{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T19:10:06Z","timestamp":1755976206424,"version":"3.44.0"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"CoNEXT1","license":[{"start":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T00:00:00Z","timestamp":1741132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62221003, 62132004"],"award-info":[{"award-number":["62221003, 62132004"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Netw."],"published-print":{"date-parts":[[2025,3,5]]},"abstract":"<jats:p>The rapid growth of global modern wide area networks has posed significant challenges to traffic engineering (TE). Existing TE methods often struggle to balance optimality with tractability, while recent machine learning based approaches fail to develop reliable strategies across diverse network scenarios. To address these issues, we introduce LO-TE, a novel TE solution integrating deep Learning and Optimization techniques. LO-TE operates in two phases: obtaining an initial solution and refining it to achieve a near-optimal TE solution. Our approach utilizes a scalable graph attention network for finding the necessary flows for refinement, paired with a refining algorithm based on linear programming. We demonstrate the application of LO-TE on three typical TE problems. We evaluate LO-TE on both real-world and self-generated large-scale topologies, demonstrating its strong generalizability across various TE problems and traffic models. The evaluation results indicate that LO-TE is 12x-188x faster than traditional TE optimization methods on large-scale network topologies, with an average performance gap of less than 6% compared to the optimal solution. Moreover, LO-TE outperforms state-of-the-art deep learning-based TE methods using limited training data, achieving only 1.8%-69% maximum link utilization under dynamic traffic conditions.<\/jats:p>","DOI":"10.1145\/3709372","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T12:15:54Z","timestamp":1741263354000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Shooting Large-scale Traffic Engineering by Combining Deep Learning and Optimization Approach"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2630-4558","authenticated-orcid":false,"given":"Chenyi","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China and Zhongguancun Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7490-5568","authenticated-orcid":false,"given":"Haotian","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-4723","authenticated-orcid":false,"given":"Vaneet","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3481-8447","authenticated-orcid":false,"given":"Yuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-4585","authenticated-orcid":false,"given":"Mingwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Abuzaid Firas","year":"2021","unstructured":"Firas Abuzaid, Srikanth Kandula, Behnaz Arzani, Ishai Menache, Matei Zaharia, and Peter Bailis. 2021. Contracting wide-area network topologies to solve flow problems quickly. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 175--200."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472918"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651930"},{"key":"e_1_2_1_4_1","volume-title":"How Attentive are Graph Attention Networks? arXiv","author":"Brody Shaked","year":"2021","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2021. How Attentive are Graph Attention Networks? arXiv (2021)."},{"key":"e_1_2_1_5_1","unstructured":"CAIDA. 2022. The CAIDA AS Relationships Dataset."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604860"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604854"},{"volume-title":"Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.","author":"Fey Matthias","key":"e_1_2_1_8_1","unstructured":"Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2002.1039866"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP49622.2020.9259413"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521303"},{"key":"e_1_2_1_12_1","unstructured":"Gurobi Optimization LLC. 2022. Gurobi Optimizer Reference Manual. https:\/\/www.gurobi.com"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486012"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230545"},{"key":"e_1_2_1_15_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Jain Paras","year":"2023","unstructured":"Paras Jain, Sam Kumar, Sarah Wooders, Shishir G Patil, Joseph E Gonzalez, and Ion Stoica. 2023. Skyplane: Optimizing transfer cost and throughput using {Cloud-Aware} overlays. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1375--1389."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"e_1_2_1_17_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Krishnaswamy Umesh","year":"2022","unstructured":"Umesh Krishnaswamy, Rachee Singh, Nikolaj Bj\u00f8rner, and Himanshu Raj. 2022. Decentralized cloud wide-area network traffic engineering with {BLASTSHIELD}. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 325--338."},{"key":"e_1_2_1_18_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Krishnaswamy Umesh","year":"2023","unstructured":"Umesh Krishnaswamy, Rachee Singh, Paul Mattes, Paul-Andre C Bissonnette, Nikolaj Bj\u00f8rner, Zahira Nasrin, Sonal Kothari, Prabhakar Reddy, John Abeln, Srikanth Kandula, et al. 2023. {OneWAN} is better than two: Unifying a split {WAN} architecture. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 515--529."},{"key":"e_1_2_1_19_1","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Kumar Praveen","year":"2018","unstructured":"Praveen Kumar, Yang Yuan, Chris Yu, Nate Foster, Robert Kleinberg, Petr Lapukhov, Chiun Lin Lim, and Robert Soul\u00e9. 2018. {Semi-Oblivious} Traffic Engineering: The Road Not Taken. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 157--170."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672258"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2001.948886"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563766.3564102"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483588"},{"key":"e_1_2_1_24_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Perry Yarin","year":"2023","unstructured":"Yarin Perry, Felipe Vieira Frujeri, Chaim Hoch, Srikanth Kandula, Ishai Menache, Michael Schapira, and Aviv Tamar. 2023. {DOTE}: Rethinking (Predictive){WAN} Traffic Engineering. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1557--1581."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1096536.1096551"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111322.1111341"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"e_1_2_1_28_1","volume-title":"Traffic Engineering with MPLS in the Internet","author":"Xiao Xipeng","year":"2000","unstructured":"Xipeng Xiao, Alan Hannan, Brook Bailey, and Lionel M Ni. 2000. Traffic Engineering with MPLS in the Internet. IEEE network, Vol. 14, 2 (2000), 28--33."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604857"},{"key":"e_1_2_1_31_1","volume-title":"Large language models as optimizers. arXiv preprint arXiv:2309.03409","author":"Yang Chengrun","year":"2023","unstructured":"Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. Large language models as optimizers. arXiv preprint arXiv:2309.03409 (2023)."},{"key":"e_1_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 5872--5881","author":"Zhang Kaiqing","year":"2018","unstructured":"Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, and Tamer Basar. 2018. Fully decentralized multi-agent reinforcement learning with networked agents. In International Conference on Machine Learning. PMLR, 5872--5881."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"}],"container-title":["Proceedings of the ACM on Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709372","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:41:39Z","timestamp":1755974499000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,5]]},"references-count":33,"journal-issue":{"issue":"CoNEXT1","published-print":{"date-parts":[[2025,3,5]]}},"alternative-id":["10.1145\/3709372"],"URL":"https:\/\/doi.org\/10.1145\/3709372","relation":{},"ISSN":["2834-5509"],"issn-type":[{"type":"electronic","value":"2834-5509"}],"subject":[],"published":{"date-parts":[[2025,3,5]]},"assertion":[{"value":"2025-03-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}