Dynamic robust analysis of IoV link delay in cellular Telematics and smart edge networking base on deep reinforcement learning

Abstract

Applications for the Internet of Vehicles (IoV) are progressing from more fundamental ones like those for traffic efficiency, road safety, and information services to more sophisticated ones like autonomous driving and intelligent mobility that have a variety of connectivity requirements. Therefore, IoV communication systems must overcome various obstacles in order to enable a variety of IoV applications. Attacks on TSP servers are the major target of telematics attack threat events. This article analyses data security monitoring from the vehicle end to the TSP platform, as well as gathering and analysing the status and intelligence of linked vehicles, in order to develop a Telematics TSP server attack monitoring system. Experiments show that the error detection rate of the benchmark algorithms decreases significantly as the error rate of vehicle speed data increases, with the exponential smoothing algorithm showing the largest decrease in the error detection rate. However, the proposed combined model is very close to the error detection rate of the benchmark algorithm at the later stages when the error rate is high, with an error detection rate of more than 80%.It provides great assistance for anomaly detection and data recovery, especially in researching key technologies for remote information processing data security and reliability, greatly improving their performance.