CN112040002B - Data fusion method, device and equipment based on power distribution cloud platform - Google Patents

Data fusion method, device and equipment based on power distribution cloud platform Download PDF

Info

Publication number
CN112040002B
CN112040002B CN202010928756.8A CN202010928756A CN112040002B CN 112040002 B CN112040002 B CN 112040002B CN 202010928756 A CN202010928756 A CN 202010928756A CN 112040002 B CN112040002 B CN 112040002B
Authority
CN
China
Prior art keywords
data
sensor
importance
nodes
sensor nodes
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010928756.8A
Other languages
Chinese (zh)
Other versions
CN112040002A (en
Inventor
赵瑞锋
刘洋
李波
郭文鑫
卢建刚
王海柱
李世明
都海坤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Original Assignee
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd filed Critical Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Priority to CN202010928756.8A priority Critical patent/CN112040002B/en
Publication of CN112040002A publication Critical patent/CN112040002A/en
Application granted granted Critical
Publication of CN112040002B publication Critical patent/CN112040002B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/04—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
    • H04W40/248—Connectivity information update
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The application discloses a data fusion method, a data fusion device and data fusion equipment based on a power distribution cloud platform, wherein the method comprises the following steps: calculating the importance of the sensor nodes in the power distribution network; acquiring a corresponding identification frame and a reliability function according to the current processing item; calculating a weight coefficient of a reliability function according to the importance of the sensor node and a priori correlation coefficient of data required by processing items; and calculating the reliability function according to the weight coefficient. According to the method and the device, data fusion is completed by acquiring data transmitted by the corresponding sensor according to data required by processing items, information complementation is realized, and the accuracy of system decision is improved; by selecting more important sensor nodes as data acquisition nodes, data redundancy is reduced, and the scale of data to be analyzed is reduced.

