IJDS / Archive / Volume 14, Issue 11

OPEN ACCESS ARTICLE

Understanding time-series building energy data: A review of challenges and forecasting approaches

Mohammed Mahmood Katun, Olawale Muhammed Popoola, Rembuluwani Phillip Tshubwana

1 Department of Electrical Engineering & Centre for Energy and Electric Power (CEEP), Tshwane University of Technology, Pretoria, South Africa 2 Department of Electrical Engineering, Tshwane University of Technology, Pretoria, South Africa

IJDS 2025; 14(11): 935–976.
DOI: 10.63212/IJDS25102301

Read full article (PDF)

Abstract

This article provides an in-depth analysis of building energy consumption, focusing on understanding time series energy data and various predictive techniques. Amidst rapid urbanization and growing energy needs, precisely predicting energy consumption in buildings is critical for improving energy efficiency, fostering sustainability, and optimizing building management systems. The review adopts a narrative review approach, providing a conceptual synthesis of recent advances in building energy prediction by explores the fundamental characteristics of time series electricity consumption data, such as seasonality, trends, non-linearity, and temporal dependencies, spotlighting the challenges these present for forecasting. It covers diverse data acquisition technologies and methods, stressing the common problems of data quality, and effective mitigation strategies through exploratory data analysis and data cleaning techniques. Additionally, the article studies a broad range of time series energy forecasting models, classifying them into statistical, computational intelligence, and hybrid/ensemble approaches. Key considerations for model selection are also explored. The comprehensive forecasting process, from data collection and preparation to model evaluation, is detailed. Ultimately, this study emphasizes that effective data handling and precise model refinement are inherent to accurate prediction, enhancing energy efficiency and effective operations in the built environment.

Keywords: Energy Management; Time Series Energy Data; Building Energy Consumption; Building Energy Forecasting; Predictive Models

How to cite

Katun, M.M., Popoola, M.M. and Tshubwana, R.P. (2021), “Understanding time-series building energy data: A review of challenges and forecasting approaches”, International Journal of Development and Sustainability, Vol. 14 No. 11, pp. 935-976.

Download citation: RIS · BibTeX

Copyright and licence

© 2025 The Author(s). Copyright is retained by the authors.

This article is available under CC BY 4.0. You may share and adapt the work with appropriate attribution, a link to the licence, and an indication of changes. Third-party material is included unless otherwise indicated in its credit line.

Read the journal’s publication policies