Research on Machine Learning Optimization Algorithm in New Energy Dispatching System

This paper studies the machine learning optimization algorithm of new energy scheduling system, aiming at improving the system's peak load balancing ability and operation efficiency. Firstly, this paper introduces the basic structure and challenges of new energy dispatching system, and expounds the application prospect of machine learning optimization algorithm in it. Then, the modeling and solving of multi-objective optimization problems are discussed, and an improved NSGA-II algorithm is proposed, which can effectively balance the economy and environmental protection of new energy scheduling by introducing non-dominant ranking and elite strategy. In this paper, the coding, initialization, fitness evaluation, selection, crossover, variation and other steps of the algorithm are described in detail, and the effectiveness and superiority of the algorithm are verified by model simulation experiments. The experimental results show that the proposed algorithm can significantly improve the peak load capacity of the new energy dispatching system, reduce the wind and light abandonment rate, and ensure the safe and stable operation of the power system. In addition, the effects of different parameter Settings on the performance of the algorithm are compared and analyzed, and the convergence speed and robustness of the algorithm are further optimized.