Leveraging Deep Learning to Achieve Efficient Resource Allocation with Traffic Evaluation in Datacenter Optical Networks

This paper first presents a deep learning-based resource allocation strategy supported by global evaluate factor in intra-datacenter optical networks. Numerical results show the proposed strategy improves traffic prediction accuracy and has superior performance.

[1]  Yuefeng Ji,et al.  CSO: cross stratum optimization for optical as a service , 2015, IEEE Communications Magazine.

[2]  Reza Nejabati,et al.  Towards a control plane management architecture enabling proactive network predictability , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[3]  Patrick P. C. Lee,et al.  LD-Sketch: A distributed sketching design for accurate and scalable anomaly detection in network data streams , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[4]  Yanhui Geng,et al.  CODA: Toward Automatically Identifying and Scheduling Coflows in the Dark , 2016, SIGCOMM.

[5]  Naoya Wada,et al.  First experimental demonstration of a distributed cloud and heterogeneous network orchestration with a common Transport API for E2E services with QoS , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[6]  Darko Zibar,et al.  Machine learning techniques applied to system characterization and equalization , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[7]  Jiajia Chen,et al.  Optical transport network architecture enabling ultra-low latency for communications among base stations , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).