Lagged Load Wavelet Decomposition and LSTM Networks for Short-Term Load Forecasting

Short-term load forecasting (STLF) is one of the main challenging problems in management of power systems. By emerging the new technologies and development of smart grids, STLF becomes a necessity. A STLF framework is proposed in this work which uses the long short-term memory (LSTM) network for forecasting. In the proposed framework, a feature vector containing the lagged load values is considered for each point of the load time series where this feature vector can be given to the LSTM network in three ways: 1) the original feature vector (LSTM), 2) the coefficients of discrete wavelet transform of the feature vector (DWT-LSTM), and 3) the stacked vector of wavelet coefficients and original load values (DWT-stack-LSTM). In the proposed DWT-stack-LSTM method, both of original values of load and decomposition values of load in different frequencies and scales are given to LSTM. Thus, LSTM is trained to learn more about load variables and so, provides more accurate forecasting results.