Digital twin-enabled self-evolved optical transceiver using deep reinforcement learning

摘要

Due to their high flexibility, programmable optical transceivers (POT) are regarded as one of the key optical components in optical fiber communications, where diverse transceiver freedom degrees can be controlled according to real-time network states. However, the adaptivity of classic POT modeling and controlling is limited to the prior-knowledge-dependent quality of the transmission estimation model or uncomprehensive training dataset, which has great difficulties in enabling adaptive POT modeling and controlling to evolve with time-varied network states. Here, a powerful dynamic modeling technique called digital twin (DT), enabled by the deep reinforcement learning (DRL), is first proposed for the adaptive POT modeling and controlling, to the best of our knowledge. The experimental and simulation results show that the lowest spectrum consumption and minimum latency are both available in the proposed POT, compared with the classic POTs based on neural networks and maximum capability provisioning. We believe that the proposed DT will open a new avenue for the adaptive optical component modeling and controlling for dynamic optical networks. (C) 2020 Optical Society of America