Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Autonomous Task Offloading of Vehicular Edge Computing with Parallel Computation Queues

Sungho Cho, Sung Il Choi, Seung Hyun Oh, Ian P. Roberts, Sang Hyun Lee

TL;DR

The paper tackles delay minimization in vehicular edge computing with multi-CPU edge servers and finite queues by formulating a combinatorial offloading problem and solving it with a distributed message-passing algorithm on a factor graph. It provides a rigorous convergence and optimality analysis, demonstrates exact alignment with the global optimum in simulations, and validates practical feasibility on a real-map digital-twin platform. The approach, which preserves discrete queue dynamics and balances load vs. congestion, achieves significant delay improvements over existing methods and scales to large VEC networks. A noted limitation is tail latency optimization, pointing to future work on priority-aware scheduling to improve worst-case performance.

Abstract

This work considers a parallel task execution strategy in vehicular edge computing (VEC) networks, where edge servers are deployed along the roadside to process offloaded computational tasks of vehicular users. To minimize the overall waiting delay among vehicular users, a novel task offloading solution is implemented based on the network cooperation balancing resource under-utilization and load congestion. Dual evaluation through theoretical and numerical ways shows that the developed solution achieves a globally optimal delay reduction performance compared to existing methods, which is also validated by the feasibility test over a real-map virtual environment. The in-depth analysis reveals that predicting the instantaneous processing power of edge servers facilitates the identification of overloaded servers, which is critical for determining network delay. By considering discrete variables of the queue, the proposed technique's precise estimation can effectively address these combinatorial challenges to achieve optimal performance.

Autonomous Task Offloading of Vehicular Edge Computing with Parallel Computation Queues

TL;DR

The paper tackles delay minimization in vehicular edge computing with multi-CPU edge servers and finite queues by formulating a combinatorial offloading problem and solving it with a distributed message-passing algorithm on a factor graph. It provides a rigorous convergence and optimality analysis, demonstrates exact alignment with the global optimum in simulations, and validates practical feasibility on a real-map digital-twin platform. The approach, which preserves discrete queue dynamics and balances load vs. congestion, achieves significant delay improvements over existing methods and scales to large VEC networks. A noted limitation is tail latency optimization, pointing to future work on priority-aware scheduling to improve worst-case performance.

Abstract

This work considers a parallel task execution strategy in vehicular edge computing (VEC) networks, where edge servers are deployed along the roadside to process offloaded computational tasks of vehicular users. To minimize the overall waiting delay among vehicular users, a novel task offloading solution is implemented based on the network cooperation balancing resource under-utilization and load congestion. Dual evaluation through theoretical and numerical ways shows that the developed solution achieves a globally optimal delay reduction performance compared to existing methods, which is also validated by the feasibility test over a real-map virtual environment. The in-depth analysis reveals that predicting the instantaneous processing power of edge servers facilitates the identification of overloaded servers, which is critical for determining network delay. By considering discrete variables of the queue, the proposed technique's precise estimation can effectively address these combinatorial challenges to achieve optimal performance.

Paper Structure

This paper contains 11 sections, 6 theorems, 42 equations, 11 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Motivation, background, and related works
  3. Contributions
  4. System Model
  5. Distributed Algorithm
  6. Formulation
  7. Derivation
  8. Technical issues
  9. Theoretical analysis
  10. Numerical Results
  11. Conclusion

Key Result

Proposition 1

The number of tasks assigned to CPU-$c$ in RSU-$a$, denoted by $n_{ac}$, is given by

Figures (11)

  • Figure 1: Multiprocessor computation vehicular offloading system.
  • Figure 2: Vehicle association for task offloading delay minimization.
  • Figure 3: The factor graph for an example with 4 vehicles and 2 RSUs.
  • Figure 4: The CDF of the average delay with $V = 10$.
  • Figure 5: The average delay with respect to the number of vehicles.
  • ...and 6 more figures

Theorems & Definitions (10)

  • Proposition 1
  • Proposition 2
  • Definition 1
  • Theorem 1
  • Theorem 2
  • proof
  • Theorem 3
  • proof
  • Lemma 1
  • proof