Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Distributed Resource Allocation and Application Deployment in Mesh Edge Networks

Antoine Bernard, Antoine Legrain, Maroua Ben Attia, Abdo Shabah

TL;DR

The paper extends Virtual Network Embedding to mobile, constrained mesh-edge environments by modeling a centralized resource-allocation framework that accounts for device mobility, connectivity, and energy. It compares three allocation strategies—an optimal ILP, a greedy heuristic, and an NSGA-II multi-objective optimizer—using a unified simulator with fixed arrival/departure rates. Results show ILP delivers the highest application acceptance, NSGA-II offers the best latency and resource-efficiency balance, while the greedy method provides fast deployment but lower overall performance. These findings establish a foundation for VNE deployment in highly dynamic edge networks and suggest hybrid or distributed approaches for real-world, mobility-aware edge computing.

Abstract

Virtual Network Embedding (VNE) approaches typically assume static or slowly-changing network topologies, but emerging applications require deployment in mobile environments where traditional methods become insufficient. This work extends VNE to constrained mesh networks of mobile edge devices, addressing the unique challenges of rapid topology changes and limited resources. We develop models incorporating device capabilities, connectivity, mobility and energy constraints to evaluate optimal deployment strategies for mobile edge environments. Our approach handles the dynamic nature of mobile networks through three allocation strategies: an integer linear program for optimal allocation, a greedy heuristic for immediate deployment, and a multi-objective genetic algorithm for balanced optimization. Our initial evaluation analyzes application acceptance rates, resource utilization, and latency performance under resource limitations. Results demonstrate improvements over traditional approaches, providing a foundation for VNE deployment in highly mobile environments.

Distributed Resource Allocation and Application Deployment in Mesh Edge Networks

TL;DR

The paper extends Virtual Network Embedding to mobile, constrained mesh-edge environments by modeling a centralized resource-allocation framework that accounts for device mobility, connectivity, and energy. It compares three allocation strategies—an optimal ILP, a greedy heuristic, and an NSGA-II multi-objective optimizer—using a unified simulator with fixed arrival/departure rates. Results show ILP delivers the highest application acceptance, NSGA-II offers the best latency and resource-efficiency balance, while the greedy method provides fast deployment but lower overall performance. These findings establish a foundation for VNE deployment in highly dynamic edge networks and suggest hybrid or distributed approaches for real-world, mobility-aware edge computing.

Abstract

Virtual Network Embedding (VNE) approaches typically assume static or slowly-changing network topologies, but emerging applications require deployment in mobile environments where traditional methods become insufficient. This work extends VNE to constrained mesh networks of mobile edge devices, addressing the unique challenges of rapid topology changes and limited resources. We develop models incorporating device capabilities, connectivity, mobility and energy constraints to evaluate optimal deployment strategies for mobile edge environments. Our approach handles the dynamic nature of mobile networks through three allocation strategies: an integer linear program for optimal allocation, a greedy heuristic for immediate deployment, and a multi-objective genetic algorithm for balanced optimization. Our initial evaluation analyzes application acceptance rates, resource utilization, and latency performance under resource limitations. Results demonstrate improvements over traditional approaches, providing a foundation for VNE deployment in highly mobile environments.

Paper Structure

This paper contains 22 sections, 3 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. System Model
  5. System Parameters
  6. Preprocessing Parameters
  7. Variables
  8. Complete Optimization Formulation
  9. Implementation
  10. Experiment
  11. Reference Allocation
  12. Optimization-Based Allocation
  13. Multi-Objective Genetic Algorithm (NSGA-II)
  14. Performance Metrics
  15. Experimental Parameters
  16. ...and 7 more sections

Figures (4)

  • Figure 1: Virtual Network Embedding in mobile edge networks. The middle shows virtual network requests (S1, S2, S3) with specific resource demands (CPU, memory, GPU) and bandwidth requirements. The sides depict the physical substrate mesh network of edge devices with limited resources. Arrows indicate partial mappings (orange), failed attempts (red) due to resource constraints (GPU not available on node NS, Latency $\geq$ 2 hops for N1-N4) and successful mappings (green) possible by taking into account the overall system (NSGA-II, ILP) instead of following a greedy approach.
  • Figure 2: Performance comparison of three allocation strategies showing (top) acceptance ratios over time, and (bottom) concurrent application counts
  • Figure 3: Average latency comparison across allocation strategies
  • Figure 4: Resource utilization patterns showing (top) bandwidth usage efficiency, and (bottom) maximum device resource consumption