A Hybrid Residential Short-Term Load Forecasting Method Using Attention Mechanism and Deep Learning

Abstract

Development in economics and social society has led to rapid growth in electricity demand. Accurate residential electricity load forecasting is helpful for the transformation of residential energy consumption structure and can also curb global climate warming. This paper proposes a hybrid residential short-term load forecasting framework (DCNN-LSTM-AE-AM) based on deep learning, which combines dilated convolutional neural network (DCNN), long short-term memory network (LSTM), autoencoder (AE), and attention mechanism (AM) to improve the prediction results. First, we design a T-nearest neighbors (TNN) algorithm to preprocess the original data. Further, a DCNN is introduced to extract the long-term feature. Secondly, we combine the LSTM with the AE (LSTM-AE) to learn the sequence features hidden in the extracted features and decode them into output features. Finally, the AM is further introduced to extract and fuse the high-level stage features to achieve the prediction results. Experiments on two real-world datasets show that the proposed method is good at capturing the oscillation characteristics of low-load data and outperforms other methods.

Multivariate Time-Series Forecasting: A Review of Deep Learning Methods in Internet of Things Applications to Smart Cities

“…Hybrids including CNNs were also further enhanced with the incorporation of the attention mechanism for residential load forecasting [143,144]. Furthermore, Ji et al [145] proposed a hybrid residential short-term load forecasting framework, which blends a dilated CNN to extract the long-term data relationships, an LSTM to capture the sequence features hidden in the extracted features, an autoencoder to decode them into output features, and finally an attention mechanism.…”