Artificial Intelligence based Self-Healing Protection in Smart Grid
This proposal presents self-healing protection system in smart grid. The system can be applied on a typical distribution system with loads, buses, and power sources or on a combination of several micro grids. The distribution system Automation for a smart grid can be analyzed and implemented using Multi Agent System (MAS) for three significant issues of power system such as
- Fault identification, isolation and restoration (FIIR) using Machine Learning and Multiagent system for a smart grid application
- Integration of distributed generation for FIIR using Multiagent system for a smart grid application
- Reconfiguration of distribution network using Multiagent system for a smart grid application
In each case the distribution network to be analysed is developed using MATLAB/Simulink and the agents can be developed in Foundation of Intelligent Physical Agents (FIPA) compliant Java Agent Development Environment (JADE). A two-way communication, which is considered as the main requirement of smart grid technology to provide fully automated process of distribution system. This is achieved by interfacing MATLAB/Simulink and (JADE) using MACSimJX/TCP/IP. This research has collaborations with Durham University, UK, University of Trento Italy and another collaboration for a project with West Virginia University, USA.
Research Progress
The first phase of the research is based on the detection of fault in a smart grid environment using machine learning algorithms. Implementation of an Autoencoder- based Fault detection in smart grids has been successful, with a detection rate of 98%. The algorithm has also been validated through a comparative analysis to prove the superiority of the proposed method.
Collaborations with Universities / Industry Partnerships
Dr. Hongjian Sun
Professor
Department of Engineering Durham University, UK
Dr. Sarika Khushalani Solanki
Associate Professor
Lane Department of Computer Science and Electrical Engineering
West Virginia University
Title: Development of a Multi Agent based system for self-healing protection
Dr. Fabrizio Granelli
Full Professor, University of Trento Dept. of Information Engineering and Computer Science
Via Sommarive 9 38123, T, Italy