Imperial College London Featured PhD Programmes
Sheffield Hallam University Featured PhD Programmes
University of Reading Featured PhD Programmes

Machine Learning Based Multi-Agent Control of Distribution Networks for Optimal Utilization of Ancillary Services


Project Description

SCEBE-20-021-MEFSF

Traditionally, power system is dominated by large generators that inject power into high voltage transmission, is transported to passive distribution networks and delivered to consumers at various voltage levels. However, modern power systems are based on high penetration of converter connected distributed generation such as solar PV, battery storage, wind, etc. and is difficult to operate safely and reliably. In modern power systems, many different generation sources operating in different patterns will be connected at various level in distribution network. The challenge is to integrate these new distributed generation sources efficiently and reliably to optimise the operation of future power system. Additionally, with increase in converter connected generation in the distribution network, requirements for ancillary services will increase. Traditionally, ancillary services are procured by System Operator and not Distribution Network Operators (DNO). However, with the anticipated transition of DNO to Distribution System Operator (DSO), it will be the responsibility of DSO to balance the system.

Aims
This project is aimed at investigating the efficient and economic operation of modern distribution system with view of provision of ancillary services from distributed generation sources. This will involve thorough understanding of the distribution network, distributed generation and ancillary services. The main focus will be on active power management for frequency response and reactive power management for voltage stability and congestion management. The project will investigate the development of a multiagent control system capable of performing the above-mentioned tasks. Advance machine learning and evolutionary algorithms will be incorporated to optimise the operation of proposed control system.

Funding Notes

Essential:
The successful candidate should be able to demonstrate a solid background in at least one of the aspects: electrical power engineering, control engineering, machine learning and evolutionary algorithms or relevant.

The candidate should have strong mathematical background, good modelling and simulation skills using MATLAB/Simulink.

The successful candidate should have strong self-motivation and dedicated passion in power system and/or control system research.

The willingness of team-working in a multi-cultural team and the ability to deliver research outcome to meet the deadlines on one’s own.

Desirable:
Previous experience of publishing in journals or international conferences.
Programming in MATLAB, C/C++

Related Subjects

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2020
All rights reserved.