A new optimal energy storage system model for wind power producers based on long short term memory and Coot Bird Search Algorithm

Abstract

In recent years, the development of wind power production had an important impact on the security and reliability operation of power systems. Therefore, Wind Power Producers (WPP) have a key role in power system generation. On the other hand, the wind speed uncertainty affects the WPPs commitments in the forward power markets. In this paper, a new model to determine the optimal size of suitable ESS technologies to support a wind power producer is developed. Six storage types consist of sodium sulfur battery (NAS), lead-acid battery (LA), lithium-ion battery (Li-ion), vanadium redox battery (VRB), compressed air energy storage (CAES), and thermal energy storage (TES) are considered based on installation and maintenance cost and lifetime. The presented model is based on a stochastic optimization approach. For this purpose, first, based on historical data, the WPP, uses the hybrid method based on Long Short Term Memory (LSTM) method and input selection based on MRMI method, forecasts the electricity price and wind power production for one year. The model's objective is to maximize the profit of WPP from participation in the electricity market by considering ESS capital and maintenance costs. Furthermore, to solve the optimization problem, a new optimization method based on Coot Bird Search Algorithm (CBSA) is considered. The results show that CAES, due to its low installation and maintenance cost and long lifetime, has a larger capacity. With this ESS, the profitability of the wind power producer has increased by 2.19%.