作者
Zhiying Xu, Francis Y Yan, Rachee Singh, Justin T Chiu, Alexander M Rush, Minlan Yu
发表日期
2023/9
研讨会论文
ACM Special Interest Group on Data Communication Conference (SIGCOMM)
简介
The rapid expansion of global cloud wide-area networks (WANs) has posed a challenge for commercial optimization engines to efficiently solve network traffic engineering (TE) problems at scale. Existing acceleration strategies decompose TE optimization into concurrent subproblems but realize limited parallelism due to an inherent tradeoff between run time and allocation performance.
We present Teal, a learning-based TE algorithm that leverages the parallel processing power of GPUs to accelerate TE control. First, Teal designs a flow-centric graph neural network (GNN) to capture WAN connectivity and network flows, learning flow features as inputs to downstream allocation. Second, to reduce the problem scale and make learning tractable, Teal employs a multi-agent reinforcement learning (RL) algorithm to independently allocate each traffic demand while optimizing a central TE objective. Finally, Teal fine …
学术搜索中的文章
Z Xu, FY Yan, R Singh, JT Chiu, AM Rush, M Yu - Proceedings of the ACM SIGCOMM 2023 Conference, 2023