Description

Data fusion method, device and equipment based on power distribution cloud platform
Technical Field
The application relates to the technical field of data fusion, in particular to a data fusion method, device and equipment based on a power distribution cloud platform.
Background
With the continuous expansion of the scale of the power distribution and consumption system, more and more sensors are provided on the power grid (because the sensors include data of various devices such as meters and sensors, the meters belong to the functional category of the sensors in terms of data collection, and hereinafter, various instruments capable of collecting data in the power distribution cloud platform are collectively referred to as sensors), and the sensors generate a large amount of power data. In addition, along with the development of the power internet of things, the power system also receives a plurality of comprehensive energy data such as environment temperature information, cold and hot energy information and the like, the high-efficiency and accurate fusion and data analysis of massive multi-source data are important aspects of improving the operation efficiency and stability of the power distribution and utilization platform, and the traditional data processing method enables the power distribution and utilization system to have obvious bottlenecks in the aspects of data storage space, analysis efficiency, instantaneity and the like.
Conventional power data includes historical data and real-time data, and not only low-delay real-time data but also exploratory historical data analysis is required. When various information is analyzed, all data are transmitted to a cloud platform through a transmission channel through simple preprocessing and then are stored and analyzed, the preprocessing task comprises conversion of original data and conversion of the original data into a data format required by a next data layer, and the data comprise historical and real-time data. Due to the fact that different analysis tasks have different requirements on the real-time performance of data processing, the traditional method transmits relevant data collected by the sensor to the cloud platform after the data are processed, a large amount of data are transmitted to the cloud platform in real time and analyzed, delay is caused, and therefore efficiency and real-time performance are low. Actually, with the development of a smart grid, the number of sensor nodes in a sensor network is increasing, sensors are distributed densely, the data scale is increasing exponentially, a plurality of similar sensors may be capable of monitoring data in a smaller area, and actually, if the data of the sensors are all synchronously transmitted to a cloud platform for real-time data processing, many unnecessary calculations are caused, that is, some data are redundant.
In addition, although mass data transmitted to the cloud platform are preprocessed to a certain degree at a data aggregation layer, the amount of data transmitted to the cloud platform for storage is still large, and in the conventional system, the data are directly used for data analysis to complete various tasks, which has a certain influence on the analysis speed.
Disclosure of Invention
The application provides a data fusion method, device and equipment based on a power distribution cloud platform, and solves the problems of overlarge data volume and low computing efficiency of the cloud platform.
In view of the above, a first aspect of the present application provides a data fusion method based on a power distribution cloud platform, where the method includes:
calculating the importance of the sensor nodes in the power distribution network;
acquiring a corresponding identification frame and a reliability function according to the current processing item;
calculating a weight coefficient of a reliability function according to the importance of the sensor node and a priori correlation coefficient of data required by the processing items;
and calculating the reliability function according to the weight coefficient.
Optionally, the calculating the importance of the sensor node in the power distribution network specifically includes:
I i ＝a∑I j /d ij +b×∑I j /d ij
in the formula (I), the compound is shown in the specification,
Figure BDA0002669406450000021
denoted i is the number of the neighbor node j, d ij Representing the physical distance between nodes i and j; a represents the influence factor of the neighbor node j with the same number on the current sensor node i, and b represents the influence factor of the neighbor node j with different numbers on the current sensor node i.
Optionally, the calculating the importance of the sensor node in the power distribution network further includes:
sequencing the sensor nodes of the same type according to the importance, and sequentially deleting neighbor nodes of the same type with the distance from the sensor nodes to the sensor nodes being smaller than a preset threshold value from the sensor nodes with the large importance value until all the sensor nodes are traversed;
and taking the sensor nodes left after traversing as nodes for preferentially transmitting data.
Optionally, the sorting the sensor nodes of the same type according to the importance, sequentially deleting neighboring nodes of the same type whose distances from the sensor nodes are smaller than a preset threshold from the sensor node with the larger importance value in order until all sensor nodes are traversed, and before:
and numbering the sensor nodes of different types, wherein the numbering of the sensor nodes of the same type is the same.
Optionally, the obtaining of the corresponding identification frame and the confidence function according to the current processing item specifically includes:
acquiring a corresponding identification frame according to the current processing item:
Θ＝{F 1 ,F 2 ,...,F n }
obtaining a reliability function corresponding to each fault in the identification frame as follows:
Figure BDA0002669406450000031
wherein F represents a failure of the processing item; k represents a weight coefficient of different types of data; m is 1 To m n A belief function representing different types of data.
Optionally, the calculating a weight coefficient of a reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required for processing the transaction includes:
k i ＝αI i +βL i
in the formula I i Indicates the importance of sensor i; l is i The prior correlation coefficient of the sensor i is represented; beta and alpha are both greater than 0 and smallA decimal at 1; k represents a weight coefficient.
This application second aspect provides a data fusion device based on distribution cloud platform, the device includes:
the importance calculating unit is used for calculating the importance of the sensor nodes in the power distribution network;
the identification frame acquisition unit is used for acquiring a corresponding identification frame and a reliability function according to the current processing item;
