Short and Very Short Term Firm-level Load Forecasting for Warehouses: A Comparison of Machine Learning and Deep Learning Models

Abstract

Commercial buildings are a significant consumer of energy worldwide. Logistics facilities, and specifically warehouses, are a common building type yet under-researched in the demand-side energy forecasting literature. Warehouses have an idiosyncratic profile when compared to other commercial and industrial buildings with a significant reliance on a small number of energy systems. As such, warehouse owners and operators are increasingly entering in to energy performance contracts with energy service companies (ESCOs) to minimise environmental impact, reduce costs, and improve competitiveness. ESCOs and warehouse owners and operators require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. This paper explores the performance of three machine learning models (Support Vector Regression (SVR), Random Forest, and Extreme Gradient Boosting (XGBoost)), three deep learning models (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)), and a classical time series model, Autoregressive Integrated Moving Average (ARIMA) for predicting daily energy consumption. The dataset comprises 8,040 records generated over an 11-month period from January to November 2020 from a non-refrigerated logistics facility located in Ireland. The grid search method was used to identify the best configurations for each model. The proposed XGBoost models outperform other models for both very short load forecasting (VSTLF) and short term load forecasting (STLF); the ARIMA model performed the worst.

Short term Markov corrector for building load forecasting system – Concept and case study of day-ahead load forecasting under the impact of the COVID-19 pandemic

“…In the case of non-residential building, no technique has yet achieved significantly better performance than the others [22] . In the comparison in [7] , state-of-the-art machine learning (ARIMA, Support Vector Regression (SVR-10-rbf, SVR-10-linear), Random Forest-9-200, eXtreme Gradient Boosting (XGBoost-5-100, and XGBoost-7-100)) and deep learning (Recurrent Neural Network (RNN-3-400, RNN-4-200), LSTM-3-200, LSTM-3-300, LSTM-4-400, GRU-3-100, and Gated Recurrent Units (GRU-4-300)) models got MAPE from 21.6% to 41.9% errors for short terms load forecasting for a building scale problem (evaluation on 1 hour and 1 day data). In our case study in [16] , the Prophet model achieved an average daily MAPE of 20.68%, 22.28% and 23.07% respectively for the models fit with preCovid, Covid and Mixed data - with the range of variation from 13% to 31% in September 2021 (i.e.…”

“…Medium term LF is necessary for planning and maintenance of electrical network [5] . Finally, short term LF (STLF), along with DRES production forecasting, is critical to balance the energy production/consumption and to determine the optimal usage of DRES for the advanced control of microgrid and for self consumption [6] , [7] . Challenging and dependent on the quality and amount of available data, LF is extensively treated using a wide range of advanced algorithms including regression methods (e.g.…”

Recognition of Geothermal Surface Manifestations: A Comparison of Machine Learning and Deep Learning

“…ML is the science of getting computers to act without being explicitly programmed. In recent decades, ML has proven to be a powerful tool for deriving insights from data [33,34]. It has been applied successfully in self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome thanks to many practical algorithms developed.…”