SENFC1-017
Using machine learning to represent power system dynamics
Lead Institution: University of Strathclyde
Project Summary
The ever increasing integration of variable output renewable energy sources (mainly wind and solar) as well as various other power electronic interfaced devices (e.g. electric vehicles, HVDC interconnectors, potentially battery storage, heat pumps, etc.) to achieve decarbonisation targets, significantly increases the uncertainty and complexity in the dynamic behaviour of electrical power systems. Machine learning has shown great potential in dealing with complex nonlinear systems in various domains. This project envisions bringing together the artificial intelligence and power engineering research communities to work on the very computationally demanding and complex problem of representing the power system dynamic behaviour.
Dr Panagiotis Papadopoulos
Principle Investigator
![](/media/wwwnclacuk/supergenenergynetwork/images/profiles/Panos.png)
Dr Dimitrios Tzelepis
Co-Invesitgator
![Uni of Strathclyde logo Uni of Strathclyde logo](/media/wwwnclacuk/supergenenergynetwork/images/unilogos/strathclyde.png)
Prof John Moriarty
Project Partner
![Alan Turing Institute Alan Turing Institute](/media/wwwnclacuk/supergenenergynetwork/images/companylogos/Alan Turing Institute.png)
Graham Stein
Project Partner
![National Grid ESO National Grid ESO](/media/wwwnclacuk/supergenenergynetwork/images/companylogos/nationalgrid eso.png)
Dr Sebastian Vollmer
Project Partner
![Alan Turing Institute Alan Turing Institute](/media/wwwnclacuk/supergenenergynetwork/images/companylogos/Alan Turing Institute.png)