MAC protocol design method based on multi-objective optimization in underwater acoustic sensor networks

Through multi-objective optimized MAC protocol design, combined with multi-agent reinforcement learning and delayed reward mechanism, the problems of throughput, energy efficiency and resource allocation fairness in underwater acoustic sensing networks are solved, and high throughput and stability are achieved.

CN119172445BActive Publication Date: 2025-09-30HOHAI UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202411433171.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-15
Publication Date
2025-09-30
Estimated Expiration
2044-10-15

AI Technical Summary

Technical Problem

Existing MAC protocols for underwater acoustic sensor networks have difficulty in simultaneously optimizing throughput, energy efficiency, and fairness of resource allocation in underwater communication environments, resulting in high collision rates, low throughput, and unfair resource allocation.

Method used

A MAC protocol design method based on multi-objective optimization is adopted, combined with a centralized training and distributed execution architecture. Through a dual reward mechanism, a multi-agent reinforcement learning model is used to optimize system throughput, energy efficiency, and fairness of resource allocation. A delayed reward mechanism is used to update strategies in complex environments.

Benefits of technology

It significantly improves the system throughput and energy efficiency of the underwater acoustic communication network, solves the problem of unfair resource allocation between nodes, and enhances the stability and adaptability of the network.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a MAC protocol design method based on multi-objective optimization in an underwater acoustic sensor network, and the specific steps are as follows: first, a network model of the underwater acoustic sensor network is established; second, a time slot model is established to convert the propagation delay between the underwater sensor node and the surface AP node into the number of time slots; on this basis, a multi-agent reinforcement learning model is established, and a centralized training and distributed execution architecture is adopted. By adopting a multi-agent reinforcement learning method based on multi-objective optimization, the present invention significantly improves the system throughput and energy efficiency in the underwater acoustic communication network, and effectively solves the problem of unfair resource allocation between nodes. By introducing a delayed reward and priority experience replay mechanism, the agent can accurately update the strategy in an environment with long propagation delay, thereby improving learning efficiency. The present invention not only improves the overall communication efficiency of the network, but also enhances the adaptability and stability of the system in a complex environment with high delay.
Need to check novelty before this filing date? Find Prior Art