This paper introduces a Probabilistic Dynamic Distributed Coordination Protocol (P-DDCP) to address electric vehicle charging coordination under demand uncertainty. It integrates probabilistic forecasting, scenario generation, distributed coordination, and distributionally robust optimization to maintain grid safety and privacy while being scalable.
Key findings
Develops a PICNN-based hierarchical forecasting framework for charging demand prediction.
Formulates EV charging as a two-stage stochastic program solved via distributed ADMM.
Incorporate distribution network constraints as probabilistic guarantees for grid safety.
Augments the framework with distributionally robust optimization to handle demand distribution uncertainty.
Provides theoretical guarantees on convergence and probabilistic bounds on constraint violation.
Limitations & open questions
The paper is a research proposal and does not include experimental results or validation of the proposed protocol.