Research
AI-driven decentralized energy systems, markets, and optimization.
My work integrates energy economics, multi-agent coordination, and grid-aware decision systems—bridging future electricity markets with technical grid realities.
AI-driven local energy markets
Hierarchical clearing, fairness & welfare matching, hybrid auctions, dynamic pricing, and distributed optimization for consumer-centric market design.
Multi-agent systems for coordination
Autonomous agents for bidding, negotiation, learning market patterns, forecasting, and real-time coordination under technical and economic constraints.
Flexibility markets & grid-constrained optimization
Incentive design, congestion/voltage-aware activation, and verification of flexibility provision for DSOs, TSOs, and aggregators.
DER optimization (MPC/MILP)
Control and scheduling for batteries, PV, heat pumps, and industrial loads—cost-effective operation with grid-friendly behavior.
BESS multi-market participation
Revenue stacking across day-ahead, intraday, balancing (FCR/aFRR/mFRR), flexibility, and local markets with degradation-aware strategies.
Virtual power plants & aggregator strategies
Architectures and algorithms that aggregate flexibility across assets and markets using AI-enhanced decision logic.
Integrated multi-market simulation (EUnix)
A multi-layer ecosystem connecting local markets → grid constraints → optimization engines → VPP strategies → wholesale/balancing participation.
Forecasting & reinforcement learning
LSTM/GRU forecasting, RL (Q-learning, DQN, PPO), and hybrid ML-optimization to support predictive market decisions under uncertainty.