Dr Fanlin Meng

Dr Fanlin Meng is a Senior Lecturer in Operations and Analytics at the University of Exeter Business School where he is also the Research Lead of Operations and Analytics subdepartment. Prior to joining Exeter, he was a Lecturer in Data Science (Alliance Manchester Business School) at the University of Manchester where he received his PhD in Computer Science (machine learning and optimisation) from the same university in 2015. His first permanent academic position was in Data Science and Operational Research at University of Essex (mathematical sciences). Before that, he worked as a postdoc researcher in engineering, computer science and mathematics departments in UK universities on projects in autonomous driving, energy systems, building energy management and sustainable engineering. 

Dr Meng's primary research interests include Electricity Market, Carbon Market, Smart Energy and Mobility, Machine Learning, Game Theory and Optimisation. With a strong interdisciplinary background, his research has appeared in leading journals in Operational Research, Energy, AI and Intelligent Systems.

He is a Fellow of British Computer Society (FBCS), member of EPSRC Peer Review College, and Senior Member of IEEE. 

-----------------------------------------------------------

My current research focuses on decision-making in complex and interconnected systems, with particular applications in energy and transport. More broadly, I am interested in settings where multiple organisations, markets and individuals interact, where decisions are made under uncertainty, and where the actions of one actor can affect the choices and outcomes of others. My research asks how data, analytical models and intelligent decision-support methods can help us understand these interactions and make better operational, strategic and policy decisions.

My research sits at the intersection of Operational Research, Management Science, Artificial Intelligence and Data Science. I develop and apply mathematical optimisation, game theory, machine learning and simulation, with particular interests in bilevel and multilevel optimisation, Stackelberg and Bayesian games, stochastic and robust optimisation, reinforcement learning, federated and distributed learning, transfer learning and interpretable machine learning.

One strand of my research focuses on the transition towards low-carbon and increasingly decentralised energy systems. This includes work on electricity and carbon markets, demand flexibility, energy pricing, renewable-energy integration and smart-meter analytics. I am particularly interested in the interactions between consumers, energy retailers, generators, aggregators and market operators, and in how market mechanisms and decision-support tools can balance individual incentives with wider system objectives such as affordability, reliability and decarbonisation.

Another strand of my work focuses on intelligent transport and mobility systems. My research in this area covers multimodal transport, public-transport disruption management, mixed-autonomy traffic and the growing links between transport and energy systems. I use behavioural modelling, optimisation and AI to understand how individual decisions affect wider network performance, how disruptions can spread through interconnected systems, and how operators can design more effective interventions.

Research themes

Energy markets and systems

Electricity and carbon markets; carbon-emissions trading; interactions between energy and carbon markets; market design and operation; strategic bidding and pricing; demand response and flexibility; renewable energy integration; smart meter and energy analytics; energy demand and price forecasting; non-intrusive load monitoring; digital twins; and AI-enabled energy management.

Intelligent transport and mobility

Multimodal transportation; public-transport disruption and resilience; congestion propagation; traveller behaviour; mixed-autonomy traffic; transport-energy interactions; and AI-enabled transport planning and decision support.

AI, optimisation and decision-making

Mathematical, bilevel and multilevel optimisation; game theory; stochastic and robust optimisation; machine learning; reinforcement learning and multi-agent systems; interpretable and privacy-preserving AI; and methods that integrate prediction with optimisation and decision-making.