power dispatching problems with more than two conflicting objectives. In principle, EMO algorithms utilize the Pareto optimality concept to search for the optimal configurations in the power dispatching process. In this way, a set of Pareto optimal solutions can be obtained in an effective way. In addition, the search of EMO does not require any gradient information of the specific problems, showing strong search robustness. Due to its population-based search, the EMO algorithms can be implemented naturally in parallel, which can increase the computation efficiency when tackling complex distributed power dispatching problems. Therefore, it is of great interest to investigate the role of EMO techniques in solving microgrid power dispatching problems.
This Research Topic focuses on the research of evolutionary multi-objective optimization for microgrid power dispatching problems in terms of theoretical and practical issues. The purpose of this Research Topic will bring together researchers, industry personnel, academicians, and individuals working in these areas and exchange novel ideas and the latest findings. The original papers are solicited on topics of interest that include, but are not limited to the following:
• EMO for machine learning architecture optimization in microgrid
• EMO for energy management in microgrid
• EMO for collaborative control in microgrid
• EMO for intelligent fault detection and classification in microgrid
• Scalable EMO architecture for microgrid
• Data-driven EMO
• Parallelized EMO
• Many-objective EMO
• Large-scale EMO
• New search strategies for EMO algorithms
