Optimal Configuration of Distributed Generation Based on an Improved Beluga Whale Optimization

Abstract

Large-scale distributed generation (DG) access to the distribution network brings many uncertainties to the distribution network, considering the impact of different types of distributed power supply on the optimization results as well as the uncertainty and correlation of wind energy, photovoltaic power generation, and load. A metaheuristic algorithm the Improved Beluga Whale Optimization Algorithm (IBWO) is used to optimize the capacity and location of DG. This algorithm incorporates the elite reverse learning strategy and cyclone foraging strategy while adjusting the balance factor to enhance the diversity of the algorithm population and further balance local search capability with global search capability. This study optimizes the configuration of distributed energy resources considering the uncertainty and correlation of wind power, photovoltaic power, and load. The optimization objective is to reduce active power loss, improve voltage stability, and minimize investment and operating costs. By conducting simulations on IEEE 33-bus and IEEE 118-bus test cases, the active power network losses are enhanced by 55.49% and 45.39% respectively, and the algorithm outperforms other methods regarding other data, demonstrating its superiority and effectiveness.