Wide Area Networks (WAN) are a key infrastructure in today's society. During the last years, WANs have seen a considerable increase in network's traffic and network applications, imposing new requirements on existing network technologies (e.g., low latency and high throughput). Consequently, Internet Service Providers (ISP) are under pressure to ensure the customer's Quality of Service and fulfill Service Level Agreements. Network operators leverage Traffic Engineering (TE) techniques to efficiently manage network's resources. However, WAN's traffic can drastically change during time and the connectivity can be affected due to external factors (e.g., link failures). Therefore, TE solutions must be able to adapt to dynamic scenarios in real-time. In this paper we propose Enero, an efficient real-time TE solution based on a two-stage optimization process. In the first one, Enero leverages Deep Reinforcement Learning (DRL) to optimize the routing configuration by generating a long-term TE strategy. To enable efficient operation over dynamic network scenarios (e.g., when link failures occur), we integrated a Graph Neural Network into the DRL agent. In the second stage, Enero uses a Local Search algorithm to improve DRL's solution without adding computational overhead to the optimization process. The experimental results indicate that Enero is able to operate in real-world dynamic network topologies in 4.5 seconds on average for topologies up to 100 edges.
翻译:广域网是当今社会的关键基础设施。在过去几年中,广域网的交通量和网络应用量大幅增加,对现有的网络技术提出了新的要求(例如低潜值和高吞吐量)。因此,互联网服务提供商面临压力,以确保客户服务质量并履行服务级协议。网络运营商利用交通工程技术有效管理网络资源。然而,广域网的交通量在时间上可发生急剧变化,连通因外部因素(例如连接失败)而受到影响。因此,TE解决方案必须能够实时适应动态情景。在本文件中,我们提议Enero,一个基于两阶段优化过程的高效实时TE解决方案。在第一个文件中,Enero利用深强化学习(DRL),通过制定长期的TE战略,优化路由配置。在动态网络假设(例如,发生连接失败时,我们将直线网络纳入动态网络,以便实时适应动态情景。在SDRL服务器的顶端运行过程中,我们建议Eng NErial-dealalal ASirmal ASirmal ASirmal ASirital ASimal ASVA,在Siral ASyal ASyal ASiral ASyal ASildal 中,在Sildal ASyal ASyal ASyal ASyal ASyal ASyal ASyal ASyal ASyal ASyaldaldal 中,在Sildal ASirmal ASildal ASVIL 。在Sildal 中,在Sildal ASyal 一级,在SL ASVAL 中,在SL ASVAL ASAL ASAL ASAL 上,在SL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL 上,在SAL ASVAL 上,在SBAL ASAL ASAL ASAL ASAL 上,在SAL ASAL 上,在SAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL ASAL 上,在SAL AS