Adaptive Learning-Based Cloud-Edge Collaborative Secure Resource Management for Blockchain-Empowered Demand Response

Abstract

The rapid development of renewable energy and controllable loads such as consumer electronics requires more user side resources to participate in demand response. Blockchain-empowered demand response can effectively reduce the trust cost among various market entities. However, considering the efficient transaction processing and low-delay interaction requirements of the system, how to jointly optimize blockchain consensus throughput and consensus delay through secure resource management under the decentralization constraint is a key issue. The paper proposes an adaptive learning-based cloud-edge collaborative secure resource management method for blockchain-empowered demand response. Firstly, a blockchain-empowered secure demand response framework is constructed to achieve information exchange among multiple entities. Secondly, under a decentralization constraint in long term, the joint optimization problem of consensus throughput and consensus delay is formulated. The one-slot joint optimization problem is decoupled from long-term decentralization constraint through Lyapunov optimization theory. Finally, a block and channel resource collaboration management optimization algorithm based on security bound violation penalty-driven adaptive DQN is proposed. Based on the security bound violation penalty, the probabilities of exploration and exploitation in the learning process are adaptively adjusted to avoid falling into local optimum. Simulations show that the proposed algorithm performs well in consensus throughput, consensus delay, and decentralization degree.