Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems

Zechao Zhang; Zhiping Huang; Qingshan Wang; Fengzhu lv; Shimeng Zhao; Jizhe Sun

doi:10.47297/taposatWSP2633-456904.20260706

PDF
Export
Share
Collection
Album

Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems

Volume 7, Issue 6

Views: 0 Downloads: 0

Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems
Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems
The Fourth Construction Co.,Ltd of China Construction Eighth Engineering Division, Qingdao, Shandong, 266000, China
Vol. 7, Issue 6, Pages: 20-25(2026)
Online First：18 August 2026，

Published：30 June 2026
DOI：10.47297/taposatWSP2633-456904.20260706
Accepted：

Scan QR Code

Zhang Zechao,Huang Zhiping,Wang Qingshan,et al.Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems[J].Theory and Practice of Science and Technology,2026,07(06):20-25.
DOI：

Zhang Zechao,Huang Zhiping,Wang Qingshan,et al.Optimizing Sparrow Search Algorithm for Energy Consumption Prediction in Commercial Building HVAC Systems[J].Theory and Practice of Science and Technology,2026,07(06):20-25. DOI： 10.47297/taposatWSP2633-456904.20260706.

摘要

Abstract

The energy consumption of air conditioning systems typically accounts for over half of the total building energy consumption. Establishing a reasonable prediction model for air conditioning energy consumption plays a crucial role in operational management of air conditioning equipment and effective energy management planning. Currently

large-scale comprehensive commercial buildings present significant challenges in air conditioning energy consumption prediction due to their complex functionalities and irregular energy consumption patterns. In recent years

neural network models have demonstrated remarkable achievements in energy consumption prediction. This study developed six air conditioning energy consumption prediction models based on BP and LSTM algorithms

incorporating an optimized particle swarm algorithm and an optimized sparrow algorithm

to predict the air conditioning energy consumption of a large-scale comprehensive commercial building. The results indicate that the basic BP and LSTM models before optimization tend to produce significant deviations in energy consumption prediction for this building type

particularly during periods of sudden energy consumption changes

peak and valley periods. In contrast

the optimized models substantially improved prediction accuracy. Compared with the basic BP and LSTM models

the optimized ASFSSA-IMCPSO-BP and ASFSSA-IMCPSO-LSTM models achieved MAPE values of 2.24% and 1.59%

with R² values of 0.9742 and 0.9868 respectively

demonstrating excellent predictive performance.

关键词

Keywords

references

Somu N, MR G R, Ramamritham K. A deep learning framework for building energy consumption forecast[J]. Renewable and Sustainable Energy Reviews, 2021, 137: 110591.

You K, Yu Y, Cai W, et al. The change in temporal trend and spatial distribution of CO2 emissions of China's public and commercial buildings[J]. Building and Environment, 2023, 229: 109956.

Solano J C, Caamaño-Martín E, Olivieri L, et al. HVAC systems and thermal comfort in buildings climate control: An experimental case study[J]. Energy Reports, 2021, 7: 269-277.

Li G, Sun C, Sang M, et al. The synergistic effect of multiple design factors on building energy consumption of office blocks: A case study of Wuhan, China[J]. Journal of Building Engineering, 2024, 95: 110200.

Sendra-Arranz R, Gutiérrez A. A long short-term memory artificial neural network to predict daily HVAC consumption in buildings[J]. Energy and Buildings, 2020, 216: 109952.

Li X, Chen S, Li H, et al. A behavior-orientated prediction method for short-term energy consumption of air-conditioning systems in buildings blocks[J]. Energy, 2023, 263: 125940.

Zhang L, Wen J, Li Y, et al. A review of machine learning in building load prediction[J]. Applied Energy, 2021, 285: 116452.

Ouyang C, Qiu Y, Zhu D. Adaptive spiral flying sparrow search algorithm[J]. Scientific Programming, 2021, 2021(1): 6505253.

Zhou C, Fang Z, Xu X, et al. Using long short-term memory networks to predict energy consumption of air-conditioning systems[J]. Sustainable Cities and Society, 2020, 55: 102000.

Li F, Wan Z, Koch T, et al. Improving the accuracy of multi-step prediction of building energy consumption based on EEMD-PSO-Informer and long-time series[J]. Computers and Electrical Engineering, 2023, 110: 108845.

Zhao Y, Dong S, Jiang F, et al. Mooring tension prediction based on BP neural network for semi-submersible platform[J]. Ocean Engineering, 2021, 223: 108714.

Ziyu S, Zeyu A, Huiwei W, et al. Residual LSTM based short-term load forecasting [J ] . Applied Soft Computing Journal, 2023, 144 .

Zhang L, Zhang J, Ren P, et al. Analysis of energy consumption prediction for office buildings based on GA-BP and BP algorithm[J]. Case Studies in Thermal Engineering, 2023, 50: 103445.

Sun H. Prediction of building energy consumption based on BP neural network[J]. Wireless Communications and Mobile Computing, 2022, 2022(1): 7876013.

Wang H, Xu P, Lu X, et al. Methodology of comprehensive building energy performance diagnosis for large commercial buildings at multiple levels[J]. Applied Energy, 2016, 169: 14-27.

Al-Selwi S M, Hassan M F, Abdulkadir S J, et al. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review[J]. Journal of King Saud University-Computer and Information Sciences, 2024: 102068.