Unlock instant, AI-driven research and patent intelligence for your innovation.

Downlink wireless resource scheduling method and device supporting AI engine

A wireless resource scheduling and wireless resource technology, applied in the field of downlink wireless resource scheduling that supports AI engines, can solve problems such as waste of resources, large delays, etc., achieve smooth operation, reduce delays, and avoid the effects of transmission and confirmation processes

Active Publication Date: 2021-08-27
UNIV OF SCI & TECH BEIJING
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a downlink wireless resource scheduling method and device supporting an AI engine, so as to solve the technical problems of the prior art that would cause a huge time delay and a lot of waste of resources in resource scheduling

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Downlink wireless resource scheduling method and device supporting AI engine
  • Downlink wireless resource scheduling method and device supporting AI engine
  • Downlink wireless resource scheduling method and device supporting AI engine

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0037] This embodiment provides a downlink wireless resource scheduling method for the open source OpenAirInterface (OAI) system that supports the AI ​​engine for the problem of downlink wireless resource scheduling allocation, that is, it is configured under the OAI engine, and the DDQN algorithm is designed for training. The encapsulation AI model applicable to this engine can configure multiple UEs for resource allocation at most.

[0038] The execution flow of this method is as follows figure 1 shown, including the following steps:

[0039] S1, build the AI ​​engine and establish the socket connection between the AI ​​engine and the OAI system, configure the AI ​​engine in the OAI operating environment, and use the AI ​​engine to replace the polling algorithm and fairness adopted by the MAC layer LTE for resource scheduling in the OAI system The round-robin algorithm realizes the takeover of the downlink wireless resource scheduling process;

[0040] It should be noted t...

no. 2 example

[0087] This embodiment provides a downlink radio resource scheduling device supporting an AI engine, the device comprising:

[0088] The AI ​​engine building module is used to build the AI ​​engine, establish a socket connection between the AI ​​engine and the OAI system, configure the AI ​​engine into the OAI operating environment, and use the AI ​​engine to replace the resource scheduling method used by the MAC layer LTE in the OAI system. polling algorithm and fair round-robin algorithm to realize the takeover of the downlink wireless resource scheduling process;

[0089] The scheduling information sending module is used to send the scheduling information to the AI ​​engine through the Socket during the process of OAI scheduling resources;

[0090] The resource allocation and allocation result sending module is used to use the AI ​​engine to complete resource allocation according to the scheduling information, and return the resource allocation result to OAI.

[0091] The ...

no. 3 example

[0093] This embodiment provides an electronic device, which includes a processor and a memory; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor, so as to implement the method of the first embodiment.

[0094] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) and one or more memories, wherein at least one instruction is stored in the memory, so The above instruction is loaded by the processor and executes the above method.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a downlink wireless resource scheduling method and device supporting an AI engine, and the method comprises the steps: constructing the AI engine, building a socket connection between the AI engine and an OAI system, configuring the AI engine to an OAI operation environment, replacing a polling algorithm and a fair round-robin algorithm which are adopted by the LTE of an MAC layer in the OAI system for resource scheduling by the AI engine, realizing takeover of a downlink wireless resource scheduling process; in the process that the OAI schedules the resources, scheduling information is sent to the AI engine through the Socket; and completing resource allocation according to the scheduling information by using the AI engine, and returning a resource allocation result to the OAI. According to the invention, reasonable scheduling and allocation of wireless resources are realized by using the deep reinforcement learning technology, and the system performance is improved.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a downlink wireless resource scheduling method and device supporting an AI engine. Background technique [0002] In the field of wireless transmission, downlink resources are transmitted from the base station to the user end. During the interactive transmission of downlink control resources in the existing LTE system, a large amount of redundant information and more processing delays will be generated. In the LTE transmission process In the process, multiple confirmations and transmissions of information are required, and the final transmission will only be carried out through layer-by-layer feedback of the system. In this process, a great delay and a lot of waste of resources will be generated. Contents of the invention [0003] The present invention provides a downlink wireless resource scheduling method and device supporting an AI engine, so as to sol...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04W72/04H04L29/06G06N20/00
CPCH04L69/162G06N20/00H04W72/53H04W72/20H04L47/6225G06N3/092G06N3/045Y02D30/70H04W72/535H04W72/23
Inventor 张海君管婉青王东卢同威
Owner UNIV OF SCI & TECH BEIJING