Deep Neural Network Based Dynamic Resource Reallocation of BBU Pools in 5G C-RAN ROADM Networks
Weiyang Mo, Craig Gutterman, Yao Li, Gil Zussman, Daniel C. Kilper · Optical Fiber Communication Conference · 2018
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.