End-to-end data-driven modeling framework for automated and trustworthy short-term building energy load forecasting
)Abstract
Conventional automated machine learning (AutoML) technologies fall short in preprocessing low-quality raw data and adapting to varying indoor and outdoor environments, leading to accuracy reduction in forecasting short-term building energy loads. Moreover, their predictions are not transparent because of their black box nature. Hence, the building field currently lacks an AutoML framework capable of data quality enhancement, environment self-adaptation, and model interpretation. To address this research gap, an improved AutoML-based end-to-end data-driven modeling framework is proposed. Bayesian optimization is applied by this framework to find an optimal data preprocessing process for quality improvement of raw data. It bridges the gap where conventional AutoML technologies cannot automatically handle missing data and outliers. A sliding window-based model retraining strategy is utilized to achieve environment self-adaptation, contributing to the accuracy enhancement of AutoML technologies. Moreover, a local interpretable model-agnostic explanations-based approach is developed to interpret predictions made by the improved framework. It overcomes the poor interpretability of conventional AutoML technologies. The performance of the improved framework in forecasting one-hour ahead cooling loads is evaluated using two-year operational data from a real building. It is discovered that the accuracy of the improved framework increases by 4.24%–8.79% compared with four conventional frameworks for buildings with not only high-quality but also low-quality operational data. Furthermore, it is demonstrated that the developed model interpretation approach can effectively explain the predictions of the improved framework. The improved framework offers a novel perspective on creating accurate and reliable AutoML frameworks tailored to building energy load prediction tasks and other similar tasks.
Keywords
References
Chen Z, Xiao F, Guo F, et al. (2023). Interpretable machine learning for building energy management: A state-of-the-art review. Advances in Applied Energy, 9: 100123.
Ding Y, Zhang Q, Yuan T, et al. (2018). Effect of input variables on cooling load prediction accuracy of an office building. Applied Thermal Engineering, 128: 225–234.
Fan C, Xiao F, Wang S (2014). Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques. Applied Energy, 127: 1–10.
Fan C, Xiao F, Zhao Y (2017). A short-term building cooling load prediction method using deep learning algorithms. Applied Energy, 195: 222–233.
Fan C, Chen M, Tang R, et al. (2022). A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions. Building Simulation, 15: 197–211.
Kim J, Kwak Y, Mun S-H, et al. (2022). Electric energy consumption predictions for residential buildings: Impact of data-driven model and temporal resolution on prediction accuracy. Journal of Building Engineering, 62: 105361.
Li A, Xiao F, Fan C, et al. (2021). Development of an ANN-based building energy model for information-poor buildings using transfer learning. Building Simulation, 14: 89–101.
Li J, Zhang C, Zhao Y, et al. (2022). Federated learning-based short-term building energy consumption prediction method for solving the data silos problem. Building Simulation, 15: 1145–1159.
Li A, Zhang C, Xiao F, et al. (2023). Large-scale comparison and demonstration of continual learning for adaptive data-driven building energy prediction. Applied Energy, 347: 121481.
Li G, Wu Y, Yan C, et al. (2024). An improved transfer learning strategy for short-term cross-building energy prediction using data incremental. Building Simulation, 17: 165–183.
Lu H, Cheng F, Ma X, et al. (2020). Short-term prediction of building energy consumption employing an improved extreme gradient boosting model: A case study of an intake tower. Energy, 203: 117756.
Lu J, Zhang C, Li J, et al. (2022). Graph convolutional networks-based method for estimating design loads of complex buildings in the preliminary design stage. Applied Energy, 322: 119478.
Lu C, Li S, Reddy Penaka S, et al. (2023). Automated machine learning-based framework of heating and cooling load prediction for quick residential building design. Energy, 274: 127334.
Mehmood F, Ghani MU, Ghafoor H, et al. (2022). EGD-SNet: A computational search engine for predicting an end-to-end machine learning pipeline for Energy Generation & Demand Forecasting. Applied Energy, 324: 119754.
Nie P, Roccotelli M, Fanti MP, et al. (2021). Prediction of home energy consumption based on gradient boosting regression tree. Energy Reports, 7: 1246–1255.
Olu-Ajayi R, Alaka H, Sulaimon I, et al. (2022). Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. Journal of Building Engineering, 45: 103406.
Pino-Mejías R, Pérez-Fargallo A, Rubio-Bellido C, et al. (2017). Comparison of linear regression and artificial neural networks models to predict heating and cooling energy demand, energy consumption and CO2 emissions. Energy, 118: 24–36.
Qiao Q, Yunusa-Kaltungo A, Edwards RE (2022). Feature selection strategy for machine learning methods in building energy consumption prediction. Energy Reports, 8: 13621–13654.
Seyedzadeh S, Pour Rahimian F, Rastogi P, et al. (2019). Tuning machine learning models for prediction of building energy loads. Sustainable Cities and Society, 47: 101484.
Shi X, Wong YD, Li MZF, et al. (2019). A feature learning approach based on XGBoost for driving assessment and risk prediction. Accident Analysis and Prevention, 129: 170–179.
Tang R, Fan C, Zeng F, et al. (2022). Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression. Building Simulation, 15: 317–331.
Zhang C, Li J, Zhao Y, et al. (2020a). A hybrid deep learning-based method for short-term building energy load prediction combined with an interpretation process. Energy and Buildings, 225: 110301.
Zhang C, Zhao Y, Fan C, et al. (2020b). A generic prediction interval estimation method for quantifying the uncertainties in ultra-short-term building cooling load prediction. Applied Thermal Engineering, 173: 115261.
Zhang C, Tian X, Zhao Y, et al. (2023a). Automated machine learning-based building energy load prediction method. Journal of Building Engineering, 80: 108071.
Zhang L, Chen Z, Zhang X, et al. (2023b). Challenges and opportunities of machine learning control in building operations. Building Simulation, 16: 831–852.
Zhang C, Lu J, Zhao Y (2024). Generative pre-trained transformers (GPT)-based automated data mining for building energy management: advantages, limitations and the future. Energy and Built Environment, 5: 143–169.
Zhao D, Zhong M, Zhang X, et al. (2016). Energy consumption predicting model of VRV (variable refrigerant volume) system in office buildings based on data mining. Energy, 102: 660–668.
Zhao Y, Zhang C, Zhang Y, et al. (2020). A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis. Energy and Built Environment, 1: 149–164.
Zhou Y, Tian X, Zhang C, et al. (2022). Elastic weight consolidation-based adaptive neural networks for dynamic building energy load prediction modeling. Energy and Buildings, 265: 112098.
京公网安备11010802044758号