IMPLEMENTATION OF MULTIAGENT REINFORCEMENT LEARNING MECHANISM FOR OPTIMAL ISLANDING OPERATION OF DISTRIBUTION NETWORK

Arshad Saleem, Morten Lind

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

Abstract

The Electric Power system of Denmark exhibits some unique characteristics. An increasing part of the electricity is produced by local generators called distributed generators DGs. Most of these DGs are connected to network through the distribution system. This situation has created an incentive among electric power utilities to utilize modern information and communication technologies (ICT) in order to improve the automation of the distribution system. In this paper we present our work for the implementation of a dynamic multi-agent based distributed reinforcement learning mechanism for the islanding operation of the distribution system. Purpose of this system is to dynamically divide the distribution network in different sections (islands), in a fault scenario when they are separated from main utility system, and make them survive on local DGs.
Original languageEnglish
Title of host publicationSmart Energy Strategies : Meeting the climate change challenge
Number of pages149
Volume1
Place of PublicationZurich, Switzerland
PublisherEnergu Science Center, Swiss Federal Institute of Technology
Publication date2008
Edition1
Pages101-102
ISBN (Print)978-3-7281-3218-5
DOIs
Publication statusPublished - 2008
EventSmart Energy Strategies : Meeting the climate change challenge - Zurich, Switzerland
Duration: 1 Jan 2008 → …

Conference

ConferenceSmart Energy Strategies : Meeting the climate change challenge
CityZurich, Switzerland
Period01/01/2008 → …

Fingerprint Dive into the research topics of 'IMPLEMENTATION OF MULTIAGENT REINFORCEMENT LEARNING MECHANISM FOR OPTIMAL ISLANDING OPERATION OF DISTRIBUTION NETWORK'. Together they form a unique fingerprint.

Cite this