Dependency-Aware and Energy Efficient Task Offloading in Vehicular Edge Computing Systems

The development of Artificial Intelligence and Internet of Things has not only paved the way to realize real-time intelligent tasks in vehicular edge computing systems, but also caused a series of problems such as system overload. Task offloading based on edge-terminal cooperation is one of the efficient paradigms to solve these problems. However, the dependency between the subtasks in vehicular intelligent tasks, as well as the resource shortage of terminal vehicles and edge servers, all pose serious challenges to efficient task offloading. In this paper, we investigate the optimization problem of task offloading in vehicular edge computing systems with the consideration of the above challenges, aiming to minimize the system consumption including processing delay and energy consumption, and prove it as a mixed integer nonlinear and NP-hard problem. To address this problem, we construct directed acyclic graphs to represent the complex dependency between the subtasks and utilize pipeline diagrams to calculate the task processing delay. Then, an efficient Dependency-aware and Energy efficient task offloading schedule DESR is proposed, which utilizes a cyclic iterative method to decouple the problem into sub-problems and introduces multi-layer activity on edge networks and the interior point method to jointly optimize offloading Selection and Resource allocation. Extensive simulations are conducted to evaluate the proposed DESR, and the results illustrate its superior performance.