Cognitive routing method based on MIMO link

Abstract

The invention discloses a cognitive routing method based on MIMO link, which mainly solves the problems of low throughout and high overhead in prior art. The cognitive routing method includes that: the cognition process is realized through Q learning algorithm for learning and predicating the network states; the route lifetime and hello cycle are set according to the inducted network states; the MIMO technology is used to realize multiple link types in the network, including multiplexing, diversity and group multiplexing links; spread factor table of each node in the network is established, and the table is queried to obtain the link type between nodes; the diversity link is adopted to transmit hello and RREQ packets, the table is queried to obtain the link type of links for transmitting data and RREP packets; the spread factor table is updated to continuously update the link types among nodes; and the route tables are updated to establish optimum route between the source node and thedestination node. The invention guarantees the QoS demands for services, optimizes the network performance and can regulate in self-adapting manner according to node density and network state changes.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, relates to a cognitive routing method for MIMO links, and is used in a cognitive wireless network. Background technique [0002] Cognitive routing can perceive the current state of the network, and through appropriate learning mechanisms, such as reinforcement learning, make correct plans, decisions, and actions based on the perceived network state. In the process of cognition, reinforcement learning is used as its learning mechanism, which is an unsupervised learning method that enables agents to use environmental rewards to find and execute optimal behaviors when the environmental model is unknown. A Q-learning algorithm is proposed in the document "Cognitive Network Management with Reinforcement Learning for Wireless Mesh Networks". In this algorithm, each node predicts the state of the wireless network, and reconfigures the lifetime and hello period of this route according to ...

AI Technical Summary

Problems solved by technology

However, the routing lifetime and hello period of these two routing protocols are fixed and cannot be adjusted adaptively with changes in the network status, which will lead to increased end-to-end delay, decreased throughput, and increased network overhead.

Images