公开(公告)号：US20240015079A1

公开(公告)日：2024-01-11

申请号：US18359862

申请日：2023-07-26

Applicant: ZHEJIANG LAB

Inventor： Congqi SHEN ,  Huifeng ZHANG ,  Shaofeng YAO ,  Qi XU ,  Ruyun ZHANG

IPC: H04L41/16 ,  H04L41/40 ,  G06N20/00

CPC classification number: H04L41/16 ,  H04L41/40 ,  G06N20/00

Abstract: The present disclosure discloses a reinforcement learning agent training method, modal bandwidth resource scheduling method and apparatus. The reinforcement learning agent training method utilizes a reinforcement learning agent to continuously interact with a network environment in a polymorphic smart network to obtain the latest global network characteristics and output updated actions. By adjusting the bandwidth occupied by modals, a reward value is set to determine an optimization target for the agent, the scheduling of modals is realized, and the rational use of polymorphic smart network resources is guaranteed. The trained reinforcement learning agent is applied to the modal bandwidth resource scheduling method, and can adapt to networks with different characteristics, and thus can be used for intelligent management and control of polymorphic smart networks and has good adaptability and scheduling performance.

公开(公告)号：US20230047278A1

公开(公告)日：2023-02-16

申请号：US17966917

申请日：2022-10-17

Applicant: ZHEJIANG LAB

Inventor： Congqi SHEN ,  Shaofeng YAO ,  Zhongxia PAN ,  Hanguang LUO ,  Tao ZOU

IPC: H04L45/76 ,  H04L45/745 ,  H04L45/00

Abstract: A geographical identification forwarding method for area-oriented addressing. The geographic location information is used as a transmission identification, and the communication process based on the geographical identification is realized by constructing the SDN-based geographical identification transmission architecture. In this method, a geographical identification is used instead of a traditional IP identification for network transmission, which effectively alleviates the problem of narrow waist of IP single bearing in the current network. At the same time, through a flow table decomposition design, the flow table size of the switch is effectively controlled. The method provided by the present invention can be extended to a plurality of geographical identification areas to realize large-area real-time cross-domain transmission. The method is simple to operate, easy to realize and high in real-time; the method has a wide application range, and can be used to build new networks and improve network performance.