A Similar Day Based Short Term Load Forecasting Method Using Wavelet Transform and LSTM

With the deregulation of electricity markets, short-term load forecasting (STLF) has gained importance for the operation of power systems. However, an effective STLF model is hard to achieve as the load is affected by various factors. Here we present a STLF method based on similar day approach to predict the electricity usage 24 h ahead and by employing long short-term memory (LSTM) and wavelet transform to further improve the forecasting accuracy. Compared with other methods, the proposed method achieves higher accuracy, and brings out the significance of using similar day's load, wavelet transform, and LSTM network. (c) 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Automated summary

With the deregulation of electricity markets, short-term load forecasting has become increasingly important for power system operation. This study introduces an STLF method based on a similar day approach, using LSTM and wavelet transform to enhance forecasting accuracy.