Long-life-cycle underwater acoustic sensor network adaptive multi-path routing mechanism

Abstract

The invention provides a long-life-cycle underwater acoustic sensor network adaptive multi-path routing mechanism, which aims at solving the problems of link quality reduction caused by underwater sensor network node mobility, unbalanced network load of each node and the like, the network is modeled into a multi-agent system, each node is used as an agent, and through direct interaction with the environment and information sharing with other agents, environment information is efficiently learned to adapt to dynamic changes of network topology, and the agents select an optimal relay node set which maximizes future rewards in a neighbor node set according to channel advantages and disadvantages to determine an optimal transmission path of a data packet. The network is dynamically switched between a single-path route and a multi-path route to improve the delivery rate of data packets, so that the network overhead is reduced to the greatest extent to improve the energy utilization rate, the packet delivery rate is improved to improve the network robustness, and the network load is balanced to prolong the network life cycle.

Description

technical field [0001] The invention belongs to the technical field of underwater acoustic sensor networks, is a multi-path self-adaptive routing protocol capable of perceiving network channel states and prolonging network life, and involves multi-agent cooperation reinforcement learning and other algorithms. Background technique [0002] In recent years, the underwater acoustic sensor network has made great progress with the continuous expansion of the application field of marine information, and has important applications in marine military affairs, marine environment and meteorological research, and marine resource development. On the one hand, the underwater acoustic sensor network uses underwater acoustic signals as the transmission information medium, which has the characteristics of low bandwidth and large transmission delay, which makes the land sensor network protocol with electromagnetic waves as the medium unable to be directly applied to the underwater acoustic se...

AI Technical Summary

Problems solved by technology

In the underwater optical sensor network routing protocol based on multi-agent reinforcement learning proposed by Xinge Li et al., link quality and node residual energy are considered, which enhances the adaptability of the network dynamic topology and prolongs the network life to a certain extent. However, this method does not take into account the asymmetry of the communication link and the instability of the channel.

Images