An improved approximate dynamic programming and its application in SVC control

Jian Sun, Feng Liu, Jennie Si, Wen Tao Guo, Sheng Wei Mei

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The main idea of approximate dynamic programming (ADP) is approximately computing cost function to avoid the curse of dimension. However, it needs many times learning to converge due to the randomly choosing initial weights. So it is greatly limited in the application. This paper presents a direct heuristic dynamic programming (DHDP) based on an improved proportion integration differentiation PID neural network (IPIDNN). This method constructs an equivalent between the initial action network and PID controller. Therefore, well-designed PID controller can guide the initial weights choosing, so that the convergence of this algorithm will be remarkably improved. Moreover, compared with the traditional PID neural network, the configuration of IPIDNN is flexible and easy to expand, as well as a better robust performance. The simulation results show the validity of this algorithm and initial weights choosing method by the static var compensator (SVC) supplementary control in four-machine two-area system. It also has a good performance in the circumstance of partial state feedback and state delay.

Original languageEnglish (US)
Pages (from-to)95-102
Number of pages8
JournalDianji yu Kongzhi Xuebao/Electric Machines and Control
Volume15
Issue number5
StatePublished - May 2011

Fingerprint

Dynamic programming
Neural networks
Controllers
State feedback
Cost functions
Static Var compensators

Keywords

  • Approximate dynamic programming
  • Direct heuristic dynamic programming
  • Improved proportion integration differentiation neural network
  • Static var compensator supplementary control

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

An improved approximate dynamic programming and its application in SVC control. / Sun, Jian; Liu, Feng; Si, Jennie; Guo, Wen Tao; Mei, Sheng Wei.

In: Dianji yu Kongzhi Xuebao/Electric Machines and Control, Vol. 15, No. 5, 05.2011, p. 95-102.

Research output: Contribution to journalArticle

Sun, Jian ; Liu, Feng ; Si, Jennie ; Guo, Wen Tao ; Mei, Sheng Wei. / An improved approximate dynamic programming and its application in SVC control. In: Dianji yu Kongzhi Xuebao/Electric Machines and Control. 2011 ; Vol. 15, No. 5. pp. 95-102.
@article{1f35287b0f304861b0b9623a575181c2,
title = "An improved approximate dynamic programming and its application in SVC control",
abstract = "The main idea of approximate dynamic programming (ADP) is approximately computing cost function to avoid the curse of dimension. However, it needs many times learning to converge due to the randomly choosing initial weights. So it is greatly limited in the application. This paper presents a direct heuristic dynamic programming (DHDP) based on an improved proportion integration differentiation PID neural network (IPIDNN). This method constructs an equivalent between the initial action network and PID controller. Therefore, well-designed PID controller can guide the initial weights choosing, so that the convergence of this algorithm will be remarkably improved. Moreover, compared with the traditional PID neural network, the configuration of IPIDNN is flexible and easy to expand, as well as a better robust performance. The simulation results show the validity of this algorithm and initial weights choosing method by the static var compensator (SVC) supplementary control in four-machine two-area system. It also has a good performance in the circumstance of partial state feedback and state delay.",
keywords = "Approximate dynamic programming, Direct heuristic dynamic programming, Improved proportion integration differentiation neural network, Static var compensator supplementary control",
author = "Jian Sun and Feng Liu and Jennie Si and Guo, {Wen Tao} and Mei, {Sheng Wei}",
year = "2011",
month = "5",
language = "English (US)",
volume = "15",
pages = "95--102",
journal = "Dianji yu Kongzhi Xuebao/Electric Machines and Control",
issn = "1007-449X",
publisher = "Harbin University of Science and Technology, Editorial department of Electric Machines and Control",
number = "5",

}

TY - JOUR

T1 - An improved approximate dynamic programming and its application in SVC control

AU - Sun, Jian

AU - Liu, Feng

AU - Si, Jennie

AU - Guo, Wen Tao

AU - Mei, Sheng Wei

PY - 2011/5

Y1 - 2011/5

N2 - The main idea of approximate dynamic programming (ADP) is approximately computing cost function to avoid the curse of dimension. However, it needs many times learning to converge due to the randomly choosing initial weights. So it is greatly limited in the application. This paper presents a direct heuristic dynamic programming (DHDP) based on an improved proportion integration differentiation PID neural network (IPIDNN). This method constructs an equivalent between the initial action network and PID controller. Therefore, well-designed PID controller can guide the initial weights choosing, so that the convergence of this algorithm will be remarkably improved. Moreover, compared with the traditional PID neural network, the configuration of IPIDNN is flexible and easy to expand, as well as a better robust performance. The simulation results show the validity of this algorithm and initial weights choosing method by the static var compensator (SVC) supplementary control in four-machine two-area system. It also has a good performance in the circumstance of partial state feedback and state delay.

AB - The main idea of approximate dynamic programming (ADP) is approximately computing cost function to avoid the curse of dimension. However, it needs many times learning to converge due to the randomly choosing initial weights. So it is greatly limited in the application. This paper presents a direct heuristic dynamic programming (DHDP) based on an improved proportion integration differentiation PID neural network (IPIDNN). This method constructs an equivalent between the initial action network and PID controller. Therefore, well-designed PID controller can guide the initial weights choosing, so that the convergence of this algorithm will be remarkably improved. Moreover, compared with the traditional PID neural network, the configuration of IPIDNN is flexible and easy to expand, as well as a better robust performance. The simulation results show the validity of this algorithm and initial weights choosing method by the static var compensator (SVC) supplementary control in four-machine two-area system. It also has a good performance in the circumstance of partial state feedback and state delay.

KW - Approximate dynamic programming

KW - Direct heuristic dynamic programming

KW - Improved proportion integration differentiation neural network

KW - Static var compensator supplementary control

UR - http://www.scopus.com/inward/record.url?scp=79959778829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959778829&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:79959778829

VL - 15

SP - 95

EP - 102

JO - Dianji yu Kongzhi Xuebao/Electric Machines and Control

JF - Dianji yu Kongzhi Xuebao/Electric Machines and Control

SN - 1007-449X

IS - 5

ER -