MAC protocol for realizing time domain interference alignment based on deep reinforcement learning in underwater acoustic network

Abstract

The invention discloses an MAC protocol for realizing time domain interference alignment based on deep reinforcement learning in an underwater acoustic network. The MAC protocol comprises the following steps: constructing a time slot division model; applying a deep reinforcement learning algorithm DQN to an underwater acoustic network MAC protocol, and achieving time domain interference alignment by training the deep reinforcement learning algorithm DQN; and scheduling node transmission by using the trained DQN. Compared with the prior art, the deep reinforcement learning method is adopted to allocate time slots for the nodes, the DQN is used to realize time domain interference alignment, and the trained DQN is used to schedule node transmission; and the DQNSA-MAC aligns interference at a non-destination node, and more interference-free time slots are reserved for transmitting and receiving messages, so that the throughput is improved. Besides, based on the trained DQN, each node can be mapped to a transmission action from a current state, so that the problem of high calculation overhead caused by large state space is effectively solved. In summary, the throughput, the successful transmission rate, the fairness and the like of the underwater acoustic network MAC protocol can be improved.

Description

technical field [0001] The invention relates to the field of wireless sensor network communication transmission, in particular to a MAC protocol for realizing time-domain interference alignment based on deep reinforcement learning in an underwater acoustic network. Background technique [0002] The vast ocean is rich in metals, energy and biological resources. As a key technology for exploring the ocean world, underwater acoustic networks (UANs) are applied in industrial, military and civilian fields, such as resource exploration and development, military intelligence and collection, marine environment and climate research, etc. To turn the idea of ​​underwater acoustic network into reality, it is necessary to effectively solve the problem of Media Access Control Protocol (MAC). [0003] Due to the large transmission delay in underwater acoustic networks, MAC protocols in terrestrial wireless sensor networks cannot be directly applied to UANs. There have been some studies ...

AI Technical Summary

Problems solved by technology

But the complexity of the algorithm increases exponentially with the number of nodes

Therefore, the proposed algorithm is computationally infeasible

Images