Achievement Exhibition

Optical Access Network (Optical Access Network) refers to the use of optical fiber as a transmission medium to transmit optical signals to user terminal equipment to achieve user access communication. Compared with the traditional copper cable access network, the optical access network has the advantages of high bandwidth and low delay, which can better meet the needs of high-speed broadband access, high-definition video, cloud computing and other applications. The intelligent optical access network aims to realize the automation, intelligent management and optimization of the optical access network by introducing technologies such as artificial intelligence and big data.

During the transmission process, the optical signal will be interfered by the device band limit, nonlinearity and noise, which will lead to the distortion and attenuation of the optical signal. In order to overcome these problems, the optical access network adopts various equalization techniques. In the past ten years, the laboratory has been adhering to the technical route of high-speed direct detection optical access channel equalization, and proposed methods such as optical time domain equalization, optical frequency domain equalization, photoelectric hybrid equalization, and neural network equalization to achieve continuous improvement in single-wavelength access rates. (10Gb/s25Gb/s50Gb/s100Gb/s). By comprehensively comparing the performance and complexity of different equalization algorithms under the same standard system, the equalization algorithm most suitable for high-speed direct detection optical access systems is located. Further use reinforcement learning to automatically optimize the equalizer structure, reduce complexity under the premise of ensuring performance, and finally deploy it in FPGA in real time to achieve low power consumption, high performance and high-speed optical access.

High-speed optical access system based on photoelectric hybrid balance

In order to meet the ever-increasing transmission rate requirements, the team seeks innovations and breakthroughs in the field of intelligent optical access networks, explores cutting-edge coherent point-to-multipoint (P2MP) optical access architectures, and solves the problem of traditional time-division multiplexing optical access networks (TDM-PON) ) uplink signal high-speed burst detection problem. The memory buffer auxiliary training channel is designed. The central office adopts the high-speed coherent detection technology in the field of optical transmission to gather and receive the uplink signals of different users, and the user side adopts the low-cost coherent detection technology to select and receive its own channel. The challenges faced by the current system include wavelength locking on the user side, high-efficiency online mechanism, ODN visualization, and low-cost polarization-independent coherent detection technology.

High-speed optical access system based on photoelectric hybrid balance