We are delighted to announce that the SGI's Alex Kell has been awarded his PhD and will now take on the role of Research Associate.
We spoke to Alex who told us:
'I was recently awarded a PhD in computer science from Newcastle University, which promoted me to Research Associate at the Sustainable Gas Institute. The title of my PhD thesis was “Modelling the transition to a low-carbon energy supply” and covered a range of topics. Firstly, I designed and created a novel agent-based model of the UK’s national electricity market, ElecSim . This involved modelling the behaviour of individual power generation companies as they invested in power plants. The model can explore different future scenarios and enables us to analyse how we can transition to a low-carbon energy supply by 2050.
After the model was built, I used artificial intelligence and machine learning to optimise ElecSim. For instance, I used reinforcement learning to model strategic bidding in the day-ahead market , used a genetic algorithm to find suitable parameters to make ElecSim more realistic  and found an optimal carbon tax to reduce both carbon emissions and electricity price .
As part of my role at the Sustainable Gas Institute, I work on the agent-based whole systems energy model, MUSE. Here, we look at how countries around the world can transition to net-zero whilst maintaining sustainable economic growth. For instance, we work with the governments in Kenya and Laos as part of the Climate Compatible Growth project.'
 A. Kell, M. Forshaw, and A. S. McGough, “ElecSim?: Monte-Carlo Open-Source Agent-Based Model to Inform Policy for Long-Term Electricity Planning,” Tenth ACM Int. Conf. Futur. Energy Syst. (ACM e-Energy `19), pp. 556–565, 2019.
 A. J. M. Kell, M. Forshaw, and A. S. McGough, “Exploring market power using deep
reinforcement learning for intelligent bidding strategies,” IEEE Int. Conf. Big Data (Big Data), 2020.
 A. J. M. Kell, M. Forshaw, and A. S. McGough, “Long-Term Electricity Market Agent Based Model Validation using Genetic Algorithm based Optimization,” Elev. ACM Int. Conf. Futur. Energy Syst., 2020.
 A. J. M. Kell, A. S. McGough, and M. Forshaw, “Optimizing carbon tax for decentralized electricity markets using an agent-based model,” Elev. ACM Int. Conf. Future. Energy Syst., pp. 454–460, 2020.
Article text (excluding photos or graphics) © Imperial College London.
Photos and graphics subject to third party copyright used with permission or © Imperial College London.
Department of Earth Science & Engineering