Distributed Load Orchestration for Vision Computing in Multi-Access Edge Computing

TL;DR

This paper proposes a distributed load orchestration strategy for MEC environments, specifically for video surveillance, that improves resource utilization and deadline adherence through load balancing and queue prioritization.

Contribution

It introduces a novel distributed orchestration approach based on load balancing and deadline-aware queueing for MEC, validated through simulation experiments.

Findings

Reduced number of referrals in MEC processing

Improved deadline compliance for video requests

Enhanced resource management in 5G-MEC environments

Abstract

Multi-access Edge Computing (MEC) is a type of network architecture that provides cloud computing capabilities at the edge of the network. We consider the use case of video surveillance for an university campus running on a 5G-MEC environment. A key issue is the eventual overloading of computing resources on the MEC nodes during peak demand. We propose a new strategy for distributed orchestration in MEC environments based on how load balancing strategies organize processing queue. Then, we elaborated a strategy for deadline-aware queueing prioritization that organizes requests based on pre-established thresholds. We introduce a simulation-based experimentation environment and conduct a number of tests demonstrating the benefit of our approach by reducing the number of referrals and improving the effectiveness in meeting deadlines.