A deterministic policy gradient based load control policy in direct current distribution networks

Hong Duan, Xu Zhou, Xianhong Kang*, Zhongjing Ma

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Developing algorithms for global optimum seeking of non-convex optimization problems has special potential in the real world. Previous researches in this field suffer from resulting a local optimum or losing some accuracy by convex relaxation. In this paper, we consider a demand side management (DSM) problem in direct current (DC) distribution networks as an application to study the global optimum seeking of non-convex optimization. Due to the voltage and network constraints, non-convexity appears in the objective function taking into account the tradeoff between the operation costs and users' preferences. By the freedom to express learning problem as a non-convex optimization, we explore a deterministic policy gradient (DPG) based algorithm to calculate the global optimum. A policy network and a polynomial regression critic are built to learn the optimal policy under an exploration noise. Numerical results are provided to demonstrate the DPG algorithm increasing the probability of convergence to the global optimum.

Original languageEnglish
Title of host publicationProceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019
PublisherInternational Workshop on Computer Science and Engineering (WCSE)
Pages996-1001
Number of pages6
ISBN (Electronic)9789811416842
Publication statusPublished - 2020
Event2019 9th International Workshop on Computer Science and Engineering, WCSE 2019 - Hong Kong, Hong Kong
Duration: 15 Jun 201917 Jun 2019

Publication series

NameProceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019

Conference

Conference2019 9th International Workshop on Computer Science and Engineering, WCSE 2019
Country/TerritoryHong Kong
CityHong Kong
Period15/06/1917/06/19

Keywords

  • Demand-side management (DSM)
  • Deterministic policy gradient
  • Distribution networks
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'A deterministic policy gradient based load control policy in direct current distribution networks'. Together they form a unique fingerprint.

Cite this

Duan, H., Zhou, X., Kang, X., & Ma, Z. (2020). A deterministic policy gradient based load control policy in direct current distribution networks. In Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019 (pp. 996-1001). (Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019). International Workshop on Computer Science and Engineering (WCSE).