Medium access control method for underwater acoustic network with variable number of nodes based on q-learning

Abstract

The invention discloses a Q-learning-based medium access control method for an underwater acoustic network with a variable number of nodes, involving the underwater acoustic network. Divide the transmission process of the sink node collecting the perceived data of the underwater acoustic sensor nodes into several time slots, use the Q learning algorithm, combine the feedback signal of the sink node, the change of the number of sensor nodes, and set the reward mechanism reasonably, aiming at a Q matrix The entire row (that is, the sub-matrix) is designed for the overall reward sub-matrix instead of updating the Q matrix element by element, and the time slots are reasonably allocated to each sensor node, so that the data will not be affected by other sensor nodes during transmission and avoid aggregation Node data collection conflict. The method proposed in the present invention has the characteristics of fast learning speed, high throughput, energy saving, and strong anti-interference ability, and can solve the problem of time slot redundancy when nodes are reduced or time slots when nodes are increased caused by node death or position drift Insufficient problems, to ensure the success rate of underwater acoustic data transmission and high throughput of underwater acoustic network.

Description

technical field [0001] The invention relates to an underwater acoustic network, in particular to a Q-learning-based medium access control method for an underwater acoustic network with a variable number of nodes. Background technique [0002] In recent years, the ocean, which occupies 71% of the earth's surface area, has increasingly become the focus of world attention, both in terms of military and civilian use. As an important part of the marine Internet of Things, the underwater acoustic network has gradually become one of the important research hotspots. [0003] The underwater acoustic network is composed of a large number of battery-powered underwater acoustic sensor nodes. However, in the marine environment, it is difficult and costly to replace the batteries of the nodes, and the propagation time of the underwater acoustic channel is prolonged, the channel capacity is small, and the reliability is low. This requires that the data transmission of the underwater acous...

AI Technical Summary

Problems solved by technology

At present, in the research on the combination of Q-learning and medium access control protocols in underwater acoustic networks, how to optimize the design of Q-learning to ensure that the underwater acoustic network maintains high throughput and fast Method for learning speed and strong robustness

Images