-
公开(公告)号：US12153954B2
公开(公告)日：2024-11-26
申请号：US17524335
申请日：2021-11-11
Inventor： Liang Liu , Xiaolong Zheng , Huadong Ma , Zihui Luo , Chengling Jiang
Abstract: The embodiments of the present invention provide a dynamic production scheduling method, apparatus and electronic device based on deep reinforcement learning, which relate to the technical field of Industrial Internet of Things, and can reduce the overall processing time of jobs on the basis of not exceeding the processing capacity of production device. The embodiments of the present invention includes: acquiring static characteristics, dynamic characteristics of each of jobs and system dynamic characteristics, inputting the static characteristics, dynamic characteristics of each of jobs to be scheduled and system dynamic characteristics into a scheduling model to obtain a job execution sequence or batch execution sequence of the jobs in each production stage, wherein, the static characteristics of the job include an amount of tasks and time required for completion, the dynamic characteristics of the job include reception moment, and the system dynamic characteristics include a remaining amount of tasks that can be performed by the device in each production stage. The scheduling model is a model obtained after training a first actor network based on static characteristics and dynamic characteristics of a sample job, system dynamic characteristics, and a first critic network.
-
2.发明申请公开(公告)号：US20220124179A1
公开(公告)日：2022-04-21
申请号：US17505175
申请日：2021-10-19
Inventor： Xiaolong Zheng , Dan Xia , Liang Liu , Huadong Ma
Abstract: The embodiments of the present invention provide a method, apparatus for cross-protocol opportunistic routing, an electronic device, and a storage medium, the method includes: when there is a first data packet in a low-power wireless network, simulating the first data packet to generate a second data packet including to-be-transmitted data in the first data packet; obtaining identification information of a destination node in the first data packet, and selecting a low-power node with the lowest delay to the destination node in the low-power wireless network, except the first low-power node, as a forwarding low-power node based on the identification information of the destination node; sending the generated second data packet to the forwarding low-power node, so that the forwarding low-power node forwards the to-be-transmitted data to the destination node. By using high-power nodes, when there is a data packet in the low-power node, the data packet can be sent in time without being transmitted in a reserved idle channel, thereby reducing the transmission delay of the data packet from the source node to the destination node in the low-power wireless network.
-
公开(公告)号：US20220179689A1
公开(公告)日：2022-06-09
申请号：US17524335
申请日：2021-11-11
Inventor： Liang Liu , Xiaolong Zheng , Huadong Ma , Zihui Luo , Chengling Jiang
Abstract: The embodiments of the present invention provide a dynamic production scheduling method, apparatus and electronic device based on deep reinforcement learning, which relate to the technical field of Industrial Internet of Things, and can reduce the overall processing time of jobs on the basis of not exceeding the processing capacity of production device. The embodiments of the present invention includes: acquiring static characteristics, dynamic characteristics of each of jobs and system dynamic characteristics, inputting the static characteristics, dynamic characteristics of each of jobs to be scheduled and system dynamic characteristics into a scheduling model to obtain a job execution sequence or batch execution sequence of the jobs in each production stage, wherein, the static characteristics of the job include an amount of tasks and time required for completion, the dynamic characteristics of the job include reception moment, and the system dynamic characteristics include a remaining amount of tasks that can be performed by the device in each production stage. The scheduling model is a model obtained after training a first actor network based on static characteristics and dynamic characteristics of a sample job, system dynamic characteristics, and a first critic network.
-
4.发明授权公开(公告)号：US11683398B2
公开(公告)日：2023-06-20
申请号：US17505175
申请日：2021-10-19
Inventor： Xiaolong Zheng , Dan Xia , Liang Liu , Huadong Ma
Abstract: The embodiments of the present invention provide a method, apparatus for cross-protocol opportunistic routing, an electronic device, and a storage medium, the method includes: when there is a first data packet in a low-power wireless network, simulating the first data packet to generate a second data packet including to-be-transmitted data in the first data packet; obtaining identification information of a destination node in the first data packet, and selecting a low-power node with the lowest delay to the destination node in the low-power wireless network, except the first low-power node, as a forwarding low-power node based on the identification information of the destination node; sending the generated second data packet to the forwarding low-power node, so that the forwarding low-power node forwards the to-be-transmitted data to the destination node. By using high-power nodes, when there is a data packet in the low-power node, the data packet can be sent in time without being transmitted in a reserved idle channel, thereby reducing the transmission delay of the data packet from the source node to the destination node in the low-power wireless network.
-
-
-
Search Results
4
records
(took 0.014 seconds)
