A Fuzzy Based Prediction of an Industrial Load in Microgrid System Using Particle Swarm Optimization Algorithm

Abstract

A microgrid system is an efficient, cost-effective, clean, and self-resilient power generation option for industrial customers. It consists of solar PV, wind turbine, and energy storage systems for effective utilization of renewable energy resources. The industrial customers are made up of different types of motor loads, different types of light bulbs, and air conditioners supplied from renewable energy resources-based microgrid. An accurate industrial load prediction model is designed to serve a microgrid for industrial customers. Using the fuzzy load prediction approach on the Simulink model and the Fuzzy-PSO load prediction model, an accurate estimate of the future demand of an industrial customer is developed. The parameters of time, temperature, historical load, and error correction factors are considered as the Fuzzy and Fuzzy-PSO model input variables while the forecasted industrial load is the only output variable. The Gaussian membership function is considered for both the input and output fuzzy variables. The 3-year hourly load data of an Ethiopian industrial system is used to train and validate both prediction models. The mean absolute percentage error (MAPE) is used to evaluate the performance of these prediction models. The Fuzzy-PSO load prediction model shows results that have superior performance on the fuzzy-alone load prediction results.