A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning

The large scale, time varying, and diversification of physically coupled networked infrastructures such as power grid and transportation system lead to the complexity of their controller design, implementation, and expansion. For tackling these challenges, we suggest an online distributed reinforcem...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Sun, Jie Li
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/5950678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849402999184556032
author Jian Sun
Jie Li
author_facet Jian Sun
Jie Li
author_sort Jian Sun
collection DOAJ
description The large scale, time varying, and diversification of physically coupled networked infrastructures such as power grid and transportation system lead to the complexity of their controller design, implementation, and expansion. For tackling these challenges, we suggest an online distributed reinforcement learning control algorithm with the one-layer neural network for each subsystem or called agents to adapt the variation of the networked infrastructures. Each controller includes a critic network and action network for approximating strategy utility function and desired control law, respectively. For avoiding a large number of trials and improving the stability, the training of action network introduces supervised learning mechanisms into reduction of long-term cost. The stability of the control system with learning algorithm is analyzed; the upper bound of the tracking error and neural network weights are also estimated. The effectiveness of our proposed controller is illustrated in the simulation; the results indicate the stability under communication delay and disturbances as well.
format Article
id doaj-art-92ef69eebcaf4544b7ebc7a10235a5ed
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-92ef69eebcaf4544b7ebc7a10235a5ed2025-08-20T03:37:23ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/59506785950678A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement LearningJian Sun0Jie Li1School of Electronic and Information Engineering, Southwest University, Chongqing, ChinaState Grid Chongqing Electric Power Co. Electric Power Research Institute, Chongqing, ChinaThe large scale, time varying, and diversification of physically coupled networked infrastructures such as power grid and transportation system lead to the complexity of their controller design, implementation, and expansion. For tackling these challenges, we suggest an online distributed reinforcement learning control algorithm with the one-layer neural network for each subsystem or called agents to adapt the variation of the networked infrastructures. Each controller includes a critic network and action network for approximating strategy utility function and desired control law, respectively. For avoiding a large number of trials and improving the stability, the training of action network introduces supervised learning mechanisms into reduction of long-term cost. The stability of the control system with learning algorithm is analyzed; the upper bound of the tracking error and neural network weights are also estimated. The effectiveness of our proposed controller is illustrated in the simulation; the results indicate the stability under communication delay and disturbances as well.http://dx.doi.org/10.1155/2018/5950678
spellingShingle Jian Sun
Jie Li
A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
Complexity
title A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
title_full A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
title_fullStr A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
title_full_unstemmed A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
title_short A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
title_sort stable distributed neural controller for physically coupled networked discrete time system via online reinforcement learning
url http://dx.doi.org/10.1155/2018/5950678
work_keys_str_mv AT jiansun astabledistributedneuralcontrollerforphysicallycouplednetworkeddiscretetimesystemviaonlinereinforcementlearning
AT jieli astabledistributedneuralcontrollerforphysicallycouplednetworkeddiscretetimesystemviaonlinereinforcementlearning
AT jiansun stabledistributedneuralcontrollerforphysicallycouplednetworkeddiscretetimesystemviaonlinereinforcementlearning
AT jieli stabledistributedneuralcontrollerforphysicallycouplednetworkeddiscretetimesystemviaonlinereinforcementlearning