Distributed reinforcement learning stable topology generation method based on adaptive boundary

A technology of reinforcement learning and topology generation, applied in the field of communication, can solve problems such as long execution time, no consideration of the comprehensive impact of links, network communication congestion, etc., to improve network communication quality, enhance link connection time, and avoid network overhead. Effect

A technology of reinforcement learning and topology generation, applied in the field of communication, can solve problems such as long execution time, no consideration of the comprehensive impact of links, network communication congestion, etc., to improve network communication quality, enhance link connection time, and avoid network overhead. Effect

CN110753384AActive Publication Date: 2020-02-04XIAN UNIV OF POSTS & TELECOMM
5 Cites 6 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Distributed reinforcement learning stable topology generation method based on adaptive boundary
  • Distributed reinforcement learning stable topology generation method based on adaptive boundary
  • Distributed reinforcement learning stable topology generation method based on adaptive boundary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] The mobile ad hoc network plays an important role in the communication network without infrastructure. The network has no infrastructure support. Each mobile node has both router and host functions, and can form any network topology through wireless connection. Mobile ad hoc networks have broad application prospects in military communications, mobile networks, connecting personal area networks, emergency services and disaster recovery, and wireless sensor networks. Therefore, the mobile ad hoc network has also become one of the current research hotspots. The mobility of nodes in the mobile ad hoc network causes the network topology formed by the entire wireless channel to change at any time. In order to effectively reduce the impact of dynamic topology changes, the existing methods use the mobility of nodes to predict the link connection in the network. The degree of stability and network topology to reduce the impact of dynamic topology changes. However, the existing ...

Embodiment 2

[0055] The distributed reinforcement learning stable topology generation method based on adaptive boundaries is the same as that in Embodiment 1, and the reinforcement learning method described in step 4 of the present invention, the specific implementation process includes the following steps:

[0056] Step 4.1 Determine the overall structure of the reinforcement learning method: In the interval [a,b], each node in the mobile ad hoc network is regarded as an agent agent, and the dynamic changes of MANET can be regarded as a distributed multi-agent collaborative system . For each distributed agent Agent, it is assumed that its environment state set is S, the action set is A, and the reward function is The action selection strategy is π(s i ,a j ).

[0057] The present invention builds a reinforcement learning model in the mobile self-organizing network, regards the network as a multi-agent cooperative system, effectively combines the scene of the mobile self-organizing net...

Embodiment 3

[0079] The distributed reinforcement learning stable topology generation method based on adaptive boundaries is the same as that in Embodiment 1-2, and the adaptive interval boundary update formula in step 6 of the present invention is as follows:

[0080]

[0081] In the formula: a is the upper boundary of the interval; b is the lower boundary of the interval; RSSI is the received signal strength indicator value of the neighbor node; s' is the actual connection variable state of the node and the neighbor node at the next moment; For the prediction of the connection variable state between the node and the neighbor node at the next moment; in the present invention, adaptive_rate is set as the proportional coefficient of the adaptive boundary adjustment, that is, the ratio of the connection state prediction error times and the total number of predictions at the next transmission moment predicted by the current node . like When a0.1, adjust the adaptive boundary a=RSSI; if ...

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 distributed reinforcement learning stable topology generation method based on an adaptive boundary, and solves the problems of poor link node connection continuity and stability in routing. The method comprises the following steps of: constructing a node dynamic topology in the mobile ad hoc network; dividing an adaptive reinforcement learning interval and initializing aQ value table; processing the received signal intensity values by sections; performing reinforcement learning in the adaptive interval, updating the Q value by using an adaptive reward function, and judging the stability of the connection state; judging a direct decision interval state; self-adaptively updating the boundary of the self-adaptive interval; and generating a distributed adaptive stable connection topology. According to the method, the received signal strength value is combined with reinforcement learning, adaptive interval boundary updating is combined with adaptive reward function updating, a stable topology link in the dynamic topology change process is accurately achieved, node energy consumption is reduced, large network expenditure is avoided, the learning rate is high, and complexity is low. The method is used for mobile ad hoc network distributed topology generation.

Description

technical field [0001] The invention belongs to the field of communication technology, and relates to stable topology generation of mobile ad hoc networks, in particular to a self-adaptive boundary-based distributed reinforcement learning stable topology generation method for mobile ad hoc networks, which is used in mobile ad hoc distributed networks. Background technique [0002] As a special wireless mobile network, mobile ad hoc networks (MANET) are widely used in civilian applications due to the characteristics of no need to set up network facilities, fast deployment, free movement of network nodes and ability to communicate with each other in any way. and modern military communications. Mobile ad hoc network is a comprehensive technology combining multiple disciplines. How to build a safe, stable and reliable mobile ad hoc network is an aspect to be solved in the current communication field. The impact of mobile nodes on building a stable topology in mobile ad hoc netw...

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
04 Feb 2020
Publication
CN110753384A
IPC
H04W40/24; H04W52/02; H04W84/18
CPC
H04W40/24; H04W52/0212; H04W84/18; Y02D30/70
Inventors
黄庆东; 石斌宇