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

A wifi offloading method based on q-learning and multi-attribute decision-making

A multi-attribute decision-making and network attribute technology, applied in the field of WiFi offloading based on Q-learning and multi-attribute decision-making, to achieve the effect of suitable decision-making scheme, reducing complexity and improving QoS

Active Publication Date: 2021-11-26
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the scenario considered by this method is static, and the users inside the cell are stationary, which is often not in line with reality

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
  • A wifi offloading method based on q-learning and multi-attribute decision-making
  • A wifi offloading method based on q-learning and multi-attribute decision-making
  • A wifi offloading method based on q-learning and multi-attribute decision-making

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] 1. System model

[0063] The application scenarios of the present invention are as figure 1 As shown, the LTE base station is located at a radius of r cell The center of the cell, there are N in the cell AP WiFi AP points, denoted as AP k ,k∈{1,2,...,N AP}. The cell is covered by an overlapping LTE network and WiFi network, and the user terminal is a multi-mode terminal that can transmit data through the LTE network or the WiFi network. The agent moves in a straight line inside the community, marking the position it passes by as Posi i ,i∈{1,2,...,N p}, where N p Indicates the total number of locations the user has traveled through. Due to the movement of the user terminal, the network environment such as its channel quality and available bandwidth is constantly changing, which will cause changes in the network attributes of the user terminal. The present invention utilizes the Q-learning model, regards the user terminal as an agent, and regards the four networ...

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 WiFi offloading method based on Q-learning and multi-attribute decision-making, which is suitable for mobile user scenarios where LTE networks and WiFi networks coexist. The method uses a Markov model to describe changes in the network environment, and comprehensively considers user throughput, Establish optimization goals for the four network attributes of terminal power consumption, user cost and communication delay, and obtain the internal relationship between each network attribute through AHP (Analytic Hierarchy Process) and TOPSIS (Approximation to Ideal Value Sorting Method) in the multi-attribute decision-making method As well as the reward function, the Q-learning model is used to combine the current network conditions and its own uninstallation history to make an uninstallation decision, and finally obtain the optimal WiFi offloading scheme. The invention can be applied to heterogeneous networks, and has faster processing speed.

Description

technical field [0001] The invention relates to wireless communication technology, in particular to a WiFi unloading method based on Q-learning and multi-attribute decision-making suitable for LTE networks. Background technique [0002] With the proliferation of smart devices, mobile data traffic is growing at an unprecedented rate, a phenomenon known as the data traffic explosion. Due to the development of wireless access technologies, LTE networks can transmit data services at a high rate, and because of the mobility advantages of LTE networks, applications and traffic are gradually migrating from the traditional Internet to wireless networks. According to the Ciscovisual network index forecast, from 2016 to 2021, global mobile data traffic will grow at a compound annual growth rate of 47%, reaching 49 exabytes per month by 2021. In fact, not only the increasing number of smartphones and tablets, but also the emerging Machine-to-Machine (M2M) modules are exacerbating the ...

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): H04W16/22H04W28/02H04W28/08
CPCH04W16/22H04W28/0221H04W28/0236H04W28/08
Inventor 朱琦孙麟
Owner NANJING UNIV OF POSTS & TELECOMM