Tamper-proof strategy of dynamic hash chain for smart grid cloud storage based on reinforcement learning key update mechanism

Cloud storage systems in smart grids face dual challenges: ensuring data integrity while maintaining real-time responsiveness when managing large-scale power data. Conventional static key management strategies, due to their fixed update patterns, are prone to predictability. Meanwhile, standalone data integrity verification mechanisms often introduce substantial computational and communication overhead, rendering them unsuitable for real-time grid monitoring requirements. To address these issues, this study proposes a collaborative anti-tampering strategy that integrates reinforcement learning with dynamic hash chains. The approach employs a deep Q-network (DQN) to dynamically optimize the update timing and strategy of Advanced Encryption Standard (AES) keys, thereby enhancing the adaptability of key management. Simultaneously, by constructing a dynamic hash chain, it achieves chain-style cross-verification between data blocks to ensure traceability and rapid localization of tampering incidents. Simulation results demonstrate that, compared with conventional key rotation and Secure Hash Algorithm (SHA)-based methods, the proposed scheme improves the tamper detection rate by 67.2%, reduces the average system latency by 38.5 ms, and significantly decreases computational and communication overhead by 52% and 88%, respectively. This study provides an effective technical pathway for addressing dynamic security challenges in smart grid cloud storage environments.