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

Multi-cell cooperative beam forming method based on distributed reinforcement learning

A technology of collaborative beamforming and reinforcement learning, applied in machine learning, diversity/multi-antenna systems, spatial transmit diversity, etc., can solve problems such as increasing overhead, achieve the effect of reducing overhead, lowering overhead, and improving network performance

Pending Publication Date: 2021-10-01
HUNAN GUOTIAN ELECTRONICS TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method requires each base station to know the global channel state information, which greatly increases the overhead of execution

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
  • Multi-cell cooperative beam forming method based on distributed reinforcement learning
  • Multi-cell cooperative beam forming method based on distributed reinforcement learning
  • Multi-cell cooperative beam forming method based on distributed reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention will be further described below in conjunction with the accompanying drawings, but the present invention is not limited in any way. Any transformation or replacement based on the teaching of the present invention belongs to the protection scope of the present invention.

[0060] The present invention is described in further detail below in conjunction with accompanying drawing:

[0061] see figure 1 , consider a multi-cell multiple-input single-output scenario, there are K cells, and each base station is equipped with N t Antennas, each user is equipped with a single antenna. Each base station only serves one user on the same time-frequency resource, and each user will receive useful signals from the serving base station and interference signals from other base stations. The entire cooperative beamforming process is described as figure 2 As shown, the description is as follows:

[0062] First, every M time slots, the base stations exchange cha...

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 multi-cell cooperative beam forming method based on distributed reinforcement learning. The method comprises the following steps: establishing a training DQN with the weight of [theta]j, a target DQN with the weight of [theta]'j and an empty experience pool Mj for a base station j; using random weight to initialize the training DQN; repeating the following steps every M time slots that the base stations interact channel state information from themselves to all users; each base station generates global channel samples of multiple groups of M time slots in the future; each base station takes action randomly and stores corresponding experience in an experience pool Mj of the base station; and each base station carries out network training. Under the condition of extremely low overhead, the performance of the method is superior to that of a greedy scheme and a random scheme, and is close to that of an optimal scheme needing global information.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a multi-cell cooperative beamforming method based on distributed reinforcement learning. Background technique [0002] Traditional mobile communication systems are usually designed with a cellular architecture, which can improve throughput and save energy consumption in cellular scenarios. However, since the cells share the band portion of the spectrum among themselves, this can lead to severe inter-cell interference, impairing system capacity. Multi-cell coordinated beamforming is considered to be one of the key technologies for interference management because it can mitigate inter-cell interference and maximize system capacity by jointly controlling the transmit power and beamforming of adjacent base stations. [0003] In general, the system capacity of a cellular communication system is represented by the sum of the achievable rates of all users, th...

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
IPC IPC(8): H04J11/00H04W16/28H04B7/06H04B7/08G06N20/00
CPCH04J11/005H04W16/28H04B7/0617H04B7/086G06N20/00Y02D30/70
Inventor 高贞贞廖学文吴丹青张金罗伟
Owner HUNAN GUOTIAN ELECTRONICS TECH CO LTD