About the project
Powering the Net Zero future demands smarter, safer AI. This project tackles one of energy’s greatest challenges: ensuring resilient, cyber-secure power systems run by decentralised AI agents. By developing novel methods to detect and prevent unsafe behaviours, you’ll help unlock reliable, renewable-powered grids and shape the future of sustainable, intelligent energy systems.
The global transition towards Net Zero demands power systems capable of integrating vast, distributed renewable energy sources while maintaining security, reliability, and cost-effectiveness. AI offers potential to optimise these complex systems. Yet, as control shifts from centralised operators to decentralised AI agents, each managed by different stakeholders, instability risks and vulnerability to cyber threats grows significantly.
This project addresses a critical question: how can we guarantee safety in power systems with decentralised AI agents operating across market and physical layers, ensuring resilience against malicious interference? While individually “safe” AI agents may comply with safeguards, their collective behaviour can still lead to unsafe system-wide outcomes, as highlighted in control theory and multi-agent systems research. This problem is largely unaddressed in current literature, where most safety frameworks assume centralised oversight.
This project will develop and validate an integrated workflow for detecting and mitigating unsafe emergent behaviours within crowds of AI agents in power system operations. The research draws on methods from optimisation, control theory, game theory, and cybersecurity to ensure resilience not only under normal operating conditions but also in the presence of adversarial threats. These approaches will be tested in scenarios including electricity markets, distributed resource coordination, and renewable energy integration. By systematically benchmarking these methods, the project will deliver a novel scalable approach guarantying safe and resilient decentralised AI for power systems. This project will make AI-driven power systems safer by reducing grid balancing costs, enabling renewable adoption, and preventing large-scale blackouts, empowering the Net Zero energy transition.
The project is part of the UKRI AI Centre for Doctoral Training in AI for Sustainability (SustAI), a 4-year integrated programme (iPhD). You'll be part of a dynamic and diverse cohort, benefiting from expert mentorship and interdisciplinary collaboration. The programme includes comprehensive training in sustainability, AI and machine learning, and digital design, preparing you for a career at the forefront of research in this area. You'll have access to state-of-the-art facilities and resources, fostering an environment of innovation and excellence.
The School of Electronics and Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
