Paper
27 March 2022 Educational experimental platform for engineering training in AI-assisted optical networks for data center
Author Affiliations +
Proceedings Volume 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications; 121695E (2022) https://doi.org/10.1117/12.2624364
Event: Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 2021, Kunming, China
Abstract
With the rapid development of optical network for data center techniques and artificial intelligent algorithms, it’s harder to train relevant professionals. Experimental course plays an important role for students to deepen understanding of complex theoretical knowledge. However, existing SDN-based experimental platforms face two challenges that increase the learning cost: (1) how to evaluate intelligent algorithms in optical network for data center rapidly and automatically, (2) how to provide a large-scale optical network for data center environment for students’ practice with acceptable cost. To overcome these two challenges, this paper proposed an innovative educational platform with two features: (1) Introducing an intelligent algorithm center in the control layer to store and manage students’ different customized intelligent algorithms. (2) Introducing the combination of physical domain and virtual domain in underlying devices layer to provide a large-scale network experimental environment for students. The main functions of the proposed platform have been realized. Many students have used this platform to evaluate their intelligent algorithms. The difficulty of evaluating intelligent algorithms is greatly reduced. Students can make it more clear how intelligent algorithm works on optical networks for data center.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ziyi Xi, Boyang Lin, Rentao Gu, Zeyuan Yang, and Yuefeng Ji "Educational experimental platform for engineering training in AI-assisted optical networks for data center", Proc. SPIE 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 121695E (27 March 2022); https://doi.org/10.1117/12.2624364
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data centers

Optical networks

Networks

Evolutionary algorithms

Network architectures

Control systems

Algorithm development

Back to Top