A method for recovering and reconstructing lost data in marine wireless sensor networks

Abstract

The invention discloses a method for recovering and reconstructing loss data of an ocean wireless sensor network, comprising node clustering and loss data recovery, wherein node clustering comprises:firstly, arranging nodes satisfying a ocean wireless sensor network communication requirement and a real-time monitoring requirement in an ocean area to be monitored, constructing the topology of theocean wireless sensor network, and effectively clustering the nodes according to an improved K-means algorithm; and wherein the loss data recovery includes: when the node data is lost, excavating thespace-time correlation of the node data in data loss clusters by a RBF neural network optimized by a PSO algorithm, and then recovering the loss data value according to the historical and current round data in the loss clusters. The method can adapt to the high dynamics of the topology of the ocean wireless sensor network, and can reduce the energy consumption of data transmission between nodes, thereby achieving a purpose of extending the life cycle of the network.

Description

technical field [0001] The invention relates to a data prediction and transmission technology of an ocean wireless sensor network, in particular to a method for recovering and reconstructing lost data of an ocean wireless sensor network (OWSNs). Background technique [0002] The real-time collection of marine data is the premise of a comprehensive understanding of the ocean, the development of marine resources and the protection of the ocean in the 21st century. Wireless sensor network (WSN, wireless sensor network) has been widely used in the field of environmental monitoring due to its low power consumption, low cost, distributed and self-organizing characteristics. In the monitoring of marine ecological environment, a large number of sensor nodes scattered in the target sea area can quickly self-organize into a monitoring network with better adaptability in a wireless multi-hop manner, so as to meet the requirements of real-time collection of marine data. [0003] In rec...

AI Technical Summary

Problems solved by technology

[0006] The existing data recovery and prediction methods are mainly based on the time correlation model and the probability model for data recovery, but both of these two models have large data recovery errors when the monitoring data changes over time, and considering the ocean wireless The characteristics of the real-time dynamic change of the sensor network topology and the influence of the wave shading effect on the data transmission between nodes, so the time correlation and spatial correlation of marine environmental data are combined to propose a new ocean wireless sensor network. Lost data Restoration and reconstruction methods are very necessary

Images