Wireless routing optimization method based on attention mechanism and deep reinforcement learning

Abstract

The invention relates to a network routing method, in particular to a wireless routing optimization method based on an attention mechanism and deep reinforcement learning, which comprises the following steps of: acquiring current latest decision model parameters from a server when each node accesses a network; neighbor node information is intercepted, a candidate father node set is constructed based on the candidate father node set, information modeling of m father nodes with the maximum energy is selected from the candidate father node set to serve as graph vectors to serve as input, graph vector features are extracted through an attention mechanism based on CNN, and the optimal father node is selected through deep reinforcement learning to serve as a relay node for data transmission of the optimal father node. After each data period is finished, the node counts related performance indexes of the data transmission node of the node; mapping the performance index into a corresponding reward value of the node under the corresponding state and action by adopting a same-degree quantization function, and transmitting experience information acquired in the data period to a server by the node; the method has relatively high expandability and can be applied to a node dynamic change scene in a network.

Description

technical field [0001] The invention relates to a network routing method, in particular to a wireless routing optimization method based on deep reinforcement learning. Background technique [0002] In recent years, the Internet of Things technology has continuously achieved new results, and has been applied to the fields of national defense and military, environmental detection, traffic management, medical and health care, manufacturing, disaster relief, etc. As one of the underlying technologies of the Internet of Things, the wireless sensor network has become an important Research hotspots in academia and industry. The routing protocol is the most important part of the wireless sensor network, and it is also one of the research hotspots at home and abroad. If you want to adapt to different working environments and complete corresponding tasks, the most important part is to design the corresponding routing protocol to make the network work. In various environments, it main...

AI Technical Summary

Problems solved by technology

[0005] In order to make up for the limitations of traditional routing algorithms in complex network scenarios, and solve the problem that existing reinforcement learning algorithms cannot be deployed on resource-constrained terminal devices, the present invention proposes an algorithm based on attention mechanism and deep reinforcement learning. The wireless routing optimization method specifically includes the following steps:

Images