Quality-Aware Task Offloading for Cooperative Perception in Vehicular Edge Computing

TL;DR

Quality-aware Cooperative Perception Task Offloading (Q-CPTO) addresses the problem of enhancing traffic awareness in Vehicular Edge Computing by prioritizing the Value of Information ($VOI$) over mere data quantity. It combines Kalman Filter-based mobility prediction to estimate each vehicle's Region of Interest ($ROI$), a quality utility framework to compute $VOI$ and shared interest $q_{ik}$, and an ILP formulation (QMKP) to offload perception tasks to edge workers while minimizing redundancy. A polynomial-time heuristic, Q-CPTO-H, provides scalable near-optimal decisions with significant runtime reductions. Empirical results show Q-CPTO and Q-CPTO-H outperform latency-focused baselines in both response delay and traffic awareness by up to substantial margins, with Q-CPTO-H approaching optimal performance and offering substantial scalability benefits for real-time CP in dynamic traffic scenarios.

Abstract

Task offloading in Vehicular Edge Computing (VEC) can advance cooperative perception (CP) to improve traffic awareness in Autonomous Vehicles. In this paper, we propose the Quality-aware Cooperative Perception Task Offloading (QCPTO) scheme. Q-CPTO is the first task offloading scheme that enhances traffic awareness by prioritizing the quality rather than the quantity of cooperative perception. Q-CPTO improves the quality of CP by curtailing perception redundancy and increasing the Value of Information (VOI) procured by each user. We use Kalman filters (KFs) for VOI assessment, predicting the next movement of each vehicle to estimate its region of interest. The estimated VOI is then integrated into the task offloading problem. We formulate the task offloading problem as an Integer Linear Program (ILP) that maximizes the VOI of users and reduces perception redundancy by leveraging the spatially diverse fields of view (FOVs) of vehicles, while adhering to strict latency requirements. We also propose the Q-CPTO-Heuristic (Q-CPTOH) scheme to solve the task offloading problem in a time-efficient manner. Extensive evaluations show that Q-CPTO significantly outperforms prominent task offloading schemes by up to 14% and 20% in terms of response delay and traffic awareness, respectively. Furthermore, Q-CPTO-H closely approaches the optimal solution, with marginal gaps of up to 1.4% and 2.1% in terms of traffic awareness and the number of collaborating users, respectively, while reducing the runtime by up to 84%.

Figures (5)

• Figure 1: Software-defined network for cooperative services (SD-CS) framework.
• Figure 2: Impact of the schemes over varying computation capability (deadline=0.4, users=40).
• Figure 3: Impact of the schemes over varying deadlines (c=2, users=40).
• Figure 4: Impact of the schemes over varying users (c=2, deadline=0.4).
• Figure 5: Run Time of Decision Making for Q-CPTO, Q-CPTO-H.