Analysis of energy consumption prediction for office buildings based on GA-BP and BP algorithm

• Published in: Case studies in thermal engineering Vol. 50; p. 103445
• Main Authors: Zhang, Lingling, Zhang, Jiran, Ren, Panpan, Ding, Libin, Hao, Wengang, An, Chaofeng, Xu, Ao
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2023; Elsevier
• Subjects: Energy consumption prediction; Parametric simulation; Prediction model evaluation; Significance analysis; Parametric simulation; Energy consumption prediction; Prediction model evaluation; Significance analysis
• ISSN: 2214-157X; 2214-157X
• DOI: 10.1016/j.csite.2023.103445

To gain building energy consumption information during the design phase, the variance analysis to identify significant factors affecting energy consumption in China cold-region office buildings are carried out in this study. Key factors are selected, and prediction models for energy consumption in cold-region office buildings are established using BP and GA-BP algorithms. Three prediction model evaluation indexes are introduced to evaluate the prediction accuracy of the models. The results show that the maximum RMSE of the BP neural network prediction model is 0.498, and the maximum MAPE is 0.797%. Furthermore, the GA algorithm is used to optimize the BP neural network, resulting in a prediction model with a maximum RMSE of 0.359 and a maximum MAPE of 0.289%. The prediction accuracy of the GA-BP algorithm is better than that of the BP algorithm.