论文信息 - Deep Reinforcement Learning Based Policy for Power Efficient Dynamic Subcarrier Assignment in OFDMA-PONs

Deep Reinforcement Learning Based Policy for Power Efficient Dynamic Subcarrier Assignment in OFDMA-PONs

The paper proposes a deep reinforcement learning (DRL) based policy for power efficient dynamic subcarrier assignment in OFDMA-PONs. The simulation results show it can reaches the near-optimal traffic delay with a significant power saving.

[1] Weisheng Hu,et al. Power efficient dynamic bandwidth allocation algorithm in OFDMA-PONs , 2013, IEEE/OSA Journal of Optical Communications and Networking.

[2] Lena Wosinska,et al. A Slice Admission Policy Based on Reinforcement Learning for a 5G Flexible RAN , 2018, 2018 European Conference on Optical Communication (ECOC).

[3] Lei Guo,et al. Joint resource allocation and software- based reconfiguration for energy- efficient OFDMA-PONs , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[4] Srikanth Kandula,et al. Resource Management with Deep Reinforcement Learning , 2016, HotNets.

[5] Yuefeng Ji,et al. Deep Reinforcement Learning for BBU Placement and Routing in C-RAN , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).