Scalable knowledge-defined orchestration for hybrid optical–electrical datacenter networks [Invited]

Abstract

To better provision fast-emerging network applications with various quality-of-service demands, datacenter network (DCN) operators need an effective network orchestration scheme that can coordinate IT and bandwidth resources for differentiated services in a timely manner. In this work, we consider a hybrid optical–electrical DCN (HOE-DCN) and study how to achieve scalable knowledge-defined network orchestration (KD-NO) for managing the delay-sensitive and delay-tolerant applications in it. For delay-sensitive applications, we leverage a multi-agent scheme to distribute the tasks of placing virtual machines (VMs) in server racks and routing VM traffic in electrical–optical inter-rack clouds to two cooperative deep reinforcement learning modules, respectively. Then, we utilize a classic-algorithm-based module to provision delay-tolerant applications with the residual resources in the HOE-DCN. We design the operation and coordination procedure of the KD-NO system and build a small HOE-DCN testbed that consists of four server racks to demonstrate its performance experimentally. Experimental results indicate that our KD-NO system can make timely and correct network orchestration decisions and have better convergence performance compared with the existing benchmark.

Results and Achievements of the ALLIANCE Project: New Network Solutions for 5G and Beyond

“…The resulting AI-empowered knowledge plane can be beneficial to efficiently implement emerging networking trends based on complex high-level operational goals, such as Intent-Driven Networking [12], or Beyond-Shannon Semantic communications [13]. Since it was conceived, KDN has served as a reference for a large body of literature aiming to deploy AI/ML techniques for network automation [14][15][16].…”

Enabling knowledge-defined networks : deep reinforcement learning, graph neural networks and network analytics

“…With this architecture, KDN facilitates the construction of a functional knowledge plane running AI-based solutions to operate networks in a more efficient and automatic way, all this with the ultimate goal of achieving self-driving networks in the future. Since it was conceived, the networking community has received KDN with increasing interest and -in line with its objectives -it has already served as a reference paradigm for later research endeavors to deploy AI techniques for network automation[25][26][27][28][29].…”