Predicting Residential Electricity Consumption Using CNN-BiLSTM-SA Neural Networks

Abstract

As global population growth and the use of household appliances increase, residential electricity consumption has surged, leading to challenges in maintaining a balanced electrical load. This surge often results in localized and intermittent power outages, adversely affecting residential electricity reliability and the profitability of power supply companies. Addressing this, we propose a novel CNN-BiLSTM-SA model, combining Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Self-Attention (SA) mechanisms, to accurately predict residential electricity consumption. The model integrates temporal feature extraction through the CNN module, correlation capture via BiLSTM, and intrinsic feature analysis using SA mechanisms, enhancing predictive accuracy. Our experimental results demonstrate the model's precision, outperforming existing methods in key performance metrics. Additionally, ablation studies affirm the synergistic design of CNN-BiLSTM-SA's network components, contributing to its overall efficacy.