Energy-Latency Tradeoff for Dynamic Computation Offloading in Vehicular Fog Computing

Vehicular Fog Computing (VFC) provides solutions to relieves overload cloudlet nodes, reduces service latency during peak times, and saves energy for battery-powered cloudlet nodes by offloading user tasks to a vehicle (vehicular node) by exploiting the under-utilized computation resources of nearby vehicular node. However, the wide deployment of VFC still confronts several critical challenges: lack of energy-latency tradeoff and efficient resource allocation mechanisms. In this paper, the authors address the challenges and provide an Energy-efficient dynamic Computation Offloading and resources allocation Scheme (ECOS) to minimize energy consumption and service latency. The authors first formulate the ECOS problem as a joint energy and latency cost minimization problem while satisfying vehicular node mobility and end-to-end latency deadline constraints. The authors then propose an ECOS scheme with three phases. In the first phase, the authors propose an overload cloudlet node detection policy based on resource utilization. In the second phase, the authors propose a computational offloading selection policy to select a task from an overloaded cloudlet node for offloading, which minimizes offloading cost and the risk of overload. Next, the authors propose a heuristic approach to solve the resource allocation problem between the vehicular node and selected user tasks for energy-latency tradeoff. Extensive simulations have been conducted under realistic highway and synthetic scenarios to examine the ECOS scheme's performance. In comparison, the authors' proposed scheme outperforms the existing schemes in terms of energy-saving, service latency, and joint energy-latency cost.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01765402
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Feb 2 2021 10:19AM