Topology control method based on unsupervised learning for ultra-dense wireless sensor network

Abstract

The invention relates to a topology control method based on unsupervised learning for an ultra-dense wireless sensor network. On the basis of a framework of a genetic algorithm, network nodes are clustered, and the optimal clustering network topology is searched through continuous unsupervised learning. In the optimization process, the three factors of node energy, node distance and node density of the network are important input data sets, and different factor weights are determined by using a hierarchical analysis method to establish a fitness function. By adoption of the topology control method provided by the invention, the node energy consumption can be effectively improved, and the network life of the wireless sensor network is improved at last.

Description

technical field [0001] The invention relates to the technical field of wireless sensor networks, in particular to a topology control method based on unsupervised learning for ultra-dense wireless sensor networks. Background technique [0002] With the advent of the 5G era, ultra-dense wireless sensor networks are one of the important components of future networks, and the issue of network lifespan has always been the focus and focus of research on ultra-dense wireless sensor networks. Wireless sensor network is a network in which nodes can dynamically and automatically find the optimal path to transmit and collect new information to the base station. It is widely used in military, industrial control, agricultural production and many other fields. Due to the limited energy supply and processing capability of nodes, traditional routing algorithms cannot be directly applied to wireless sensor networks. Therefore, establishing a topology with good network performance is the key...

AI Technical Summary

Problems solved by technology

Based on IEEE 802.15.4 (PHY, MAC), Zigbee forms a low-speed network specification by adding three layers of Network, Security and Application protocols. Short-distance communication within 100 meters cannot effectively meet the application requirements of heterogeneous sensor networks where low-speed short-distance and medium-, high-speed, and medium-to-long-distance nodes coexist

Fixed network topology, lack of adaptability and customizability to multiple application fields, and poor flexibility

Therefore, the architecture of Zigbee cannot be well used in sensor networks with heterogeneity and mobility for the time being.

Images