A Short Term Load Forecasting by Considering Heat Island Effect Factor Based on IGA-ELM Model

Load forecasting accuracy directly affects the safety, stability, and economic efficiency of the power grid. For the problem that the extreme learning machine (ELM) randomly generates the weights and the thresholds which makes the network model unstable, this paper proposes a load forecasting method based on an improved genetic algorithm (IGA) to optimize the ELM. The characteristics and causes of the heat island effect are analyzed and the prediction accuracy is further improved after adding the heat island effect for the first time, which is of great significance for ensuring the safe and stable operation of the power grid.