Optimizing Service Stipulation Uncertainty with Deep Reinforcement Learning for Internet Vehicle Systems

Fog computing brings computational services near the network edge to meet latency constraints of cyber-physical System (CPS) applications. Edge devices enable limited capacity and energy availability that hamper end user performance. We designed a novel performance measurement index gauge device’s resource capacity. This examination addresses offloading mechanism issues, where (EU) offloads part its workload nearby server (ES). Sometimes, ES further another or cloud achieve reliable because resources (such as storage computation). The manuscript aims reduce service rate by selecting potential device accomplish low average completion time deadline sub-divided services. In this regard, an adaptive online status predictive model design is significant for prognosticating asset requirement arrived make float decisions. Consequently, development reinforcement learning-based flexible x-scheduling (RFXS) approach resolves x = service/resource producing high network. Our theoretical bound complexity derived formulating system efficiency. A quadratic restraint employed formulate optimization issue according set measurements, well behavioural association adulation factor. managed 0.89% rate, with 39 delay over complex scenarios (using three servers 50% arrival rate). simulation outcomes confirm proposed scheme attained uncertainty, suitable simulating heterogeneous CPS frameworks.