Energy Consumption Forecasting in Commercial Buildings during the COVID-19 Pandemic: A Multivariate Multilayered Long-Short Term Memory Time-Series Model with Knowledge Injection

The COVID-19 pandemic and the subsequent implementation of lockdown measures have significantly impacted global electricity consumption, necessitating accurate energy consumption forecasts for optimal energy generation and distribution during a pandemic. In this paper, we propose a new forecasting model called the multivariate multilayered long short-term memory (LSTM) with COVID-19 case injection (mv-M-LSTM-CI) for improved energy forecast during the next occurrence of a similar pandemic. We utilized data from commercial buildings in Melbourne, Australia, during the COVID-19 pandemic to predict energy consumption and evaluate the model's performance against commonly used methods such as LSTM, bidirectional LSTM, linear regression, support vector machine, and multilayered LSTM (M-LSTM). The proposed forecasting model was analyzed using the following metrics: mean percent absolute error (MPAE), normalized root mean square error (NRMSE), and R2 score values. The model mv-M-LSTM-CI demonstrated superior performance, achieving the lowest mean percentage absolute error values of 0.061, 0.093, and 0.158 for DatasetS1, DatasetS2, and DatasetS3, respectively. Our results highlight the improved precision and accuracy of the model, providing valuable information for energy management and decision making during the challenges posed by the occurrence of a pandemic like COVID-19 in the future.