the weight coefficient calculation unit is used for calculating the weight coefficient of the reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required by the processing items;
and the reliability function calculation unit is used for calculating the reliability function according to the weight coefficient.
Optionally, the method further includes:
the priority node acquisition unit is used for sequencing the sensor nodes of the same type according to the importance, and sequentially deleting the neighbor nodes of the same type with the distance from the sensor nodes smaller than a preset threshold value from the sensor nodes with the large importance value until all the sensor nodes are traversed;
and taking the sensor nodes left after traversing as nodes for preferentially transmitting data.
Optionally, the method further includes:
and the numbering unit is used for numbering different types of sensor nodes, and the numbering of the sensor nodes of the same type is the same.
The third aspect of the present application provides a data fusion device based on a power distribution cloud platform, where the device includes a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the steps of the power distribution cloud platform-based data fusion method according to the first aspect.
According to the technical scheme, the method has the following advantages:
the application provides a data fusion method, a device and equipment based on a power distribution cloud platform, and the method comprises the following steps: calculating the importance of the sensor nodes in the power distribution network; acquiring a corresponding identification frame and a reliability function according to the current processing item; calculating a weight coefficient of a reliability function according to the importance of the sensor node and a priori correlation coefficient of data required by processing items; and calculating the reliability function according to the weight coefficient. According to the method and the device, data fusion is completed by acquiring data transmitted by corresponding sensors according to data required by processing items, information complementation is realized, and the accuracy of system decision is improved; by selecting more important sensor nodes as data acquisition nodes, data redundancy is reduced, and the scale of data to be analyzed is reduced.
Drawings
Fig. 1 is a flowchart of a method according to an embodiment of a data fusion method based on a power distribution cloud platform according to the present application;
fig. 2 is a flowchart of a method according to another embodiment of a data fusion method based on a power distribution cloud platform according to the present application;
fig. 3 is a device structure diagram of an embodiment of a data fusion device based on a power distribution cloud platform according to the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method of an embodiment of a data fusion method based on a power distribution cloud platform, as shown in fig. 1, including:
101. and calculating the importance of the sensor nodes in the power distribution network.
It should be noted that, in the sensor network, data collected by sensor nodes that are relatively close to each other are relatively similar, so in actual calculation, in order to avoid unnecessary overhead and unnecessary redundancy, the most representative sensor data in the same area and the same type of sensor may be transmitted first. Specifically, the importance of each sensor node may be calculated.
In a specific embodiment, calculating the importance of the sensor node in the power distribution network specifically includes:
I i ＝a∑I j /d ij +b×∑I j /d ij
in the formula (I), the compound is shown in the specification,
Figure BDA0002669406450000051
denoted i is the number of the neighbor node j, d ij Representing the physical distance between nodes i and j; a represents the influence factor of the neighbor node j with the same number on the current sensor node i, and b represents the influence factor of the neighbor node j with different numbers on the current sensor node i.
102. And acquiring a corresponding identification frame and a reliability function according to the current processing item.
It should be noted that, depending on the specific processing items, the degree of influence of the data transmitted by each sensor on the processing items is different, and thus, the identification frame corresponding to each processing item is different from the confidence function corresponding to the identification frame. Specifically, due to the fact that various data are stored in the power distribution cloud platform, besides relevant data of voltage and other power systems, various environmental data such as temperature and wind power are also stored, different items are processed, and the importance degree of the functions of different data is different. For example, when analyzing the cause of a feeder fault, data related to the feeder in environmental conditions such as wind power and power systems, such as voltage data, play a more important role in this data analysis task, and higher weighting factors should be given to such data.
Specifically, the identification frame corresponding to the current processing item is:
Θ＝{F 1 ,F 2 ,...,F n }
identifying a belief function for a plurality of different types of sensor data for each fault in the framework as:
Figure BDA0002669406450000052
in the formula, F represents a failure occurring in a processing item, and may include n failures; m (F) represents a comprehensive reliability function of the fault F (obtained by distributing basic probability of a plurality of types of sensors), and the reliability function of each fault in the identification frame is obtained by the formula; in particular, the method comprises the following steps of,
Figure BDA0002669406450000061
indicating that the confidence function for each fault is determined by multiple types of sensor data; k represents the weighting coefficient of different types of data (data acquired by different sensors); m is 1 To m n Fundamental probability distribution, m, representing different types of sensor data n Is a priori probability, representing F for different types of faults i When the data of the sensor n is abnormal, a failure F occurs i The prior probability is determined by an expert, that is, the prior probability is set by a professional in advance, and when the reliability function is calculated, the table is automatically looked up (that is, the preset prior probability is automatically looked up).
103. And calculating a weight coefficient of the reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required by the processing item.
It should be noted that after determining the importance node in each type of sensor and the prior correlation coefficient corresponding to the specific processing item, the weighting coefficient k of each type of data may be calculated according to the importance value of the node and the prior correlation coefficient. The prior correlation coefficient is related to the distance and parameter correlation and can be set according to experimental data.
