A wireless sensor network data prediction method
A wireless sensor and network data technology, applied in wireless communication, advanced technology, climate sustainability, etc., can solve the problems of high energy consumption and high computing overhead, and achieve the effect of high flexibility, small amount of calculation, and high precision
Active Publication Date: 2020-04-07
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem to be solved by the present invention is to aim at the disadvantages of high energy consumption and large calculation overhead in the traditional method. Therefore, a new data prediction method is proposed. Taking the cluster in the wireless sensor network as the unit, each The cluster head of the cluster is responsible for data prediction, which can effectively guarantee the accuracy of data prediction, and has good versatility and practicability
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0037] The concrete flow process of the inventive method is as figure 2 As shown, the specific steps are as follows:
[0038] Step 1: Carry out clustering and elect a cluster head according to a certain clustering algorithm. The clustering algorithm must be able to select a node with strong computing power to serve as the cluster head. After the clustering ends, the cluster head obtains the ID of the non-cluster head nodes in the cluster (marked as ID i , 1=<i<=n) and the total number n, and set the number k of stored data (for data prediction) (the choice of k is related to the accuracy of data prediction, the larger the value of k, the more The larger the amount of predicted data, the more accurate the predicted result, but at the same time it will consume a larger memory space and cause higher computing overhead). After completing the selection of k va...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a wireless sensor network data prediction method. Firstly, clustering is performed according to a clustering algorithm and a cluster head is elected. The cluster head obtains the ID and the total number n of non-cluster head nodes in the cluster, and sets the item for storing data. After the cluster head obtains the data, the records are stored in the memory; for each new record, the value of each node is calculated, and the residual and error with the target value are obtained, and saved. When the number of records in the memory is equal to k , carry out data prediction, assign weights to each node selected for data prediction, correct the value calculated by the latest cluster head, and determine the direction and step size of the correction. The invention has high flexibility, small amount of calculation, can effectively save energy consumption, and simultaneously has high precision. Moreover, the method proposed by the invention is simple and easy to implement, has better practicability, and is easy to use in actual environments.
Description
technical field [0001] The invention belongs to the technical field of wireless sensor network and data prediction, and in particular relates to a data prediction method of wireless sensor network. Background technique [0002] Wireless sensor network (Wireless Sensor Network, WSN) is a typical distributed network, which contains a large number of sensor nodes, which are usually deployed in various environments to collect data. Through the historical data collected in the wireless sensor network, future data or trends can be predicted. For example, predict the temperature of some key areas in the forest to judge whether there is a risk of fire, predict the trend of smog in the next few days, and remind the general public to take corresponding precautions in a timely manner. [0003] The data collected by wireless sensors has the characteristics of multiple sources, that is, due to the high density of nodes in the network, the sampling values of the nodes that are closer i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04W4/38H04W52/02
CPCH04W4/38H04W52/0209Y02D30/70
Inventor 黄海平张凯何凡吴鹏飞胡林康杜安明王汝传沙超
Owner NANJING UNIV OF POSTS & TELECOMM