QR-MO: Q-Routing for Multi-Objective Shortest-Path Computation in 5G-MEC Systems

2025-03-23

AI Summary

To address the challenge of computing shortest paths under multiple concurrent objectives—latency, packet loss rate, and jitter—in 5G multi-access edge computing (MEC) networks, this paper proposes a multi-objective Q-Routing reinforcement learning method that requires no predefined weight assignments. The approach integrates Pareto-optimal path policy learning, multi-objective reward shaping, and tailored state encoding, thereby extending Q-Routing to dynamic multi-objective routing for the first time. Evaluated against the multi-objective Dijkstra algorithm (MDA) baseline, the method achieves 100% path accuracy within just 100 training episodes in low- to medium-degree networks, and maintains over 85% accuracy even in high-degree networks. These results demonstrate substantial improvements in end-to-end quality-of-service (QoS) adaptability and routing efficiency under heterogeneous network conditions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Multi-access edge computing (MEC) is a promising technology that provides low-latency processing capabilities. To optimize the network performance in a MEC system, an efficient routing path between a user and a MEC host is essential. The network performance is characterized by multiple attributes, including packet-loss probability, latency, and jitter. A user service may require a particular combination of such attributes, complicating the shortest-path computation. This paper introduces Q-Routing for Multi-Objective shortest-path computation (QR-MO), which simultaneously optimizes multiple attributes. We compare the QR-MO's solutions with the optimal solutions provided by the Multi-objective Dijkstra Algorithm (MDA). The result shows the favorable potential of QR-MO. After 100 episodes, QR-MO achieves 100% accuracy in networks with low to moderate average node degrees, regardless of the size, and over 85% accuracy in networks with high average node degrees.

Problem

• Optimizes multi-attribute routing in 5G-MEC systems
• Compares QR-MO with Multi-objective Dijkstra Algorithm
• Achieves high accuracy in diverse network conditions

Innovation

• Q-Routing optimizes multiple network attributes
• Compares with Multi-objective Dijkstra Algorithm
• Achieves high accuracy in varying networks