Research on STLF Method Based on One-Dimensional Convolution and Slope Feature

Abstract

Short-term load forecasting is of great importance to how to efficiently utilize generating units, optimize resource allocation and ensure the normal transmission of power in power system. This paper mainly studies how to improve the accuracy of short-term load forecasting through feature engineering and deep learning technology. Specifically, we construct a feature based on the slope of load data according to the changing trend of load data. We applied the proposed method to two real datasets of Hunan power grid and obtained MAPE values of 0.5758 and 0.5745 respectively. The experimental results show the effectiveness of the proposed method.