Intelligent routing decision method based on DDPG reinforcement learning algorithm

A technology of reinforcement learning and decision-making methods, applied in the field of computer networks and data center networks, it can solve problems such as poor load balance of equivalent paths, and achieve the effect of improving bandwidth resource utilization, making full use of network bandwidth resources, and improving balance.

Active Publication Date: 2019-12-24
XIDIAN UNIV +1
View PDF5 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose an intelligent routing decision-making m

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
  • Intelligent routing decision method based on DDPG reinforcement learning algorithm
  • Intelligent routing decision method based on DDPG reinforcement learning algorithm
  • Intelligent routing decision method based on DDPG reinforcement learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0034] refer to figure 1 , the implementation steps of the present invention are as follows:

[0035] Step 1), build network topology:

[0036] Construct a network topology G including a server nodes and m switch nodes 0 , a≥2, m≥2, and G 0 Each server node in can be used as a source server node, and other server nodes can be used as the destination node of the node, and each source server node is connected to other destination server nodes through one or more switch nodes to form an equivalent path , so each equivalent path includes one or more switch nodes in addition to the source server node and the destination server node. In this example, a fat-tree topology with 16 server nodes is selected. In this topology, a=16, m =20;

[0037] Step 2), to the network topology G 0 The equivalent path in is numbered:

[0038] (2a) Initi...

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 an intelligent routing decision method based on reinforcement learning, in particular to an intelligent routing decision method based on a DDPG reinforcement learning algorithm.The method aims at designing an intelligent routing decision by utilizing reinforcement learning, balancing an equivalent path flow load and improving the processing capacity of a network for burst flow, an experience decision mechanism based on a sampling probability is adopted, the probability that experience with poorer performance is selected is higher, and the training efficiency of an algorithm is improved. In addition, noise is added into neural network parameters, system exploration is facilitated, and algorithm performance is improved. The method comprises the following steps: 1) constructing a network topology structure; 2) numbering equivalent paths in the network topology structure G0; (3) constructing a routing decision model based on a DDPG reinforcement learning algorithm,(4) initializing a flow demand matrix DM and an equivalent path flow proportion matrix PM, and (5) carrying out iterative training on the routing decision model based on reinforcement learning, and the method can be used for scenes such as a data center network.

Description

technical field [0001] The invention belongs to the technical field of computer networks, and relates to an intelligent routing decision-making method based on reinforcement learning, in particular to an intelligent routing decision-making method based on a DDPG reinforcement learning algorithm, which can be used in fields such as data center networks. Background technique [0002] For the network, the routing decision is the process of determining the specific forwarding path of the data packet in the network. It specifies how the data flow reaches another node from a specified node in the network. The routing decision determines the load balance of the equivalent path in the network. , which is mainly related to the difference in bandwidth utilization of each equivalent path and whether deadlock occurs. The smaller the difference, the worse the load balance of the equivalent path, and the occurrence of deadlock will also lead to the deterioration of the load balance of 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
IPC IPC(8): H04L12/751H04L12/803G06N3/08H04L45/02
CPCH04L45/08H04L47/125G06N3/08
Inventor 顾华玺张瑞卿郭彦涛李健嘉魏雯婷肖哲
Owner XIDIAN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap