A deep-learning approach for modeling the demand function of air conditioning resources with respect to the electricity prices

Chenge Gao, Ye Guo, Yinliang Xu, Jieming Huang, Fan Zhang, Wuhua Hu and Qiang Liu

Applied Energy, 2025, vol. 392, issue C, No S030626192500707X

Abstract: This study considers the problem of modeling the demand function of air conditioning (AC) resources with respect to electricity prices. We propose a deep-learning approach based on the staircase properties of demand functions and their sensitivity to price and temperature fluctuations. The model integrates two expert networks which capture common features for ACs in the same area – one for price and one for temperature – dynamically weighted by gate units adjusted based on historical data, allowing the model to adaptively balance the influence of both factors. Furthermore, trainable staircase activation functions in the output layer enable flexible modeling across diverse AC resources with substantially lower sample requirements. Simulations on two cases, New York City and Shenzhen, demonstrate that the proposed method achieves accurate performance for a wide range of AC resources and reduces the cost when participating in the market.

Keywords: Air-conditioners; Deep learning; Distributed energy resources; Electricity markets (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S030626192500707X
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:appene:v:392:y:2025:i:c:s030626192500707x

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2025.125977

Access Statistics for this article

Applied Energy is currently edited by J. Yan

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