学术文献库

In the last few decades, data center architecture evolved from the traditional client-server to access-aggregation-core architectures. Recently there is a new shift in the data center architecture due to the increasing need for low latency and high throughput between server-to-server communications, load balancing and, loop-free environment. This new architecture, known as leaf and spine architecture, provides low latency and minimum packet loss by enabling the addition and deletion of network nodes on demand. Network nodes can be added or deleted from the network based on network statistics like link speed, packet loss, latency, and throughput. With the maturity of Open Virtual Switch (OvS) and OpenFlow based Software Defined Network (SDN) controllers, network automation through programmatic extensions has become possible based on network statistics. The separation of the control plane and data plane has enabled automated management of network and Machine Learning (ML) can be applied to learn and optimize the network. In this publication, we propose the design of an ML-based approach to gather network statistics and build a knowledge plane. We demonstrate that this knowledge plane enables data center optimization using southbound APIs and SDN controllers. We describe the design components of this approach - using a network simulator and show that it can maintain the historical patterns of network statistics to predict future growth or decline. We also provide an open-source software that can be utilized in a leaf and spine data center to provide elastic capacity based on load forecasts.