Multi-Objective Optimization of Pumped Storage Power Station Engineering based on Improved Particle Swarm Optimization Algorithm

The benefits of hybrid Pumped Energy Storage Systems (PESS) are reducing voltage fluctuations, mitigate active power losses, and improves power quality storage within distributed power generation systems. However, due to single-objective optimization algorithms and challenge to find various optimal solutions in existing Multi-Objective (MO) optimization processes lead to increase high voltage fluctuations and decrease energy in systems. To solve these limitations, an Improved Particle Swarm Optimization (IPSO) model and Mutation Greedy Algorithm (MGA) is proposed for hybrid energy storage performs based on loss and economic indicators which is vital to optimize energy storage. The balance among hybrid ESS stability and costs is increased by IPSO and MGA. This highlights advantages of ESS and its notable capacity for optimizing voltage fluctuations and power losses in systems. The experimental results show rational outline of PESS improves energy storage levels up to 4861 kw power and minimize power losses continuously and improve system stability while considering both aspects of stability and economic. The results are superior than existing optimization algorithms such as Multi-Objective Sine Cosine Algorithm (MO-SCA), Grasshopper Optimization Algorithm (GOA), Multi-Objective Particle Swarm Optimization (MOPSO), and Non-Sorting Genetic Algorithm-II (NSGA-II).