Study on energy consumption prediction method of air-conditioning system from the perspective of indoor environmental parameters by using Elman neural network

Hongji Wu, Wei Li, Changwei Jiang, Xiaoqin Sun and Jili Zhang

Energy, 2025, vol. 335, issue C

Abstract: Introducing real-time energy consumption into the automatic control of air-conditioning can effectively improve energy-saving of indoor environments. Existing methods for predicting energy consumption provide a basis for optimizing operational strategies, which can reduce energy consumption. However, the methods often involve numerous input parameters and fail to quantify energy consumption associated with indoor temperature setpoints under a specific adjustment amount. This paper proposes an Elman neural network-based model for predicting energy consumption in air-conditioning systems. The model takes current indoor temperature and next temperature setpoints as inputs, enabling the precise prediction of energy consumption changes from the current temperature to the next setpoints. Spearman correlation analysis is employed to select input variables, and training parameters are optimized to improve performance. At a learning rate of 0.08, the model exhibits a normalized root mean square error of 0.0547. Results demonstrate that the model provides high predictive accuracy and generalization while significantly reducing input dimensionality and simplifying data collection, providing an innovative solution for real-time energy consumption prediction. By quantifying the effect of indoor temperature setpoint changes on energy consumption, the model aims to guide the selection of optimal temperature setpoints for minimizing energy consumption, thus improving the air-conditioning energy conservation effect.

Keywords: HVAC system; Energy consumption prediction; Elman neural network; Indoor temperature setpoints; Energy efficiency optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225036540
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:335:y:2025:i:c:s0360544225036540

DOI: 10.1016/j.energy.2025.138012

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().