In a specific embodiment, the weight coefficient for calculating the reliability function is specifically:
k i ＝αI i +βL i
in the formula I i Indicates the importance of sensor i; l is a radical of an alcohol i The prior correlation coefficient of the sensor i is represented; β and α are both decimal numbers greater than 0 and less than 1; k represents a weight coefficient.
104. And calculating a reliability function according to the weight coefficient.
It should be noted that, obtaining the weight coefficient k of each type of data and the reliability function corresponding to each type of data may synthesize the reliability functions of each type to obtain a final reliability function, where a specific formula is as follows:
Figure BDA0002669406450000062
wherein, the type of sensor data required for each type of fault handling is different, and therefore, the resultant type of the obtained belief function is also different, wherein:
Figure BDA0002669406450000063
fn, fy and Fz respectively represent faults corresponding to n, y and z; m is i (F y ) Indicating class i sensor data about failure F y The reliability function value of (1);
according to the method and the device, data fusion is completed by acquiring data transmitted by corresponding sensors according to data required by processing items, information complementation is realized, and the accuracy of system decision is improved; by selecting more important sensor nodes as data acquisition nodes, data redundancy is reduced, and the scale of data to be analyzed is reduced.
For convenience of understanding, the present application further provides a method flowchart of another embodiment of a data fusion method based on a power distribution cloud platform, please refer to fig. 2, which specifically includes:
201. and calculating the importance of the sensor nodes in the power distribution network.
It should be noted that each sensor or each sensor may be regarded as a node, a sensor network G is formed according to a routing policy, each node in the network G is numbered according to the sensor type, for example, the number of the low-voltage distribution area data is set to 1, the number of the environmental data such as the temperature and the wind power size is set to 2, and so on, a node number set of the sensor network G is formed; for each sensor node, the weight of the importance contribution degree of its neighbor node with the same number as that of the sensor node may be set to 1, and the weight of the importance contribution degree of its neighbor node with a different number as that of the sensor node may be set to 0.5.
Namely, the importance of calculating the sensor nodes in the power distribution network is specifically as follows:
I i ＝∑I j /d ij +0.5×∑I j /d ij
in the formula (I), the compound is shown in the specification,
Figure BDA0002669406450000071
denoted by the number of the neighbor node j of i, d ij Representing the physical distance between nodes i and j; a represents the influence factor of the neighbor node j with the same number on the current sensor node i, and b represents the influence factor of the neighbor node j with different numbers on the current sensor node i.
202. And sequencing the sensor nodes of the same type according to the importance, and sequentially deleting the neighbor nodes of the same type with the distance smaller than a preset threshold value from the sensor node with the large importance value in sequence until all the sensor nodes are traversed.
203. And taking the sensor nodes left after traversing as nodes for preferentially transmitting data.
It should be noted that the sensor nodes with the same number are sorted according to importance, and all neighbor nodes with the same number as the node and a distance smaller than a preset threshold value in one-hop neighbor nodes of the node are deleted from the node with the highest importance. And so on until all nodes have been traversed. The sensor nodes with higher importance are reserved, unnecessary sensor nodes are deleted, and a large amount of redundant data is avoided. In addition, after the importance of the nodes is calculated, the speed of transmitting data to a cluster head (when the sensor transmits data, a plurality of adjacent nodes form a cluster, each cluster is internally provided with a cluster head (cluster head), the clusters can be communicated with one another through the cluster heads) by the deleted nodes can be reduced, and the cluster heads set the transmission time of transmitting data to the cluster heads by different nodes.
204. And acquiring a corresponding identification frame and a reliability function according to the current processing item.
It should be noted that, depending on the specific processing items, the influence degree of the data transmitted by each sensor on the processing items is different, and the identification frame corresponding to each processing item is different from the confidence function corresponding to the identification frame. Specifically, due to the fact that various data are stored in the power distribution cloud platform, besides relevant data of voltage and other power systems, various environmental data such as temperature and wind power are also stored, different items are processed, and the importance degree of the functions of different data is different. For example, when analyzing the cause of feeder fault, environmental conditions such as wind power, and feeder related data such as voltage data in the power system play a more important role in this data analysis task, and a higher weighting factor should be given to such data.
Specifically, the identification frame corresponding to the current processing item is:
Θ＝{F 1 ,F 2 ,...,F n }
identifying a belief function for a plurality of different types of sensor data for each fault in the framework as:
Figure BDA0002669406450000081
in the formula, F represents a failure occurring in a processing item, and may include n failures; m (F) represents a comprehensive reliability function of the fault F (obtained by distributing basic probability of a plurality of types of sensors), and the reliability function of each fault in the identification frame is obtained by the formula; in particular, the method comprises the following steps of,
Figure BDA0002669406450000082
representing the confidence level of each faultThe function is determined by a plurality of types of sensor data; k represents the weighting coefficients of different types of data (data acquired by different sensors); m is 1 To m n Fundamental probability distribution, m, representing different types of sensor data n Is a priori probability, representing F for different types of faults i When the data of the sensor n is abnormal, a failure F occurs i The prior probability is determined by an expert, that is, the prior probability is set by a professional in advance, and when the reliability function is calculated, the table is automatically looked up (that is, the preset prior probability is automatically looked up).
