Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Femtocell power control method based on q-learning

A femtocell and power control technology, applied in power management, wireless communication, electrical components, etc., to achieve the effect of solving excessive energy consumption

Active Publication Date: 2021-07-16
CHONGQING UNIV OF POSTS & TELECOMM
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problem of excessive energy consumption in heterogeneous cellular networks, this method takes the total energy efficiency of femtocells as the optimization goal, and proposes to use the Q-learning algorithm to control the transmit power of user terminals to reduce system energy consumption.

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
  • Femtocell power control method based on q-learning
  • Femtocell power control method based on q-learning
  • Femtocell power control method based on q-learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] like figure 1 As shown, this embodiment adopts a heterogeneous cellular network model. The system consists of a macro-cell and multiple femto cells. Users share the same spectrum bandwidth W. When users communicate with base stations, they will Interference from users in the same cell (intra-cell interference) and interference from users in other cells (inter-cell interference). The present invention studies the energy efficiency optimization problem of femto cells, and defines the user throughput per unit power as the user energy efficiency η b,μ , define the sum of user energy efficiency in the femtocell as the cell energy efficiency η b .

[0042]

[0043]

[0044] The present invention introduces the minimum received signal signal-to-interference-noise ratio SINR under the consideration of intra-cell and inter-cell interference b,μ min and the user's maximum transmit power p b,μ max As a constraint condition, with the energy efficiency of the community a...

Embodiment 2

[0055] like image 3 As shown, the present invention updates the Q function according to the incremental summation expression of the Q function, and the expression is specifically in, Indicates that the control entity is in network state s at time slot t+1 b Select transmit power action a b The state-action value function of ; Indicates that the controlling entity is in network state s b Take transmit power action a b System energy efficiency value after return; s' b Indicates that the controlling entity is in network state s b Select transmit power action a b , the new state in which it is located; a' b Indicates the network state s' b The corresponding transmit power action below, α represents the learning efficiency, and γ represents the discount reward factor.

Embodiment 3

[0057] In this embodiment, on the basis of the foregoing embodiments, the detailed steps for implementing the transmit power control of the user terminal in this embodiment are as follows:

[0058] Step 1 Set the channel model (bandwidth, gain, etc.), and SINR b,μ min , p b,μ max, γ, α and other initial information; determine the transmit power level of the femto cell user terminal (that is, determine the agent’s action space A b ); Set the total execution steps as T;

[0059] As an optional manner, in the present invention, α=0.1, γ=0.9, and T=1000 are set.

[0060] Step 2 takes the transmit power level of the user terminal as a sample of the transmit power vector (that is, the action of the agent, hereinafter referred to as action), the user terminal sends a signal to the base station, and the base station measures the uplink interference and signal interference corresponding to each transmit power vector according to the received signal A vector of noise ratio coeffici...

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 present invention provides a femtocell power control method based on Q-learning, which belongs to the field of heterogeneous cellular networks of mobile communication technology; the method includes, according to the heterogeneous cellular network model, while considering inter-cell interference and intra-cell interference, Establish an energy efficiency optimization model with the minimum received signal SINR and maximum user transmit power as constraints, and the total energy efficiency of the femtocell as the optimization goal; according to the Q-learning algorithm, according to the energy efficiency optimization model, define the state space, action space, Reward function; by updating the state-action value function, the optimal power allocation strategy is obtained. Compared with the traditional power control algorithm, the present invention can effectively control the transmission power of the user terminal in the femto cell without knowing the channel state information, thereby reducing energy consumption and improving the energy efficiency of the system.

Description

technical field [0001] The invention belongs to the field of heterogeneous cellular networks of mobile communication technology, and relates to an uplink power control method in a femtocell of a heterogeneous cellular network, in particular to a femtocell power control method based on Q-learning. Background technique [0002] The rapid development of mobile communications makes wireless networks face dual tasks, that is, on the premise of supporting rapid business growth, it is necessary to further reduce system energy consumption. Current heterogeneous cellular networks are generally composed of outdoor deployed macro base stations and indoor deployed home base stations. Outdoor macro base stations mainly use existing cellular network base stations. A home base station is a small base station with short-distance transmission. It is deployed within the coverage of a macro base station. It can increase indoor coverage, provide users with high-speed mobile services, and impro...

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 Patents(China)
IPC IPC(8): H04W24/02H04W52/14H04W52/24
Inventor 李云唐英刘涵霄
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com