A Medium Access Control Method for Ad Hoc Networks Based on Reinforcement Learning

Abstract

The invention discloses an ad hoc network medium access control method based on enhanced learning, which is applied in the field of wireless networks, and aims at the problem of multi-slot selection of distributed network nodes in the dynamic TDMA medium access control method that is generally not considered in the prior art; the present invention The frame structure design adopts the time slot interleaving scheme, which makes the medium access control method more relaxed in the packet response delay performance requirements of the hardware device; at the same time, the multi-time slot reservation mechanism is adopted, so that the network node only needs to send a control frame once per cycle and reserve For subsequent information time slots of multiple cycles, the interaction process is simple and easy to implement, and the control overhead is small; and the multi-slot selection algorithm based on reinforcement learning adaptively adjusts the selection probability of each time slot to generate a more optimal time slot selection strategy, thereby reducing time Slot contention conflicts, improve slot allocation efficiency, and further optimize the success rate of contention, transmission bandwidth, transmission delay, packet loss rate and other performance of the media access control method.

Description

technical field [0001] The invention belongs to the field of wireless networks, in particular to a multi-slot selection technology based on reinforcement learning. Background technique [0002] Self-organizing (Ad hoc) network is a multi-hop communication system that can be established and maintained by itself without relying on fixed communication facilities in a wireless network environment. It has strong robustness and invulnerability. Self-organizing networks are very suitable for wireless network scenarios such as drone communication, car networking scenarios, and environmental monitoring. [0003] MAC (Medium Access Control) medium access control method is the key responsible for nodes sharing and accessing limited channel resources, and its performance directly affects the overall performance of the network. Usually, compared with the traditional stochastic contention media access control method, the media access control method based on TDMA (Time Division Multiple A...

AI Technical Summary

Problems solved by technology

The factors affecting network performance are relatively complex. The above algorithms generally do not consider the problem of multi-slot selection of distributed network nodes in the dynamic TDMA medium access control method. Applying enhanced learning technology to the scene of multi-slot selection of distributed network nodes can make the selection of time slots The algorithm comprehensively considers environmental factors, and learns adaptively from them to a more optimal multi-slot selection strategy. The multi-slot selection method based on reinforcement learning has important research value and challenges

Images