Blockchain-based cyber-physical systems security autonomous routing scheme

Abstract

Improving the quality of service (QoS) and quality of experience (QoE) for users of cyber-physical systems (CPS) is the key to the widespread promotion and deployment of this technology. Network latency is an important factor affecting users' network experience. Due to the limited processing capacity of a single device node of CPS, the communication relationship between equipment is extremely complicated, and multi-hop device nodes may be passed through in the middle, so designing an efficient routing scheme for CPS is a serious challenge. CPS routing also faces a security crisis. System nodes may send viruses or erroneous results to user equipment, and user equipment may also refuse to pay for routing services to system nodes. In order to solve the above problems, this paper proposes a secure routing scheme based on blockchain. Blockchain is used to ensure secure transactions between system nodes and user equipment. At the same time, deep reinforcement learning (DRL) technology is used, and two deep neural networks are used to train intelligent agent to achieve low-latency adaptive traffic scheduling. Experimental results show that the proposed autonomous routing technology can reduce the system communication latency by about 31.7%-45.4%.