Deep Reinforcement Learning Based Dynamic Pricing Demand Response of Smart Grid

With the development of modern information and communication technology, dynamic pricing demand response algorithm is more and more widely used in smart grid system. In this paper, a dynamic pricing demand response algorithm is proposed, which considers the profits of power company and the costs of...

Full description

Saved in:

Bibliographic Details
Published in:	2022 First International Conference on Cyber-Energy Systems and Intelligent Energy (ICCSIE) pp. 1 - 6
Main Authors:	Qiang, Chengpeng, Zhang, Huifeng, Zhang, Anhua
Format:	Conference Proceeding
Language:	English
Published:	IEEE 14-01-2023
Subjects:	Demand response Dynamic pricing Markov decision Reinforcement learning
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	With the development of modern information and communication technology, dynamic pricing demand response algorithm is more and more widely used in smart grid system. In this paper, a dynamic pricing demand response algorithm is proposed, which considers the profits of power company and the costs of power customers. The reinforcement learning method is mainly used to solve this problem. The dynamic pricing problem is expressed as a discrete finite Markov Decision Process (MDP), and Deep Deterministic Policy Gradient (DDPG) is used to solve the decision problem. The power company can adaptively determine the retail price in the online learning process, which solves the uncertainty of the power customers' load demand curve and the flexibility of the wholesale price. At the same time, on the basis of the retail price, increase the cash subsidy incentives for power customers to fully mobilize the willingness of customers to participate in the response. The final simulation results show that the demand response algorithm can improve the profitability of power company, reduce the energy cost of power customers, balance the energy supply and demand in the power market, and improve the reliability of power systems, which can be seen as a win-win strategy for company and customers.
DOI:	10.1109/ICCSIE55183.2023.10175274