论文标题
使用强化学习分配和管理蜂窝网络中的服务功能链
Using Reinforcement Learning to Allocate and Manage Service Function Chains in Cellular Networks
论文作者
论文摘要
可以预期，下一代蜂窝网络为建立了一个完全流动性的社会，以增强社会经济转型的能力。其他几种技术将受益于这种发展，例如物联网，智能城市，智能农业，车辆网络，医疗保健应用程序等。这些方案中的每一个都提出了特定的要求，并要求不同的网络配置。为了处理这种异质性，虚拟化技术是关键技术。实际上，网络功能虚拟化（NFV）范式为网络经理提供了灵活性，根据需求分配资源，并降低了收购和运营成本。此外，可以为给定服务指定一组有序的网络虚拟函数（VNF），该功能称为服务功能链（SFC）。但是，除了服务虚拟化带来的优点外，预计网络性能和可用性不会受到其用法的影响。在本文中，我们建议使用增强学习来部署蜂窝网络服务的SFC并管理VNFS操作。我们认为，SFC是由强化学习代理人部署的，考虑到具有分布式数据中心的方案，其中VNF在商品服务器的虚拟机中部署。 NFV管理与创建，删除和重新启动VNF有关。主要目的是考虑服务器的能源消耗，减少丢失的数据包数量。我们使用近端策略优化（PPO）算法来实现代理，初步结果表明，代理能够分配SFC并管理VNF，从而减少了丢失的数据包的数量。
It is expected that the next generation cellular networks provide a connected society with fully mobility to empower the socio-economic transformation. Several other technologies will benefits of this evolution, such as Internet of Things, smart cities, smart agriculture, vehicular networks, healthcare applications, and so on. Each of these scenarios presents specific requirements and demands different network configurations. To deal with this heterogeneity, virtualization technology is key technology. Indeed, the network function virtualization (NFV) paradigm provides flexibility for the network manager, allocating resources according to the demand, and reduces acquisition and operational costs. In addition, it is possible to specify an ordered set of network virtual functions (VNFs) for a given service, which is called as service function chain (SFC). However, besides the advantages from service virtualization, it is expected that network performance and availability do not be affected by its usage. In this paper, we propose the use of reinforcement learning to deploy a SFC of cellular network service and manage the VNFs operation. We consider that the SFC is deployed by the reinforcement learning agent considering a scenarios with distributed data centers, where the VNFs are deployed in virtual machines in commodity servers. The NFV management is related to create, delete, and restart the VNFs. The main purpose is to reduce the number of lost packets taking into account the energy consumption of the servers. We use the Proximal Policy Optimization (PPO) algorithm to implement the agent and preliminary results show that the agent is able to allocate the SFC and manage the VNFs, reducing the number of lost packets.
