论文信息 - Deep Neural Network Based Dynamic Resource Reallocation of BBU Pools in 5G C-RAN ROADM Networks - 字舞流文

Deep Neural Network Based Dynamic Resource Reallocation of BBU Pools in 5G C-RAN ROADM Networks

An LSTM network is developed to predict BBU pool traffic in 5G C-RAN ROADM networks. 5G throughput improvement and resource savings are observed with resource reallocation by reconfiguring the optical network 30 minutes in advance.

Yao Li | Daniel C. Kilper | Gil Zussman | Weiyang Mo | Craig L. Gutterman | D. Kilper | G. Zussman | Craig L. Gutterman | Yao Li | W. Mo

[1] L. E. Nelson,et al. SDN-controlled 400GbE end-to-end service using a CFP8 client over a deployed, commercial flexible ROADM system , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[2] Jürgen Schmidhuber,et al. Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[3] Luiz A. DaSilva,et al. Integrating wireless BBUs with optical OFDM flexible-grid transponders in a C-RAN architecture , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[4] Francesco Musumeci,et al. Optimal BBU Placement for 5G C-RAN Deployment Over WDM Aggregation Networks , 2016, Journal of Lightwave Technology.

[5] Depeng Jin,et al. Understanding Mobile Traffic Patterns of Large Scale Cellular Towers in Urban Environment , 2015, Internet Measurement Conference.

[6] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.