Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MACH: Multi-Agent Coordination for RSU-centric Handovers

Nikolaus Spring, Andrea Morichetta, Boris Sedlak, Schahram Dustdar

TL;DR

MACH tackles the problem of latency-aware task offloading in vehicular edge computing by shifting handover coordination from vehicles or central controllers to the network edge, specifically RSUs. It introduces a lightweight, decentralized multi-agent framework where RSU and vehicle agents predict trajectories and load to optimize handovers, balancing QoS and RSU utilization without requiring heavy training. The authors validate MACH in a realistic urban scenario with real traffic traces, showing improved QoS and fair load distribution across varying RSU densities and under RSU failures. This edge-centric approach reduces communication overhead and enhances adaptability, offering a practical framework for robust vehicular computing in dynamic environments.

Abstract

This paper introduces MACH, a novel approach for optimizing task handover in vehicular computing scenarios. To ensure fast and latency-aware placement of tasks, the decision-making -- where and when should tasks be offloaded -- is carried out decentralized at the Road Side Units (RSUs) who also execute the tasks. By shifting control to the network edge, MACH moves away from the traditional centralized or vehicle-based handover method. Still, it focuses on contextual factors, such as the current RSU load and vehicle trajectories. Thus, MACH improves the overall Quality of Service (QoS) while fairly balancing computational loads between RSUs. To evaluate the effectiveness of our approach, we develop a robust simulation environment composed of real-world traffic data, dynamic network conditions, and different infrastructure capacities. For scenarios that demand low latency and high reliability, our experimental results demonstrate how MACH significantly improves the adaptability and efficiency of vehicular computations. By decentralizing control to the network edge, MACH effectively reduces communication overhead and optimizes resource utilization, offering a robust framework for task handover management.

MACH: Multi-Agent Coordination for RSU-centric Handovers

TL;DR

MACH tackles the problem of latency-aware task offloading in vehicular edge computing by shifting handover coordination from vehicles or central controllers to the network edge, specifically RSUs. It introduces a lightweight, decentralized multi-agent framework where RSU and vehicle agents predict trajectories and load to optimize handovers, balancing QoS and RSU utilization without requiring heavy training. The authors validate MACH in a realistic urban scenario with real traffic traces, showing improved QoS and fair load distribution across varying RSU densities and under RSU failures. This edge-centric approach reduces communication overhead and enhances adaptability, offering a practical framework for robust vehicular computing in dynamic environments.

Abstract

This paper introduces MACH, a novel approach for optimizing task handover in vehicular computing scenarios. To ensure fast and latency-aware placement of tasks, the decision-making -- where and when should tasks be offloaded -- is carried out decentralized at the Road Side Units (RSUs) who also execute the tasks. By shifting control to the network edge, MACH moves away from the traditional centralized or vehicle-based handover method. Still, it focuses on contextual factors, such as the current RSU load and vehicle trajectories. Thus, MACH improves the overall Quality of Service (QoS) while fairly balancing computational loads between RSUs. To evaluate the effectiveness of our approach, we develop a robust simulation environment composed of real-world traffic data, dynamic network conditions, and different infrastructure capacities. For scenarios that demand low latency and high reliability, our experimental results demonstrate how MACH significantly improves the adaptability and efficiency of vehicular computations. By decentralizing control to the network edge, MACH effectively reduces communication overhead and optimizes resource utilization, offering a robust framework for task handover management.
Paper Structure (61 sections, 1 equation, 19 figures, 2 tables)

This paper contains 61 sections, 1 equation, 19 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Computation Offloading in Vehicular Edge Computing
  4. Task-driven Offloading Solutions
  5. Infrastructure-driven Offloading Solutions
  6. RSU-Centric Approaches
  7. Simulation Environments for Offloading in VEC
  8. Takeaways
  9. Methodology
  10. Vehicular Platform and Infrastructure
  11. Vehicular Edge Layer
  12. Infrastructure RSU Layer
  13. Vehicle-Infrastructure Communication
  14. Limitations
  15. Agent-Based Collaboration
  16. ...and 46 more sections

Figures (19)

  • Figure 1: Optimize the Quality of Service (QoS) for vehicular computation offloading: find an RSU station with maximal available capacity and minimum transmission latency; find the best time to handover Vehicle #1 from RSU #1 to RSU #2 according to the predicted vehicle trajectory
  • Figure 2: Optimize task handover in vehicular edge computing according to expected QoS and infrastructure load: (1) find best RSU for handover, (2) request handover, (3) accept request, and (4) transfer vehicle state
  • Figure 3: Logic flow of the MACH strategy for vehicles' tasks handovers.
  • Figure 4: Logic flow of the MACH load balancing strategy.
  • Figure 5: Europarc Roundabout in Créteil, France
  • ...and 14 more figures