Distributed reinforcement learning stable topology generation method based on adaptive boundary

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...

AI Technical Summary

Problems solved by technology

The existing methods are divided into the following aspects: 1.) Predict the stability degree and network topology of the link connection in the network through the mobility characteristics of the node, and predict the trajectory of the node based on the adaptive neuro-fuzzy system to select the link The node transmits, but a large amount of control information generated between nodes in the prediction process causes excessive energy consumption and large computing overhead; 2.) Collect the received signal strength of the node, and perform deep learning training on it to predict the node's Movement, to build a stable link connection according to the movement trajectory, only considering the relative movement characteristics of the nodes in the process of predicting the position can not reflect the changes of the movement characteristics of the nodes in time, and the collected data only use the movement parameters of a certain period can not reflect well The current movement characteristics of the node; 3.) The method of selecting a stable path according to the received signal strength, dividing the link into two types of strong connection and weak connection according to the average value of the received signal strength of the node within a period of time, and setting the threshold to select a certain threshold However, this method does not consider the comprehensive influence of other factors on the link

[0004] In the information collection process of the existing method, when there are many mobile nodes, there will be disadvantages such as network communication blockage, large amount of node calculation, and high energy consumption of nodes. In the path stability determination link, the information cannot be transmitted in time or the node transmission information is lost due to the unsmooth information communication, resulting in the distributed MANET topology not being able to efficiently predict the link stability, or the link prediction can be made but the stability is not Guaranteed, poor reliability, and long method execution time

[0005] The above defects limit the performance of MANET, resulting in increased energy consumption, shortened life cycle and increased network delay, thus affecting the link stability prediction method in MANET Applications

Images