mlsanityData to 7 Oct 2026

Is Machine Learning Ready for Traffic Engineering Optimization?

arXiv 2109.01445 ↗First posted 3 Sep 2021cs.NI cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Traffic Engineering (TE) is a basic building block of the Internet. In this paper, we analyze whether modern Machine Learning (ML) methods are ready to be used for TE optimization. We address this open question through a comparative analysis between the state of the art in ML and the state of the art in TE. To this end, we first present a novel distributed system for TE that leverages the latest advancements in ML. Our system implements a novel architecture that combines Multi-Agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN) to minimize network congestion. In our evaluation, we compare our MARL+GNN system with DEFO, a network optimizer based on Constraint Programming that represents the state of the art in TE. Our experimental results show that the proposed MARL+GNN solution achieves equivalent performance to DEFO in a wide variety of network scenarios including three real-world network topologies. At the same time, we show that MARL+GNN can achieve significant reductions in execution time (from the scale of minutes with DEFO to a few seconds with our solution).

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 52 references that are in the map. First posted on arXiv 3 Sep 2021.

Builds on

15 of 52 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  5. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  6. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  7. 2018Graph Convolutional Reinforcement Learningcited by 148
  8. 2019Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use casecited by 53
  9. 2018Experience-driven Networking: A Deep Reinforcement Learning based Approachcited by 41
  10. 2019GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platformscited by 29
  11. 2019Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDNcited by 27
  12. 2017Machine Learning for Networking: Workflow, Advances and Opportunitiescited by 20
3 more
  1. 2017A Deep-Reinforcement Learning Approach for Software-Defined Networking Routing Optimizationcited by 14
  2. 2020Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communicationcited by 12
  3. 2017REPETITA: Repeatable Experiments for Performance Evaluation of Traffic-Engineering Algorithmscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 1; 2025: 1.

8 papers.

  1. 2023MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineeringcited by 10
  2. 2024Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passingcited by 8
  3. 2022Proximal Policy Optimization with Graph Neural Networks for Optimal Power Flowcited by 4
  4. 2021A Graph Attention Learning Approach to Antenna Tilt Optimizationcited by 3
  5. 2023FERN: Leveraging Graph Attention Networks for Failure Evaluation and Robust Network Designcited by 1
  6. 2021Physics Constrained Flow Neural Network for Short-Timescale Predictions in Data Communications Networkscited by 0
  7. 2022Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategiescited by 0
  8. 2025Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networkscited by 0