A Review of Algorithm-Based Energy-Saving Optimization in Buildings

DOI: https://doi.org/10.62517/jes.202602405

Author(s)

Mingze Li

Affiliation(s)

Building Environment and Energy Application Engineering, Faculty of Science and Engineering, University of Nottingham Ningbo China, Ningbo, Zhejiang, China

Abstract

The building sector is a major source of energy demand and carbon emissions, so algorithm-based energy-saving optimization has become important for low-carbon construction and operation. This review examines five recent computational intelligence approaches used in building energy efficiency and construction management: an artificial-neural-network-driven genetic algorithm (ANN-GA), a hybrid NSGA-II-MOPSO algorithm, an entropy-based grey wolf optimizer (ENTGWO), a BIM-integrated deep Q-network (BIM-DQN), and the Falco peregrinus optimization algorithm with its multi-objective extension (FPO/MOFPO). The paper compares their principles, application scenarios, and practical significance. The reviewed studies show that hybrid and adaptive algorithms improve convergence, search diversity, and engineering usability, especially when combined with surrogate models or structured digital building data. The review also identifies limitations, including weak treatment of occupant behaviour, limited real-time validation, and dependence on expert parameter tuning. Overall, intelligent optimization methods provide useful pathways for reducing building energy use, but future research should move toward transparent, transferable, and human-centred optimization platforms.

Keywords

Building Energy Efficiency; Optimization Algorithm; Genetic Algorithm; Artificial Neural Network; NSGA-II; MOPSO; Grey Wolf Optimizer; Reinforcement Learning; Building Information Modelling; Carbon Reduction

References

[1] Ioannidis, D., Rigopoulos, P., Braimakis, K., Pallis, P. and Karellas, S. (2026) Multi-objective ANN-driven genetic algorithm optimization of energy efficiency measures in an NZEB multi-family house building in Greece. Energy and Buildings, 351, 116653. [2] Yu, Y., Chen, X., Guo, X., Chen, W. and Wei, S. (2026) A multi-objective optimization strategy for ultra-low energy residential buildings based on a hybrid machine learning algorithm. Energy, 344, 140037. [3] Li, Y. and Zhang, Y. (2025) Computer Algorithm Optimization of BIM and Reinforcement Learning in Complex Building Structure Construction Process Optimization Under Big Data Environment. Procedia Computer Science, 261, pp. 262-269. [4] Deb, K., Pratap, A., Agarwal, S. and Meyarivan, T. (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), pp. 182-197. [5] Coello Coello, C.A., Pulido, G.T. and Lechuga, M.S. (2004) Handling multiple objectives with particle swarm optimization. IEEE Transactions on Evolutionary Computation, 8(3), pp. 256-279. [6] Mirjalili, S., Mirjalili, S.M. and Lewis, A. (2014) Grey Wolf Optimizer. Advances in Engineering Software, 69, pp. 46-61. [7] Tugal, I. (2025) Energy efficiency in building: Entropy-based Grey Wolf Optimization for improved MLP performance. Energy Reports, 13, pp. 4247-4260. [8] Mnih, V. et al. (2015) Human-level control through deep reinforcement learning. Nature, 518, pp. 529-533. [9] Wei, L. and Zhong, H. (2026) Falco peregrinus optimization algorithm: A novel biomimetic metaheuristic algorithm for engineering applications. Energy Reports, 15, 109064.