KTH Royal Institute of Technology is offering a fully funded PhD position in the area of smart and resilient microgrids, supervised by Associate Professor Qianwen Xu. The research focuses on developing advanced methods for microgrids using machine learning (including deep reinforcement learning), power electronics, and control theory to ensure stability, security, and resilience under various disturbances. The project is part of the Wallenberg AI, Autonomous Systems and Software Program (WASP), Sweden’s largest research initiative in AI and autonomous systems.

The PhD project aims to support the energy transition and a carbon-neutral society by enhancing microgrid technology for renewable energy integration, electrified transport, and local resilience. Candidates can pursue research in either novel algorithm design (advanced control, optimization, deep reinforcement learning) or hardware-oriented development (converter control, experimental validation). The research will also extend to large-scale power converter-dominated grids, addressing the challenges of modern, cyber-physical energy systems.

Applicants should have a strong background in power systems, power electronics, optimization, or deep reinforcement learning, and must meet the English proficiency requirement (English B/6). The selection process values goal orientation, perseverance, independence, collaboration, and analytical skills. The position is fully funded, with a monthly salary and benefits according to KTH’s doctoral student salary agreement. The employment is full-time for up to four years, with annual or biannual renewal, and tuition is covered.

To apply, candidates must submit a CV, an application letter with a research statement and future research plan, and representative publications or technical reports. Applications are accepted through KTH’s recruitment system until January 9, 2026. For more information, visit the official job posting or contact Associate Professor Qianwen Xu at [email protected].

Keywords: smart microgrids, resilient microgrids, machine learning, deep reinforcement learning, power electronics, power systems, advanced control, energy transition, renewable energy integration, cyber-physical systems.