Power Grid Load State Information Perception Forecasting Technology for Battery Energy Storage System Based on Elman Neural Network

摘要

The key to effectively enhance the supporting and regulation capacity of battery energy storage system on power grid is to improve the accuracy of power grid load forecasting. In order to solve the problems in traditional forecasting mathematical models that they lack the ability of self-learning, self-adaptation and have weak robustness of the forecasting system, a new method of forecasting power load using the feedback neural network with the characteristic of input delay is proposed in this paper. The characteristics of Elman neural network model are studied, the experimental model of Elman neural network is established and then trained with real data in power system. The results show that the power grid load forecasting based on this model possesses a high accuracy, and has good adaptability and learning ability for power grid load.