Blind calibration method for data drift of distributed wireless sensor network

Abstract

The invention discloses a blind calibration method for data drift of a distributed wireless sensor network and solves the technical problems that the wireless sensor network data drift blind calibration process has high requirements on the environment, has many restrictions and is easy to fail. The method comprises the following steps: determining a distributed wireless sensor network; collectingcalibration network model parameter training data; establishing a distributed data drift blind calibration model and training model parameters; collecting data in real time; and each node continuouslyacquires measurement data in real time to perform data blind calibration until the node energy is exhausted, thereby completing the blind calibration process of the distributed network. Distributed implementation is adopted, independent execution is performed at each distributed node, interactive calibration among the nodes is not needed, the network load is reduced, and the problem that the calibration method of the network fails when part of the nodes in the network fail is avoided. By recovering the actual signal, the calibration precision is higher, and the training is faster; easy engineering implementation. The method is used for data drift blind calibration of the wireless sensor network.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to wireless sensor network data drift blind calibration, in particular to a distributed wireless sensor network data drift blind calibration method, which is used for distributed data drift blind calibration under the wireless sensor network. Background technique [0002] Wireless sensor networks (wireless sensor networks, WSN) are composed of a group of sensor nodes with wireless communication capabilities, combined with various technical means such as wireless communication technology, embedded computing technology, sensor technology, distributed information processing technology, etc., can realize data It has three functions of collection, processing and transmission, which can be divided into centralized and distributed according to the data processing method. Studies have shown that the centralized information processing method of WSN consumes a lot of energy and has poor n...

AI Technical Summary

Problems solved by technology

[0004] 1) Cost constraints need to be considered in practical applications. Usually, the preconditions for intensive deployment or monitoring of the same target required in the blind calibration method are difficult to meet in many scenarios, and it is difficult to achieve, and the blind calibration method only relies on dense deployment and other conditions. The effect is more general;

[0005] 2) Usually, when calibrating data, multiple nodes in the network need to send data to the same node set to calibrate the data. In this way, the information of neighboring nodes can be used to help its own nodes calibrate the data. However, centralized data The processing method will increase the energy consumption of nodes and increase the communication load of nodes in the wireless sensor network, and when some nodes in the network are exhausted and fail or new nodes are added to the wireless sensor network, it may cause the original calibration of the entire network function failure;

[0006] 3) In the process of blind calibration, many blind calibration methods need to select individual nodes for manual calibration as standard data, and other nodes calibrate their own node data through information interaction with manual calibration nodes, but the actual application needs to consider the environment and other limiting factors, manual calibration cannot be performed in many cases, which affects the entire blind calibration process and results

[0007] To sum up, the existing algorithms will have disadvantages such as network communication congestion, heavy network load, high node energy consumption, and difficult to meet the calibration preconditions during the calibration process, which will affect the application of the data drift blind calibration method in the actual environment, resulting in data loss. The disadvantages of drift blind calibration are low accuracy, poor stability or even unusable

[0008] The above defects limit the performance of wireless sensor networks, resulting in many application environment restrictions, heavy network load, unstable algorithm performance, and easy failure due to changes in network nodes such as increase or death, thus affecting the application performance of wireless sensor networks.

Images