Application of Genetic Algorithm-Optimized Backpropagation Network in Library Energy Consumption Prediction

Xiangyu Tian, Haiyan Xie
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:205-211, 2025.

Abstract

The development of building energy consumption prediction models is crucial for achieving sustainable development in the construction industry; however, establishing rational, accurate, and efficient models to promote energy conservation and enhance energy utilization efficiency remains a challenge. This study takes libraries as a representative building type, selecting operational hours, humidity, maximum temperature, occupancy density, and solar irradiance as key influencing factors to construct a Genetic Algorithm-optimized Backpropagation (GA-BP) neural network for energy consumption prediction. Comparative experiments with a standard Backpropagation (BP) neural network, Regularized Radial Basis Function (RRBF) neural network, and Generalized Radial Basis Function (GRBF) neural network demonstrate the superior fitting performance of the GA-BP model, providing reliable scientific support for library energy management and offering a practical framework for energy-efficient building operations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-tian25a, title = {Application of Genetic Algorithm-Optimized Backpropagation Network in Library Energy Consumption Prediction}, author = {Tian, Xiangyu and Xie, Haiyan}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {205--211}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/tian25a/tian25a.pdf}, url = {https://proceedings.mlr.press/v278/tian25a.html}, abstract = {The development of building energy consumption prediction models is crucial for achieving sustainable development in the construction industry; however, establishing rational, accurate, and efficient models to promote energy conservation and enhance energy utilization efficiency remains a challenge. This study takes libraries as a representative building type, selecting operational hours, humidity, maximum temperature, occupancy density, and solar irradiance as key influencing factors to construct a Genetic Algorithm-optimized Backpropagation (GA-BP) neural network for energy consumption prediction. Comparative experiments with a standard Backpropagation (BP) neural network, Regularized Radial Basis Function (RRBF) neural network, and Generalized Radial Basis Function (GRBF) neural network demonstrate the superior fitting performance of the GA-BP model, providing reliable scientific support for library energy management and offering a practical framework for energy-efficient building operations.} }
Endnote
%0 Conference Paper %T Application of Genetic Algorithm-Optimized Backpropagation Network in Library Energy Consumption Prediction %A Xiangyu Tian %A Haiyan Xie %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-tian25a %I PMLR %P 205--211 %U https://proceedings.mlr.press/v278/tian25a.html %V 278 %X The development of building energy consumption prediction models is crucial for achieving sustainable development in the construction industry; however, establishing rational, accurate, and efficient models to promote energy conservation and enhance energy utilization efficiency remains a challenge. This study takes libraries as a representative building type, selecting operational hours, humidity, maximum temperature, occupancy density, and solar irradiance as key influencing factors to construct a Genetic Algorithm-optimized Backpropagation (GA-BP) neural network for energy consumption prediction. Comparative experiments with a standard Backpropagation (BP) neural network, Regularized Radial Basis Function (RRBF) neural network, and Generalized Radial Basis Function (GRBF) neural network demonstrate the superior fitting performance of the GA-BP model, providing reliable scientific support for library energy management and offering a practical framework for energy-efficient building operations.
APA
Tian, X. & Xie, H.. (2025). Application of Genetic Algorithm-Optimized Backpropagation Network in Library Energy Consumption Prediction. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:205-211 Available from https://proceedings.mlr.press/v278/tian25a.html.

Related Material