Directional antenna neighbor discovery method based on deterministic estimator learning automaton in D2D network

Abstract

The invention discloses a directional antenna neighbor discovery method based on a deterministic estimator learning automaton in a D2D network, and the method enables a neighbor discovery process to be modeled as the deterministic estimator learning automaton, and an estimator carries out the approximate estimation of the reward probability of an action according to the previous feedback condition, and strengthens the action with a higher reward probability estimation value. The directional antenna neighbor discovery algorithm based on the Pursuit algorithm is adopted, the direction of the directional antenna is adjusted by updating the sector probability distribution, and the neighbor discovery efficiency is further improved.

Description

technical field [0001] The invention belongs to the technical field of wireless ad hoc network in the field of wireless communication, in particular to a neighbor node discovery method based on a directional antenna. Background technique [0002] Compared with infrastructure-based wireless networks, D2D networks have flourished in recent years due to their faster network deployment, lower cost, and greater flexibility. Neighbor discovery is the basic process of initializing the D2D network and letting D2D devices know the information of single-hop neighbors. [0003] Currently proposed neighbor node discovery algorithms are mainly divided into two categories: random neighbor discovery algorithms and deterministic neighbor discovery algorithms. In the random neighbor discovery algorithm, the nodes in the network randomly select the node's transceiver mode and the direction that the directional antenna points to. In the deterministic neighbor discovery algorithm, nodes disco...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the existing neighbor discovery method based on learning automata only changes the probability of action selection according to the latest feedback, which causes the performance of neighbor discovery to be affected by randomness, this invention proposes a learning automaton based on deterministic estimator in D2D network In the directional antenna neighbor discovery method, the estimator makes an approximate estimate of the reward probability of the action based on the previous feedback, and strengthens the action with the highest reward probability estimate to improve the neighbor discovery performance

Images