Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations
2026-05-25 • Machine Learning
Machine Learning
AI summaryⓘ
The authors used historical electricity usage data and weather information from two university campuses to predict electricity consumption for the next year. They tested several machine learning methods and improved them by selecting important features and tuning model settings. Their combined method, called Weaker Separator Booster (WSB), gave the most accurate predictions. They also found that past electricity use was much more important for predictions than weather factors. This work helps manage electricity costs better in expanding institutions.
electricity consumption forecastingmachine learninglong short-term memory (LSTM)random forest (RF)support vector regression (SVR)extreme gradient boosting (XGBoost)Shapley additive explanations (SHAP)genetic algorithm (GA)particle swarm optimization (PSO)ensemble learning
Authors
Eduardo Luiz Alba, Gilson Adamczuk Oliveira, Matheus Henrique Dal Molin Ribeiro, Érick Oliveira Rodrigues
Abstract
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.