Wireless sensor network data fusion method based on clustering discrete grey model (DGM)
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A wireless sensor and network data technology, applied in the field of high-performance computing, can solve the problems of data transmission consumption and error reduction, time-series data spatial correlation, and insufficient consideration of uncertainty, etc.
Active Publication Date: 2018-07-27
CHONGQING UNIV OF POSTS & TELECOMM
View PDF1 Cites 3 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, there are problems of insufficient consideration of the spatial correlation and uncertainty o...
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0062] A kind of wireless sensor network data fusion method based on clustering DGM of the present invention comprises the following steps:
[0063] S11. According to the spatial position of the sensor, the sensor is clustered, and the cluster head node is set; the sensor node transmits the data collected at the first q moments to the cluster head node; the cluster head node transmits the data to the sink node;
[0064] S21. Call the DGM-based multi-sensor data fusion MS-DGM prediction model, generate a data matrix according to the original data, and obtain the data prediction value at the q+1th moment;
[0065] S31. On the cluster head node, the actual data at the q+1th moment Perform standardization to obtain the error set between the multi-sensor value at the q+1th moment and the actual data at the q+1th moment if The cluster head node sends the actual data Transfer to the sink node and update the data table of the sink node; where, Indicates the error of the i-th da...
Embodiment 2
[0115] Compared with Embodiment 1, the present embodiment has the following steps, including:
[0116] S41. Adopt the updated data table as the original data, and use the q-N+2th data to the q+1th data as the original data, q=q+1, return to step S2, N represents the number of historical data for prediction N can be the value of q in the first cycle, or a value smaller than q in the first cycle. For example, if there are data at 100 moments (q=100) in the original data, N can be 100, or Can be a value less than 100.
[0117] This embodiment can realize not only the data prediction at the q+1th time, but also the data prediction at the next q+1 time, and the data at the subsequent time.
[0118] This method can effectively detect and complement the abnormal points, improve the reliability of the data, and treat the data of multiple sensors as a whole, and use the spatial correlation between the data to correct the predicted data, effectively improving the reliability of the dat...
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 relates to the technical field of high performance computing, and in particular relates to a wireless sensor network data fusion method based on clustering discrete grey model (DGM). Themethod comprises the steps of dynamically clustering multi-sensor data according to spatial correlation; detecting and polishing abnormal points in a data sequence group; describing correlation between sensor nodes with the aid of a discrete interval grey number concept in a grey theory; using a discrete grey number DGM prediction model to perform modeling and prediction on a development trend ofa data sequence; and achieving fusion of multi-sensor data. According to the method provided by the invention, the abnormal points can be effectively detected and polished, and the data reliability is enhanced; the prediction data is corrected by using the spatial correlation between the data, and thus the accuracy of data prediction is effectively enhanced; the data sending amount between the cluster node and convergence node is reduced; the transmission distance of the sensor node is effectively reduced; the transmission energy consumption of the sensor node is reduced; and the butt joint point number of the convergence nodes is reduced, and the network congestion problem is relieved.
Description
technical field [0001] The invention relates to the technical field of high-performance computing, in particular to a wireless sensor network data fusion method based on a clustering discrete gray model (Discretegrey model, DGM). Background technique [0002] Wireless Sensor Networks (WSNs) is an ad hoc network system formed by communicating with a large number of sensor nodes deployed in the monitoring area. Reconnaissance, biomedicine, intelligent transportation, resource detection and other fields. [0003] Data redundancy and limited sensor data acquisition and transmission are bottlenecks in WSNs applications, mainly due to the structural characteristics of WSNs: (1) Sensor nodes are densely deployed, data is greatly affected by time changes, and there is a large redundancy and Instability; (2) Sensor nodes generally have many constraints (such as battery capacity, computing power, storage space, and communication bandwidth, etc.), and limited network resources cannot ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more