DSM pricing method based on A3C and LSTM under cloud-edge environment

Fangyuan Sun, Xiangyu Kong, Jianzhong Wu, Bixuan Gao, Ke Chen and Ning Lu

Applied Energy, 2022, vol. 315, issue C, No S0306261922002896

Abstract: Demand-side management (DSM) could realize “peak cutting and valley filling” of power load and improve the stability and efficiency of power system. With the development of information systems, more smart devices are being deployed on the demand side. It has become a challenge for DSM service providers to take full use of the edge computing capacity and demand-side information to improve the accuracy of DSM decision-making, without revealing user privacy. This paper proposes a distributed DSM pricing method for service provider, based on asynchronous advantage actor-critic (A3C) algorithm and long short-term memory (LSTM) network under cloud-edge environment. The on-site utilization of user information is realized through distributed training and centralized decision-making structure of A3C algorithm. The training process is accelerated by LSTM based virtual environment, which greatly reduces the training cost of the algorithm. Case study results shows that the proposed method is able to make pricing decision for DSM service provider under cloud-edge environment. Moreover, through the combination of LSTM based virtual environment and A3C algorithm, the proposed method requires less historical data than other methods and improves the profit of service providers.

Keywords: Demand-side management; LSTM; A3C; Cloud-edge environment (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261922002896
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:315:y:2022:i:c:s0306261922002896

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.2022.118853

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 ().