Privacy-Preserving Robust Optimization of User-Side Integrated Energy Management Based on Information Masking

With the increasing deployment of cloud-based energy management services in the energy internet, the optimal dispatch of user-side integrated energy systems (IES) has been significantly facilitated by cloud computing. The potential privacy leakage during the interaction process among local and cloud side hazards the further development of cloud computing in power systems. This paper focuses on the robust optimization of userside optimal dispatch considering uncertainties in renewable energy resources(RES) and load prediction, and proposes a privacypreserving robust optimization framework based on information masking (IM). Case studies demonstrate that the robust optimization model balances economics with resilience, flattening power curves to reserve capacity for uncertainties. Moreover, the IM scheme effectively randomizes matrix structures and obscures private information in optimal strategy, preventing privacy leakage and validating the reversibility and reliability of the masking process.