Introduction
The transition towards net-zero energy systems is fundamentally changing the design and operation of electricity and multi-energy markets
High penetrations of renewable generation, distributed energy resources, energy storage, hydrogen, flexible demand, and sector coupling introduce unprecedented uncertainty, making traditional deterministic market design increasingly inadequate. At the same time, Artificial Intelligence (AI) is becoming an important tool for supporting market operation and planning, yet many AI models remain black boxes, limiting trust and adoption in high-stakes regulatory and policy settings.
Existing research on energy market design has largely focused on developing new market mechanisms or using AI to improve forecasting and operational decision-making. However, comparatively little attention has been paid to how AI and stochastic optimisation can jointly provide transparent and explainable decision-making for designing future energy markets under uncertainty. Future regulators and system operators will require not only optimal market designs, but also a clear understanding of why particular market structures perform better, which uncertainties drive the results, and how robust market designs remain under different future scenarios.
Research Aim
This PhD project aims to develop a new generation of explainable stochastic decision intelligence methods for future energy market design.
The research will integrate stochastic optimisation, explainable artificial intelligence, machine learning, and uncertainty quantification to develop transparent, trustworthy, and data-driven decision-support tools for electricity and integrated energy markets.
Research Questions
Key research questions include:
How should future electricity and multi-energy markets be designed under deep uncertainty?
How can explainable AI improve transparency and trust in AI-assisted market design?
How can stochastic optimisation and AI jointly quantify the value of flexibility, resilience, and low-carbon technologies?
How can explainable decision intelligence support regulators, system operators and policymakers in evaluating future market designs?
The project aims to develop novel optimisation algorithms, interpretable AI models, and computational market-design frameworks, with applications including flexibility markets, balancing markets, capacity markets, hydrogen markets, and integrated electricity–hydrogen systems. The expected outputs include new theory, open-source software, high-quality journal publications, and decision-support tools for future sustainable energy markets.
References:
Birge, J. R., & Louveaux, F. (2011). Introduction to Stochastic Programming.
Conejo, A. J., Morales, J. M., & Baringo, L. (2010). Decision Making Under Uncertainty in Electricity Markets.
Molnar, C. (2022). Interpretable Machine Learning.
Gilpin, L. H., et al. (2018). “Explaining Explanations: An Overview of Interpretability of Machine Learning.”
Morales, J. M., Conejo, A. J., Madsen, H., Pinson, P., & Zugno, M. (2014). Integrating Renewables in Electricity Markets.