Since the data type requirements required for each transaction are different, the resultant types of the confidence functions obtained are also different, where:
Figure BDA0002669406450000083
fn, fy and Fz respectively represent faults corresponding to n, y and z; m is a unit of i (F y ) Indicating class i sensor data about failure F y The reliability function value of (1);
in the formula, m represents a reliability function that the symptom measured by the sensor belongs to processing items, and an identification frame formed by processing different items is different from the reliability function; k represents a weighting coefficient; x and Y represent specific processing items; i, j represents an integer of zero or more and n or less. Specifically, due to the fact that various data are stored in the power distribution cloud platform, besides relevant data of voltage and other power systems, various environmental data such as temperature and wind power are also stored, different problems (namely different processing items) are solved, and the important degrees of the functions of the data collected by different sensors are different. For example, when analyzing the cause of a feeder fault, data related to the feeder in environmental conditions such as wind power and power systems such as voltage data play a more important role in this data analysis task, and higher weighting coefficients should be given to the data, and specific weighting coefficients can be set according to experimental data.
205. And calculating a weight coefficient of the reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required by the processing item.
It should be noted that, according to the importance of each sensor node and the a priori correlation coefficient L i Each sensor is given a weight coefficient k. Wherein the prior correlation coefficient is related to the distance and parameter correlation and can be set according to experimental data. Specifically, the weighting coefficient k may be obtained by the following method:
k i ＝αI i +βL i
in the formula I i Indicates the importance of sensor i; l is i The prior correlation coefficient of the sensor i is represented; and both β and α are fractional numbers greater than 0 and less than 1.
Specifically, the method for confirming the prior correlation coefficient may construct a judgment matrix according to the scale 1-9 of Santy, and then the table for determining the prior correlation coefficient is as follows:
L i explanation of the invention
1 i is equally important as j
3 i is slightly more important than j
5 i is significantly more important than j
7 i is strongly important than j
9 i is extremely important than j
2，4，6，8 Median value of the above two adjacent judgments
Then, according to the obtained judgment matrix, obtaining the maximum eigenvalue and eigenvector of the judgment matrix, where the eigenvector is the prior correlation coefficient L of each type of data (data collected by each type of sensor) finally obtained through iteration of the type of data i . The iteration method specifically comprises the following steps: a is an n-th order matrix, and if the number λ and the n-dimensional non-0 column vector x satisfy Ax = λ x, the number λ is referred to as an eigenvalue of a, and x is referred to as an eigenvector of a corresponding to the eigenvalue λ. The expression Ax = λ x can also be written as (a- λ E) x =0, and | λ E-a | is called a characteristic polynomial of a. When the characteristic polynomial is equal to 0, the characteristic equation is called A, the characteristic equation is a homogeneous linear equation set, the process of solving the characteristic value is actually to solve the solution of the characteristic equation, a Jacobi (Jacobi) iteration method is adopted to solve the solution of the characteristic equation, and the method is also a general method for solving the solution of the characteristic equation.
206. And calculating the reliability function according to the weight coefficient.
It should be noted that, obtaining the weight coefficient k of each type of data and the reliability function corresponding to each type of data may synthesize each type of reliability function to obtain a final reliability function, where a specific formula is as follows:
Figure BDA0002669406450000101
according to the method and the device, data fusion is completed by acquiring data transmitted by corresponding sensors according to data required by processing items, information complementation is realized, and the accuracy of system decision is improved; by selecting more important sensor nodes to preferentially transmit important data, the real-time performance of the system is improved, the data redundancy is reduced, and the scale of the data to be analyzed is reduced.
The above is an embodiment of the data fusion method based on the power distribution cloud platform, and the present application also includes an embodiment of the data fusion device based on the power distribution cloud platform, as shown in fig. 3, including:
and the importance calculating unit 301 is used for calculating the importance of the sensor nodes in the power distribution network.
The identification frame acquiring unit 302 is configured to acquire a corresponding identification frame and a reliability function according to the current processing item.
The weight coefficient calculation unit 303 is configured to calculate a weight coefficient of the reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required for processing the event.
And a reliability function calculation unit 304, configured to calculate a reliability function according to the weight coefficient.
In a specific embodiment, the method further comprises the following steps:
and the priority node acquisition unit is used for sequencing the sensor nodes of the same type according to importance, and sequentially deleting the neighbor nodes of the same type with the distance from the sensor nodes smaller than a preset threshold value from the sensor nodes with the large importance value until all the sensor nodes are traversed.
And taking the sensor nodes left after traversing as nodes for preferentially transmitting data.
In a specific embodiment, the method further comprises the following steps:
and the numbering unit is used for numbering different types of sensor nodes, and the numbering of the sensor nodes of the same type is the same.
The application also provides an embodiment of data fusion equipment based on the power distribution cloud platform, and the equipment comprises a processor and a memory:
the memory is used for storing and transmitting the program codes to the processor.
The processor is used for executing the embodiment of the data fusion method based on the power distribution cloud platform according to the instructions in the program codes.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "comprises," "comprising," and "having," and any variations thereof, in this application are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b and c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims (8)

