A Novel Data-Driven Method for Medium-Term Power Consumption Forecasting Based on Transformer-LightGBM

Abstract

With the widespread use of new energy sources and Internet of things, the power market landscape has become complex. In particular, new energy is more stochastic and volatile; it is prone to the problems of inaccurate forecasting on longer time scales, affecting electricity trading. This study proposes a new method for predicting medium-term load series data based on the transformer-lightGBM. The method first preprocesses electricity market data, including missing value processing, outlier processing, overall analysis, and correlation analysis, to extract features with a strong correlation to medium-term electricity consumption forecasts. Then, a transformer neural network is used to learn the complex patterns and dynamic time scales of the load series data to predict the day-ahead market series. Finally, lightGBM is used to combine power characteristics and time characteristics to forecast power consumption. The effectiveness of the proposed method is proved using the ISO-NE dataset. Experimental results indicate that the present method verified more accurate prediction than LSTM-based methods.