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

Car networking load balanced access method based on history reinforced learning

A technology of reinforcement learning and load balancing, which is applied in access restriction, network traffic/resource management, electrical components, etc., can solve problems such as network load balancing, and achieve the effect of improving service speed and good network service experience

Active Publication Date: 2017-12-22
DONGHUA UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is how to ensure the load balance of the network when the vehicle accesses the base station in the case of heterogeneous base stations, unknown and complex Internet of Vehicles environment, and high dynamic changes of vehicles

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
  • Car networking load balanced access method based on history reinforced learning
  • Car networking load balanced access method based on history reinforced learning
  • Car networking load balanced access method based on history reinforced learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Below in conjunction with specific embodiment, further illustrate the present invention.

[0038] Reinforcement learning focuses on how an agent, the base station, can take a sequence of actions in an environment so as to maximize cumulative rewards. Trial and error and delayed rewards are two distinctive features of reinforcement learning. By continuously interacting with the unknown environment, an agent should know what action to take in what state.

[0039] The load-balancing access method of the Internet of Vehicles based on historical reinforcement learning provided in this embodiment is composed of two parts: the initial reinforcement learning module and the history reinforcement learning module, such as figure 1 shown.

[0040] exist figure 1 In the system architecture described above, firstly, the access base station allocation mode of the vehicle is obtained through the initial reinforcement learning module. These access base station allocation modes are c...

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 provides a car networking load balanced access method based on history reinforced learning. The method comprises the following steps: first of all, obtaining an accessed base station distribution mode of a vehicle via an initial reinforced learning module, and continuously accumulating to an access mode accumulation library; through learning accumulation, enabling a history reinforced learning module to replace the initial reinforced learning module to continuously reside and operate in a system, and when a base station encounters a network change again, invoking, by the history reinforced learning module, a history record in the access mode accumulation library to self-adaptively learn a new vehicle access distribution mode; and recording to form a dynamically changed operating loop of a self-adaptive processing network, thereby guaranteeing that a network load accessed by the vehicle is balanced in a dynamically changed car networking environment. According to the method, a potential regularity of space-time distribution of a traffic flow is utilized, so in an iterative feedback with an environment, the vehicle access space-time experience with history load balance is learnt and used; and thus, in the dynamic environment, a vehicle accessed base station distribution scheme that can guarantee the network load balance is obtained continuously.

Description

technical field [0001] The invention relates to the technical field of network load balancing of the Internet of Vehicles, in particular to a load balancing access method of the Internet of Vehicles based on history reinforcement learning. Background technique [0002] With the development of the Internet of Vehicles, more and more vehicles need to access heterogeneous base stations in the network. These heterogeneous base stations are different in transmission power, physical size and construction cost. In a city, these access requirements are very different. For example, in dense traffic areas, the demand for vehicle access to base stations is much greater than that in sparse traffic areas. Under the traditional maximum SINR (Signal to Interference plus Noise Ratio) scheme, base stations with stronger power can attract more vehicles to access. A strong base station receives a strong downlink signal, which causes the base station with higher power to be overloaded, while t...

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): H04W28/08H04W48/06H04W48/10H04L29/08
CPCH04L67/12H04W48/06H04W48/10H04W28/082
Inventor 蒋昌俊李重李德敏任佳杰齐诚嗣
Owner DONGHUA UNIV
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