1. A data fusion method based on a power distribution cloud platform is characterized by comprising the following steps:
calculating the importance of the sensor nodes in the power distribution network;
sequencing the sensor nodes of the same type according to the importance, and sequentially deleting neighbor nodes of the same type with the distance from the sensor nodes to the sensor nodes smaller than a preset threshold value from the sensor nodes with the large importance value until all the sensor nodes are traversed;
taking the rest sensor nodes after traversing as nodes for preferentially transmitting data;
acquiring a corresponding identification frame and a reliability function according to the current processing item;
calculating a weight coefficient of a reliability function according to the importance of the sensor node and a priori correlation coefficient of data required by the processing items;
and calculating the reliability function according to the weight coefficient.
2. The data fusion method based on the power distribution cloud platform according to claim 1, wherein the importance of the sensor nodes in the computing power distribution network is specifically as follows:
I i ＝a∑I j /d ij +b×∑I j /d ij
in the formula (d) ij Representing the physical distance between nodes i and j; a represents the influence factor of the neighbor node j with the same number on the current sensor node i, and b represents the influence factor of the neighbor node j with different numbers on the current sensor node i.
3. The data fusion method based on the power distribution cloud platform according to claim 1, wherein after the sensor nodes of the same type are sorted according to the importance, and from the sensor node with a large importance value, neighbor nodes of the same type with a distance to the sensor node smaller than a preset threshold value are sequentially deleted in sequence until all sensor nodes are traversed, the method further comprises:
and numbering the sensor nodes of different types, wherein the numbering of the sensor nodes of the same type is the same.
4. The power distribution cloud platform-based data fusion method according to claim 1, wherein the obtaining of the corresponding identification frame and the confidence function according to the current processing item specifically includes:
acquiring a corresponding identification frame according to the current processing item:
Θ＝{F 1 ,F 2 ,...,F n }
obtaining a reliability function corresponding to each fault in the identification frame as follows:
Figure FDA0004051476520000011
wherein F represents a failure in the processing item; k represents a weight coefficient of different types of data; m is 1 To m n A belief function representing different types of data.
5. The power distribution cloud platform-based data fusion method according to claim 1, wherein the calculating of the weight coefficient of the reliability function according to the importance of the sensor node and the a priori correlation coefficient of the data required for processing the transaction comprises:
k i ＝αI i +βL i
in the formula I i Indicates the importance of sensor i; l is i The prior correlation coefficient of the sensor i is represented; β =1- α, β and α are both decimal numbers greater than 0 and less than 1; k represents a weight coefficient.
6. The utility model provides a data fusion device based on distribution cloud platform which characterized in that includes:
the importance calculating unit is used for calculating the importance of the sensor nodes in the power distribution network;
the priority node acquisition unit is used for sequencing the sensor nodes of the same type according to the importance, and sequentially deleting the neighbor nodes of the same type with the distances from the sensor nodes smaller than a preset threshold value from the sensor nodes with the large importance value until all the sensor nodes are traversed;
taking the rest sensor nodes after traversing as nodes for preferentially transmitting data;
the identification frame acquisition unit is used for acquiring a corresponding identification frame and a reliability function according to the current processing item;
the weight coefficient calculation unit is used for calculating the weight coefficient of the reliability function according to the importance of the sensor node and the prior correlation coefficient of the data required by the processing items;
and the reliability function calculation unit is used for calculating the reliability function according to the weight coefficient.
7. The power distribution cloud platform-based data fusion device of claim 6, further comprising:
and the numbering unit is used for numbering the sensor nodes of different types, and the numbering of the sensor nodes of the same type is the same.
8. A data fusion device based on a power distribution cloud platform is characterized by comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the power distribution cloud platform-based data fusion method of any one of claims 1-5 according to instructions in the program code.
CN202010928756.8A 2020-09-07 2020-09-07 Data fusion method, device and equipment based on power distribution cloud platform Active CN112040002B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010928756.8A CN112040002B (en) 2020-09-07 2020-09-07 Data fusion method, device and equipment based on power distribution cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010928756.8A CN112040002B (en) 2020-09-07 2020-09-07 Data fusion method, device and equipment based on power distribution cloud platform

