Short-term Load Forecasting Based on Electricity Price in LSTM in Power Grid

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Cai, Ruyi^1 ; Li, Shixin^1 ; Tian, Jiecai^1 ; Ren, Liqiang^2

College of Electronic Engineering, Tianjin University of Technology and Education, Tianjin

300222, China^1

Tianjin Shitai Group Co. Ltd., Tianjin

300222, China^2

关键词: Active distribution networks;    Electricity prices;    Power grids;    Prediction accuracy;    Short term load forecasting;    Short term loads;    Short term memory;    Stable operation;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/4/042046/pdf
DOI  :  10.1088/1757-899X/569/4/042046

来源: IOP

【 摘 要 】

In the electricity market, accurate short-term load forecasting can ensure the safe and stable operation of the grid, but the real-time fluctuation of electricity price increases the complexity of load changes and increases the difficulty of forecasting. In response to this problem, this paper studies the correlation between electricity price and power load, and provides a basis for the prediction of short-term load in the active distribution network. Based on the correlation between electricity price and power load, this paper proposes a short-term load forecasting model for long-term and short-term memory-cycle neural networks. Taking the power data of a certain area as an example, the LSTM model and other models were used to carry out simulation experiments. The results show that the proposed method outperforms other models in terms of prediction accuracy and stability.