Mistill: Distilling Distributed Network Protocols From Examples

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT(2023)

引用 0|浏览1
暂无评分
摘要
Traffic Engineering (TE) mechanisms in data center networks make distributed forwarding decisions based on the global network state. Thus, new TE mechanisms require the design and implementation of effective information exchange and efficient decentralized algorithms to compute forwarding decisions, which is challenging and time-intensive. To automate and simplify this process, we propose Mistill. Mistill distills the forwarding behavior of TE policies from exemplary forwarding decisions into a Neural Network. Mistill learns (i) how to encode local state into update messages, (ii) which network devices must exchange updates, and (iii) how to map the exchanged updates into forwarding decisions. We demonstrate the abilities of Mistill by learning three TE policies, verifying their performance in simulations on synthetic and real-world traffic patterns, and by showing that the learned policies generalize to unseen traffic patterns. We implement Mistill as a proof-of-concept and show that Mistill reacts on average within 1.3ms to changes in the network.
更多
查看译文
关键词
Switches,Artificial neural networks,Fats,Topology,Servers,Network topology,Data centers,Network protocols,traffic engineering,routing,neural networks,supervised learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要