Strathprints logo
Strathprints Home | Open Access | Browse | Search | User area | Copyright | Help | Library Home | SUPrimo

Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade

Lincoln, Richard and Galloway, Stuart and Stephen, Bruce and Burt, Graeme (2012) Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade. IEEE Transactions on Power Systems, 27 (1). pp. 373-380. ISSN 0885-8950

[img] PDF
tps_policy_paper_submit_final_040711.pdf - Draft Version

Download (200kB)

Abstract

In electrical power engineering, reinforcement learning algorithms can be used to model the strategies of electricity market participants. However, traditional value function based reinforcement learning algorithms suffer from convergence issues when used with value function approximators. Function approximation is required in this domain to capture the characteristics of the complex and continuous multivariate problem space. The contribution of this paper is the comparison of policy gradient reinforcement learning methods, using artificial neural networks for policy function approximation, with traditional value function based methods in simulations of electricity trade. The methods are compared using an AC optimal power flow based power exchange auction market model and a reference electric power system model.

Item type: Article
ID code: 33071
Keywords: artificial Intelligence, game theory, gradient methods, learning control systems, neural network applications, power system economics , Electrical engineering. Electronics Nuclear engineering, Energy Engineering and Power Technology, Electrical and Electronic Engineering
Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
Department: Faculty of Engineering > Electronic and Electrical Engineering
Depositing user: Pure Administrator
Date Deposited: 18 Nov 2011 16:45
Last modified: 27 Mar 2015 03:27
URI: http://strathprints.strath.ac.uk/id/eprint/33071

Actions (login required)

View Item View Item