Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations

• Published in: Forecasting Vol. 6; no. 3; pp. 839 - 863
• Main Authors: Alba, Eduardo Luiz, Oliveira, Gilson Adamczuk, Ribeiro, Matheus Henrique Dal Molin, Rodrigues, Érick Oliveira
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2024
• Subjects: Accuracy; Algorithms; Artificial intelligence; College campuses; Colleges & universities; Commonality; Competitive advantage; Datasets; educational institution; Electricity; Electricity consumption; Electricity distribution; Energy consumption; Ensemble learning; Environmental management; Feature selection; Forecasting; Genetic algorithms; hyperparameter optimization; Machine learning; Mathematical optimization; Neural networks; Optimization algorithms; Particle swarm optimization; Shapley values; Support vector machines; Time series; university; Variables; Brazil
• ISSN: 2571-9394; 2571-9394
• DOI: 10.3390/forecast6030042

Electricity expense management presents significant challenges, as this resource is susceptible to various influencing factors. In universities, the demand for this resource is rapidly growing with institutional expansion and has a significant environmental impact. In this study, the machine learning models long short-term memory (LSTM), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost) were trained with historical consumption data from the Federal Institute of Paraná (IFPR) over the last seven years and climatic variables to forecast electricity consumption 12 months ahead. Datasets from two campuses were adopted. To improve model performance, feature selection was performed using Shapley additive explanations (SHAP), and hyperparameter optimization was carried out using genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate that the proposed cooperative ensemble learning approach named Weaker Separator Booster (WSB) exhibited the best performance for datasets. Specifically, it achieved an sMAPE of 13.90% and MAE of 1990.87 kWh for the IFPR–Palmas Campus and an sMAPE of 18.72% and MAE of 465.02 kWh for the Coronel Vivida Campus. The SHAP analysis revealed distinct feature importance patterns across the two IFPR campuses. A commonality that emerged was the strong influence of lagged time-series values and a minimal influence of climatic variables.