Wireless sensor network abnormal data analysis method and wireless sensor node

Abstract

The invention relates to a wireless sensor network technology, and discloses an abnormal data analysis method and a wireless sensor node. The abnormal data analysis method comprises the following steps: S1, after a reading xt is obtained at a moment t by a node i, and whether the xt is an abnormal value or not is judged according to all readings in the current window, if yes, a step S2 is executed, and if no, a step S3 is executed; S2, readings of k neighbor nodes are obtained at the moment t by the node i, and the cause of the abnormal value of the xt is judged accordingly, if the cause is resulted from hardware or software errors, a step S4 is executed, otherwise, a step S5 is executed; S3, the xt is stored by the node I; S4, the xt is divorced from the node i; and S5, the xt is sent to a base station by the node i. The node comprises a data acquisition module, an abnormal data analysis module, a storage module and a wireless communication module. According to the technical scheme, the computation is finished within the neighbourhood of the node, so that the network flow expense is reduced; and by the use of the space-time relevance of data, the abnormal value is detected automatically, the cause of the abnormal value is analyzed, and the misdeclaration and false declaration events are avoided.

Description

technical field [0001] The invention relates to the technical field of wireless sensor networks, in particular to an abnormal data analysis method and a wireless sensor node. Background technique [0002] With the rapid development of communication technology, chip manufacturing technology and embedded computing technology, wireless sensor networks are increasingly being used in many fields such as national defense, construction, environment, and urban management. Although wireless sensor nodes are widely favored due to their low cost and low power consumption, an important factor restricting their development is the low reliability of sensor data, which often contains abnormal data. A typical data anomaly scenario is: sensor nodes deployed in the forest, the sensory data at noon in summer is generally about 30 degrees Celsius, and suddenly the data at a certain moment becomes 100 degrees Celsius, this 100 degrees Celsius is an abnormal data. [0003] The sources of abnorma...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a method for analyzing abnormal data in a wireless sensor network and a wireless sensor node, so as to solve the problem that the existing abnormal data detection method cannot effectively analyze the causes of abnormal values, and is prone to misreporting or missing important events. And the problems of high power consumption of nodes and large network traffic overhead

Images