Workload-Aware Routing Optimization via Graph Reinforcement Learning for Joint Delay Minimization in Edge–Cloud Networks
- 12 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (2) , 2831-2847
Abstract
The rapid proliferation of end devices and their hosted applications has significantly increased the demand for data processing. However, lightweight edge endpoints often suffer from limited computational capabilities due to power and battery constraints. Consequently, computation-intensive tasks are typically offloaded to cloud servers located in data centers for processing. While existing studies often abstract the edge–cloud connection as a direct link, the actual backbone network features complex topologies and constrained bandwidth, which intensify as workload scales up. To address this challenge, this paper investigates routing optimization within the backbone network under task offloading scenarios, and proposes a workload-aware deep reinforcement learning (DRL)-based routing algorithm for joint minimization of transmission and processing delays. Specifically, we first develop a detailed system model using discrete event simulation. Then, we design an integrated DRL-based decision-making scheme that simultaneously determines optimal routing paths and target data centers. Extensive experiments on diverse real-world network topologies and heterogeneous task workloads demonstrate that the proposed algorithm significantly outperforms conventional baselines in reducing both transmission and processing delays.Keywords
Funding Information
- National Natural Science Foundation of China (Grant No. 62371057)
This publication has 29 references indexed in Scilit:
- GROM: A generalized routing optimization method with graph neural network and deep reinforcement learningJournal of Network and Computer Applications, 2024
- Packet Routing with Graph Attention Multi-Agent Reinforcement Learning2021
- Line Graphs and Line Digraphs2021
- CoDRL: Intelligent Packet Routing in SDN Using Convolutional Deep Reinforcement Learning2019
- TIDE: Time-relevant deep reinforcement learning for routing optimizationFuture Generation Computer Systems, 2019
- A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and ChallengesIEEE Communications Surveys & Tutorials, 2018
- Experience-driven Networking: A Deep Reinforcement Learning based Approach2018
- A Survey on Software-Defined Network and OpenFlow: From Concept to ImplementationIEEE Communications Surveys & Tutorials, 2014
- Flow Monitoring Explained: From Packet Capture to Data Analysis With NetFlow and IPFIXIEEE Communications Surveys & Tutorials, 2014
- RESTful Web Services2009