Smart Buildings Energy Consumption Forecasting using Adaptive Evolutionary Ensemble Learning Models

2025-06-13

AI Summary

Building-level energy consumption forecasting faces dual challenges: strong temporal oscillations and coupled linear/nonlinear patterns. To address these, this paper proposes a novel ensemble learning framework tailored for aggregate building energy prediction. The method introduces an adaptive evolutionary hyperparameter optimization mechanism that dynamically coordinates three ensemble strategies—Bagging, Stacking, and Voting—while leveraging multi-source sensor time-series data. This integration enhances model generalization and robustness against nonstationary and heterogeneous energy dynamics. Evaluated on a real-world Belgian dataset, the proposed adaptive evolutionary Bagging model achieves state-of-the-art accuracy: it reduces mean absolute error (MAE) by 12.6%–27.04% compared to leading gradient-boosting methods including XGBoost and CatBoost. The framework demonstrates superior performance in capturing complex temporal dependencies and mitigating overfitting under limited or noisy operational data—establishing a new benchmark for building energy forecasting.

Technology Category

• Machine Learning: Ensemble Methods
• Search and Optimization: Evolutionary Computation
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Smart buildings are gaining popularity because they can enhance energy efficiency, lower costs, improve security, and provide a more comfortable and convenient environment for building occupants. A considerable portion of the global energy supply is consumed in the building sector and plays a pivotal role in future decarbonization pathways. To manage energy consumption and improve energy efficiency in smart buildings, developing reliable and accurate energy demand forecasting is crucial and meaningful. However, extending an effective predictive model for the total energy use of appliances at the building level is challenging because of temporal oscillations and complex linear and non-linear patterns. This paper proposes three hybrid ensemble predictive models, incorporating Bagging, Stacking, and Voting mechanisms combined with a fast and effective evolutionary hyper-parameters tuner. The performance of the proposed energy forecasting model was evaluated using a hybrid dataset comprising meteorological parameters, appliance energy use, temperature, humidity, and lighting energy consumption from various sections of a building, collected by 18 sensors located in Stambroek, Mons, Belgium. To provide a comparative framework and investigate the efficiency of the proposed predictive model, 15 popular machine learning (ML) models, including two classic ML models, three NNs, a Decision Tree (DT), a Random Forest (RF), two Deep Learning (DL) and six Ensemble models, were compared. The prediction results indicate that the adaptive evolutionary bagging model surpassed other predictive models in both accuracy and learning error. Notably, it achieved accuracy gains of 12.6%, 13.7%, 12.9%, 27.04%, and 17.4% compared to Extreme Gradient Boosting (XGB), Categorical Boosting (CatBoost), GBM, LGBM, and Random Forest (RF).

Problem

• Forecasting energy consumption in smart buildings accurately
• Managing temporal oscillations and complex energy patterns
• Improving energy efficiency via evolutionary ensemble models

Innovation

• Hybrid ensemble models with Bagging, Stacking, Voting
• Evolutionary hyper-parameters tuner for optimization
• Adaptive evolutionary bagging model outperforms others