Short‐term wind power prediction in microgrids using a hybrid approach integrating genetic algorithm, particle swarm optimization, and adaptive neuro‐fuzzy inference systems

Abstract

This paper proposes an integrated hybrid approach combining genetic algorithm (GA), particle swarm optimization (PSO), and adaptive neuro‐fuzzy inference systems (ANFIS) for short‐term wind power generation prediction in microgrids. The increasing penetration of intermittent and uncertain renewable energy resources like wind into electric power systems poses important operational challenges. Accurate prediction of wind power generation is crucial to address the challenges and fully harness the available generation capability of wind energy generation systems. Accurate wind power generation forecasting tools play a critical role in enabling system operators to plan efficient operation of power systems and ensure reliability of supply. In this paper, a combination of GA and PSO is used to optimize an ANFIS model for short‐term wind power prediction. To demonstrate the effectiveness of the proposed method, it is tested based on practical information of weather conditions and wind power generation data of a case study microgrid system in Beijing. The performance of the proposed approach is compared with four other prediction methods. The proposed approach outperformed all the other methods, demonstrating its favorable accuracy and reliability. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.