Short-Term Aggregated Residential Load Forecasting using BiLSTM and CNN-BiLSTM

TL;DR

This paper compares BiLSTM and CNN-BiLSTM neural networks for short-term residential load forecasting, demonstrating that BiLSTM achieves the lowest RMSE in predicting 24-hour aggregated power demand.

Contribution

It introduces and evaluates BiLSTM and CNN-BiLSTM models for residential load forecasting, showing BiLSTM's superior accuracy over other deep learning models.

Findings

BiLSTM achieved the lowest RMSE of 1.4842.

BiLSTM outperformed LSTM, CNN-LSTM, and CNN-BiLSTM models.

The source code is publicly available.

Abstract

Higher penetration of renewable and smart home technologies at the residential level challenges grid stability as utility-customer interactions add complexity to power system operations. In response, short-term residential load forecasting has become an increasing area of focus. However, forecasting at the residential level is challenging due to the higher uncertainties involved. Recently deep neural networks have been leveraged to address this issue. This paper investigates the capabilities of a bidirectional long short-term memory (BiLSTM) and a convolutional neural network-based BiLSTM (CNN-BiLSTM) to provide a day ahead (24 hr.) forecasting at an hourly resolution while minimizing the root mean squared error (RMSE) between the actual and predicted load demand. Using a publicly available dataset consisting of 38 homes, the BiLSTM and CNN-BiLSTM models are trained to forecast the aggregated active power demand for each hour within a 24 hr. span, given the previous 24 hr. load data. The BiLSTM model achieved the lowest RMSE of 1.4842 for the overall daily forecast. In addition, standard LSTM and CNN-LSTM models are trained and compared with the BiLSTM architecture. The RMSE of BiLSTM is 5.60%, 2.85% and 2.60% lower than the LSTM, CNN-LSTM and CNN-BiLSTM models respectively. The source code of this work is available at https://github.com/Varat7v2/STLF-BiLSTM-CNNBiLSTM.git.