The emergence of new applications brings multi-class traffic with diverse quality of service (QoS) requirements to wide area networks (WANs), motivating research in traffic engineering (TE). In recent years, novel centralized and hierarchical TE schemes have used heuristic or machine learning techniques to orchestrate resources in closed systems such as datacenter networks. However, these schemes suffer from long delivery delays and high control overhead when applied to general WANs. To provide low-delay services, this paper proposes an asynchronous multi-class traffic management (AMTM) scheme. We first establish an asynchronous TE paradigm in which distributed nodes locally perform low-complexity and low-delay traffic control based on link prices, and the TE server updates link prices to eliminate decision conflicts between edge nodes. By modeling the asynchronous TE paradigm as a control system with non-negligible control loop delay, we find that the traditional pricing strategy cannot simultaneously achieve a low packet loss rate and a low flow delivery delay. To address this issue, we propose a new pricing strategy based on the observations of virtual queues in intermediate nodes. We also present a system design and related algorithms that utilize a dynamic step size mechanism of link price update. Simulation results show that AMTM can effectively reduce the end-to-end flow delivery delay.

翻译：新兴应用带来了具有不同服务质量（QoS）要求的多类别流量，促使广域网（WAN）中流量工程（TE）的研究。近年来，新型集中式和分层式TE方案利用启发式算法或机器学习技术，在数据中心网络等封闭系统中协调资源。然而，这些方案在应用于通用WAN时存在较长的传输延迟和高控制开销。为提供低延迟服务，本文提出一种异步多类别流量管理（AMTM）方案。我们首先建立一种异步TE范式：其中分布式节点基于链路价格本地执行低复杂度、低延迟的流量控制，TE服务器则通过更新链路价格来消除边缘节点间的决策冲突。通过将异步TE范式建模为具有不可忽略控制环路延迟的控制系统，我们发现传统定价策略无法同时实现低丢包率和低流传输延迟。为解决此问题，我们提出一种基于中间节点虚拟队列观测值的新型定价策略。同时，我们给出了利用链路价格更新动态步长机制的系统设计与相关算法。仿真结果表明，AMTM能有效降低端到端流传输延迟。