An ultra-highly precise and long-term stable frequency transmission system over 120 km commercial fiber link has been proposed and experimentally demonstrated. This system is based on digital output compensation techn...An ultra-highly precise and long-term stable frequency transmission system over 120 km commercial fiber link has been proposed and experimentally demonstrated. This system is based on digital output compensation technique to suppress phase fluctuations during the frequency transmission process. A mode-locked erbium-doped fiber laser driven by a hydrogen maser serves as an optical transmitter. Moreover, a dense wavelength division multiplexing system is able to separate forward and backward signals with reflection effect excluded. The ultimate fractional frequency instabilities for the long-distance frequency distributed system are up to 3.14×10^(-15) at 1 s and 2.96×10^(-19) at 10 000 s, respectively.展开更多
Driven by advancements in artificial intelligence,end-to-end learning has become a key method for system optimization in various fields,including communications.However,applying learning algorithms such as backpropaga...Driven by advancements in artificial intelligence,end-to-end learning has become a key method for system optimization in various fields,including communications.However,applying learning algorithms such as backpropagation directly to communication systems is challenging due to their non-differentiable nature.Existing methods typically require developing a precise differentiable digital model of the physical system,which is computationally complex and can cause significant performance loss after deployment.In response,we propose a novel end-to-end learning framework called physics-guided learning.展开更多
基金supported by the National Natural Science Foundation of China(Nos.61571244 and 61501262)the Science and Technology Project of Tianjin(No.16YFZCSF00540)the Natural Science Foundation of Tianjin(No.15JCYBJC51600)
文摘An ultra-highly precise and long-term stable frequency transmission system over 120 km commercial fiber link has been proposed and experimentally demonstrated. This system is based on digital output compensation technique to suppress phase fluctuations during the frequency transmission process. A mode-locked erbium-doped fiber laser driven by a hydrogen maser serves as an optical transmitter. Moreover, a dense wavelength division multiplexing system is able to separate forward and backward signals with reflection effect excluded. The ultimate fractional frequency instabilities for the long-distance frequency distributed system are up to 3.14×10^(-15) at 1 s and 2.96×10^(-19) at 10 000 s, respectively.
基金RGC(ECS 24203724,YCRG C4004-24Y,YCRG C1002-22Y)NSFC(62405258)+2 种基金Innovation and Technology Fund(ITS/237/22)Innovation and TechnologyFund(ITS/226/21FP)NSFC/RGC Joint Research Scheme(N_CUHK444/22).
文摘Driven by advancements in artificial intelligence,end-to-end learning has become a key method for system optimization in various fields,including communications.However,applying learning algorithms such as backpropagation directly to communication systems is challenging due to their non-differentiable nature.Existing methods typically require developing a precise differentiable digital model of the physical system,which is computationally complex and can cause significant performance loss after deployment.In response,we propose a novel end-to-end learning framework called physics-guided learning.
