Power communication network utility maximization resource allocation policy generation method based on Q-learning

A technology for power communication network and resource allocation, which is applied in the field of resource allocation strategy generation of power communication network utility maximization to achieve high utility value, meet resource requirements, and improve satisfaction.

Active Publication Date: 2018-05-29
STATE GRID ANHUI ELECTRIC POWER CO LTD +1
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing research has not solved the problem of how to meet more business needs and improve user satisfaction.

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
  • Power communication network utility maximization resource allocation policy generation method based on Q-learning
  • Power communication network utility maximization resource allocation policy generation method based on Q-learning
  • Power communication network utility maximization resource allocation policy generation method based on Q-learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] A preferred embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0041] In the solution of the present invention, in order to meet as many business demands as possible on the basis of improving the resource utilization rate of the power communication network, the present invention provides a resource allocation strategy generation based on Q-learning for maximizing the utility of the power communication network methods such as figure 1 shown, including the following steps:

[0042] 101) Build a power communication network resource management model, which includes three parts: resource management simulation platform, power communication network infrastructure, and power communication services.

[0043] The power communication network resource management model proposed by the present invention is as follows: figure 2 As shown, the model transforms the resource allocation problem into a game process consist...

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 power communication network utility maximization resource allocation policy generation method based on Q-learning. The method comprises the following steps that a power communication network resource management model is established, wherein the power communication network resource management model comprises a resource management simulation platform, power communication network infrastructure and power communication business; the resource management simulation platform obtains information of the power communication network infrastructure; the resource management simulation platform obtains information of the power communication business; and the resource management simulation platform generates a resource allocation policy of power communication business based on the Q-learning. According to the method provided by the invention, a relatively fast convergence rate is achieved. Through comparison with a static resource allocation algorithm and a dynamic resource allocation algorithm, it proves that according to the method provided by the invention, under the condition of ensuring a relatively high resource utilization rate, power business obtains a relativelyhigh utility value, resource demands of relatively much business are satisfied, and the degree of satisfaction of a user is improved.

Description

technical field [0001] The invention relates to the technical field of power communication network resource allocation, in particular to a Q-learning-based method for generating resource allocation strategies for maximizing power communication network utility. Background technique [0002] With the rapid development of smart grid business, the resource demand for power communication network is gradually increasing. Network virtualization technology is the key technology of current network transformation, and it has great advantages in QoS guarantee. Under the network virtualization environment, the power communication network includes power communication network infrastructure (PTNI, Power Telecommunication Network Infrastructure) and power communication business (PCB, Power Communication Business), in which PTNI creates and manages the basic network, including computing nodes and link resources and other physical resources, while PCB provides users with differentiated serv...

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): H04L12/24H04L29/08
CPCH04L41/14H04L41/5019H04L67/61
Inventor 谢小军卓文合于浩吴非金鑫王伟
Owner STATE GRID ANHUI ELECTRIC POWER CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products