Review of Artificial Neural Network Approaches for Predicting Building Energy Consumption

• Published in: 2023 IEEE 3rd International Conference in Power Engineering Applications: Shaping Sustainability Through Power Engineering Innovation, ICPEA 2023
• Main Author: Md Ramli S.S.; Nizam Ibrahim M.; Mohamad A.; Daud K.; Saidina Omar A.M.; Darina Ahmad N.
• Format: Conference paper
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85156107051&doi=10.1109%2fICPEA56918.2023.10093183&partnerID=40&md5=9c806b69049917851a58079c6811c6cd

Recently, the forecasting of energy consumption has prompted a massive escalation in research studies that are being conducted all over the world in an effort to attain higher levels of sustainability. Forecasting is essential to decision-making for effective energy conservation and development within an organization. The adoption of data-driven models for energy forecasting has seen tremendous growth in the past few decades as a result of improvements in performance, robustness, and simplicity of deployment brought about by these improvements. There are various kinds of models, but Artificial Neural Networks (ANN) are currently among the most widely used data-driven methods that have been applied to real-world situations. This study provides a comprehensive overview of research on ANN and a comparison with other data-driven models and the evaluation metrics were employed to evaluate the performances of each technique. This review helps to outline potential future research in the area of data-driven building energy consumption prediction and prominence existing research gaps. © 2023 IEEE.