Graph Deep Learning-based Retail Dynamic Pricing for Demand Response

• Published in: IEEE transactions on smart grid Vol. 14; no. 6; p. 1
• Main Authors: Ruan, Jiaqi, Liang, Gaoqi, Zhao, Junhua, Lei, Shunbo, He, Binghao, Qiu, Jing, Dong, Zhao Yang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.11.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Behavior; Behavioral sciences; Consumers; Customization; Customized dynamic pricing; Deep learning; demand re-sponse; Demand response; Demand side management; Elasticity; Energy consumption; Energy management; Feasibility studies; graph deep learning; Peak load; Peak to average power ratio; Price elasticity; Pricing; Smart meters; temporal price elasticity per-ceptron
• ISSN: 1949-3053; 1949-3061
• DOI: 10.1109/TSG.2023.3258605

Designing customized dynamic pricing is a promising way to incent consumers to adjust their daily en-ergy consumption behaviors. It helps manage flexible de-mand response resources on peak load. However, it is insuf-ficiently investigated in previous studies from the individual behavior perspective. To tackle the gap, this paper proposes a graph deep learning-based retail dynamic pricing mecha-nism. First, a graph attention network-based temporal price elasticity perceptron model is proposed. It explores a novel path to learn price elasticity by using graph deep learning, and can accurately assess consumers energy consumption behaviors under different prices. Then, to avoid unfair eval-uation of demand response, two indexes are proposed as auxiliary measures to assess energy consumption behavior learning models. At last, a customized dynamic pricing model based on the temporal price elasticity perceptron model is proposed. It can develop consumers time-varying demand response potential. This potential is first defined in this paper to measure what potentials of shifting/curtailing energy during a period a consumer has. By the pricing, the consumer could be incented to engage in demand response. The numerical studies validate the feasibility and superior-ity of the proposed methods, meanwhile price risks from the price change can be hedged effectively.