Publications (2)

Publication Number Publication Date
CN112040002A CN112040002A (en) 2020-12-04
CN112040002B true CN112040002B (en) 2023-04-18

Family

ID=73584575

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010928756.8A Active CN112040002B (en) 2020-09-07 2020-09-07 Data fusion method, device and equipment based on power distribution cloud platform

Country Status (1)

Country Link
CN (1) CN112040002B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113239250B (en) * 2021-06-09 2022-09-02 河南科技大学 Method for screening key nodes for data acquisition
CN113516768A (en) * 2021-07-15 2021-10-19 国网山东省电力公司电力科学研究院 Visual wisdom thing of transformer substation allies oneself with management system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101539241A (en) * 2009-05-07 2009-09-23 北京航空航天大学 Hierarchical multi-source data fusion method for pipeline linkage monitoring network
EP2224371A1 (en) * 2009-02-27 2010-09-01 Honda Research Institute Europe GmbH Artificial vision system and method for knowledge-based selective visual analysis
CN111093244A (en) * 2019-12-25 2020-05-01 华北电力大学 Wireless sensor network route optimization method and system
CN111340118A (en) * 2020-02-27 2020-06-26 河南大学 Conflict evidence fusion method based on reliability entropy and BJS divergence

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2224371A1 (en) * 2009-02-27 2010-09-01 Honda Research Institute Europe GmbH Artificial vision system and method for knowledge-based selective visual analysis
CN101539241A (en) * 2009-05-07 2009-09-23 北京航空航天大学 Hierarchical multi-source data fusion method for pipeline linkage monitoring network
CN111093244A (en) * 2019-12-25 2020-05-01 华北电力大学 Wireless sensor network route optimization method and system
CN111340118A (en) * 2020-02-27 2020-06-26 河南大学 Conflict evidence fusion method based on reliability entropy and BJS divergence

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于证据理论的多传感器加权融合改进方法;李军等;《计算机测量与控制》;20111025;第2592-2595页 *

Also Published As

Publication number Publication date
CN112040002A (en) 2020-12-04

Similar Documents

Publication Publication Date Title
Ding et al. Analysis of feature matrix in machine learning algorithms to predict energy consumption of public buildings
CN112040002B (en) Data fusion method, device and equipment based on power distribution cloud platform
CN107169628B (en) Power distribution network reliability assessment method based on big data mutual information attribute reduction
CN107832876B (en) Partition maximum load prediction method based on MapReduce framework
CN110505114B (en) Method for judging node abnormity in cloud computing environment
CN114519514B (en) Low-voltage transformer area reasonable line loss value measuring and calculating method, system and computer equipment
CN113537844B (en) Method and system for analyzing load behaviors of regional energy Internet based on random matrix
Biard et al. Automated detection of weather fronts using a deep learning neural network
CN114861788A (en) Load abnormity detection method and system based on DBSCAN clustering
CN103336995A (en) Method for constructing real-time light metering network of million kilowatt level photovoltaic power generation base
Mahmoudvand et al. Forecasting mortality rate by singular spectrum analysis
CN113111305A (en) Abnormity detection method and device, storage medium and electronic equipment
CN111027837B (en) Method, system, equipment and medium for determining reference route of newly-added international route
Sandoval et al. Three-way unsupervised data mining for power system applications based on tensor decomposition
CN115879607A (en) Electric energy meter state prediction method, system, equipment and storage medium
CN102156641A (en) Prediction method and system for confidence interval of software cost
CN107491656B (en) Pregnancy outcome influence factor evaluation method based on relative risk decision tree model
Xu et al. Dynamic graph neural network with adaptive edge attributes for air quality prediction: A case study in China
CN110543996A (en) job salary assessment method, apparatus, server and storage medium
CN109165854B (en) Empty pipe operation efficiency grade evaluation method and device
CN116316617A (en) Multi-station intelligent fusion new energy generation power region prediction method and system
CN116087435A (en) Air quality monitoring method, electronic equipment and storage medium
CN115941807A (en) Efficient data compression method for park security system
CN112801564B (en) Method and device for constructing wind speed forecasting model along high-speed rail
CN114266414A (en) Loan amount prediction method, loan amount prediction device, loan amount prediction electronic device, and loan amount prediction medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant