CN108258802B - Method and device for monitoring running condition of power distribution equipment in power distribution network - Google Patents
Method and device for monitoring running condition of power distribution equipment in power distribution network Download PDFInfo
- Publication number
- CN108258802B CN108258802B CN201611241803.1A CN201611241803A CN108258802B CN 108258802 B CN108258802 B CN 108258802B CN 201611241803 A CN201611241803 A CN 201611241803A CN 108258802 B CN108258802 B CN 108258802B
- Authority
- CN
- China
- Prior art keywords
- power distribution
- distribution equipment
- index
- values
- value
- 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
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 135
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 238000003064 k means clustering Methods 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H02J13/0017—
Abstract
The embodiment of the invention provides a method for monitoring the running state of distribution equipment in a power distribution network, which comprises the steps of receiving monitoring data sent by a monitoring unit arranged in the distribution equipment, wherein the monitoring data comprises all index parameters for representing the running state of the distribution equipment and index values corresponding to the index parameters; clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm; acquiring common index parameters of all power distribution equipment in the category to be monitored; calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values. The embodiment of the invention also provides a device for monitoring the running condition of the power distribution equipment in the power distribution network.
Description
Technical Field
The invention relates to the field of distribution network automation, in particular to a method and a device for monitoring the running condition of distribution equipment in a distribution network.
Background
The power distribution network is used for connecting a power transmission network, a distributed power supply and various users and plays a role in distributing electric energy in the whole power network; in actual use, the distribution network may fail for various reasons, causing significant losses to customers and electric power companies, and therefore, efforts are made to avoid such situations. In practice, one possible solution is to detect problems, repair and/or replace them in time, before the power distribution equipment fails. For example, the intelligent power distribution network system is used for acquiring data such as power distribution network data, user data, a power grid structure and geographic information, and then performing data analysis and processing, so that problems can be found in time before deteriorated power distribution equipment in the power distribution network system breaks down, and maintenance personnel are informed to repair and/or replace in time, and the probability of the power distribution network breaking down is greatly reduced. However, the existing intelligent distribution network system only collects the monitoring data above the high-voltage side of the distribution area, and the monitoring data of the low-voltage distribution network part is lost, so that the distribution network cannot be comprehensively analyzed, and certain faults may be missed; the reason is that the number of the power distribution equipment in the low-voltage distribution network part is large, the types are complicated, the number of the monitoring data is huge, and the formats, the types, the semantics and the like are not uniform, so that great difficulty is brought to the storage, the analysis and the processing of the monitoring data of the part.
Therefore, a method for analyzing all monitoring data in a power distribution network and calculating the operating condition scores of all power distribution equipment in the power distribution network is needed.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for analyzing all monitoring data in a power distribution network and calculating operating condition scores of all power distribution devices in the power distribution network.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the embodiment of the invention provides a method for monitoring the running condition of distribution equipment in a power distribution network, which comprises the following steps:
receiving monitoring data sent by a monitoring unit arranged in power distribution equipment, wherein the monitoring data comprises all index parameters for representing the running state of the power distribution equipment and index values corresponding to the index parameters;
clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
acquiring common index parameters of all power distribution equipment in the category to be monitored;
calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values.
In the foregoing solution, the clustering all the power distribution devices into different categories according to the index parameters of the monitoring data of all the power distribution devices and the clustering algorithm includes:
and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
In the above scheme, calculating an operation index value of each power distribution device in the category to be monitored according to the index value of the common index parameter of each power distribution device in the category to be monitored and the preset weight value corresponding to each common index parameter, includes:
according to the index values of the common index parameters of all the monitoring data of all the power distribution equipment in the category to be monitored, obtaining first weight values corresponding to the common index parameters of all the power distribution equipment according to an entropy weight method, and calculating final weight values corresponding to the common index parameters of all the power distribution equipment based on the preset weight values and the corresponding first weight values of all the common index parameters; and obtaining the operation index value of each power distribution equipment based on the preset value of the common index parameter and the corresponding final weight value in each power distribution equipment.
In the foregoing solution, the calculating a final weight value corresponding to each common indicator parameter of each power distribution device based on the preset weight value and the corresponding first weight value of each common indicator parameter includes:
the product of the preset weight value of each common index parameter of each power distribution equipment and the corresponding first weight value is a first numerical value, the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, and then the medium weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value.
In the foregoing solution, the obtaining an operation index value of each distribution device based on the preset value of the common index parameter and the corresponding final weight value in each distribution device includes:
and when the preset value of any one common index parameter in each power distribution device is smaller than the preset threshold value, the operation index value of each power distribution device is the minimum value of the product of the preset values and the final weight values of all the common index parameters, otherwise, the operation index value of each power distribution device is the sum of the product of the preset values and the final weight values of all the common index parameters.
The embodiment of the invention provides a device for monitoring the running condition of distribution equipment in a power distribution network, which comprises the following modules:
the monitoring data receiving module is used for receiving monitoring data sent by a monitoring unit arranged in the power distribution equipment, and the monitoring data comprises all index parameters for representing the running state of the power distribution equipment and index values corresponding to the index parameters;
the clustering module is used for clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
the common index parameter acquisition module is used for acquiring common index parameters of all the power distribution equipment in the category to be monitored;
and the operation module is used for calculating the operation index value of each power distribution equipment in the category to be monitored according to the index value of the common index parameter of each power distribution equipment in the category to be monitored and the preset weight value corresponding to each common index parameter, and determining the operation condition of each power distribution equipment in the category to be monitored based on the operation index value.
In the foregoing solution, the clustering module is specifically configured to: and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
In the foregoing solution, the operation module is specifically configured to: according to the index values of the common index parameters of all the monitoring data of all the power distribution equipment in the category to be monitored, obtaining first weight values corresponding to the common index parameters of all the power distribution equipment according to an entropy weight method, and calculating final weight values corresponding to the common index parameters of all the power distribution equipment based on the preset weight values and the corresponding first weight values of all the common index parameters; and obtaining the operation index value of each power distribution equipment based on the preset value of the common index parameter and the corresponding final weight value in each power distribution equipment.
In the foregoing solution, the operation module is specifically configured to: the product of the preset weight value of each common index parameter of each power distribution equipment and the corresponding first weight value is a first numerical value, the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, and then the medium weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value.
In the foregoing solution, the operation module is specifically configured to: and when the preset value of any one common index parameter in each power distribution device is smaller than the preset threshold value, the operation index value of each power distribution device is the minimum value of the product of the preset values and the final weight values of all the common index parameters, otherwise, the operation index value of each power distribution device is the sum of the product of the preset values and the final weight values of all the common index parameters.
The embodiment of the invention provides a method for monitoring the running state of distribution equipment in a power distribution network, which comprises the steps of receiving monitoring data sent by a monitoring unit arranged in the distribution equipment, wherein the monitoring data comprises all index parameters for representing the running state of the distribution equipment and index values corresponding to the index parameters; clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm; acquiring common index parameters of all power distribution equipment in the category to be monitored; calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values. Therefore, the method can analyze all monitoring data in the power distribution network and calculate the running condition scores of all power distribution equipment in the power distribution network.
Drawings
Fig. 1 is a schematic flowchart of a method for monitoring an operating condition of a power distribution device in a power distribution network according to an embodiment of the present invention;
FIG. 2 is a table containing monitoring data according to an embodiment of the present invention;
FIG. 3 is a table containing entropy values of index parameters according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for monitoring an operating condition of a power distribution device in a power distribution network according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a monitoring apparatus for monitoring an operating condition of power distribution equipment in a power distribution network according to an embodiment of the present invention;
Detailed Description
In the embodiment of the invention, monitoring data sent by a monitoring unit arranged in power distribution equipment is received, wherein the monitoring data comprises all index parameters for representing the running condition of the power distribution equipment and index values corresponding to the index parameters; clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm; acquiring common index parameters of all power distribution equipment in the category to be monitored; calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values.
The present invention will be described in further detail with reference to examples.
The embodiment of the invention provides a method for monitoring the running condition of distribution equipment in a power distribution network, which comprises the following steps as shown in figure 1:
step 101: receiving monitoring data sent by a monitoring unit arranged in power distribution equipment, wherein the monitoring data comprises all index parameters for representing the running state of the power distribution equipment and index values corresponding to the index parameters;
in the running process of the power distribution equipment, the set monitoring unit can continuously monitor the running state of the power distribution equipment and send the running state to the intelligent power distribution network system in the form of monitoring data, so that the intelligent power distribution network system can receive the monitoring data of all the power distribution equipment; the monitoring data of each power distribution device has a fixed format, and includes fixed index parameters and index values corresponding to the fixed index parameters, for example, the status indexes of the plant station include: n-1 power supply capability, full shutdown power supply capability, etc.
In the monitoring method, the intelligent power distribution network system needs to collect monitoring data of all power distribution equipment in the power distribution network, and as an optional technical scheme, a data transmission network, such as an optical network and the like, can be built for specially transmitting the monitoring data; or the monitoring data above the high-voltage side of the transformer area are transmitted by using the existing intelligent distribution network system, and for other monitoring data, a new data transmission network is needed.
Due to different purposes of each power distribution device, different manufacturers and the like, each power distribution device can have unique index parameters for representing the operation condition.
Step 102: clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
step 103: acquiring common index parameters of all power distribution equipment in the category to be monitored;
in practice, different power distribution equipment has different index parameters representing the operation conditions, the formats, types, semantics and the like of monitoring data are different, and in the low-voltage distribution network part, the number and the types of the power distribution equipment are numerous and complicated, so that a unique monitoring algorithm must be established for each power distribution equipment to monitor the operation conditions of the power distribution equipment, but the operation is extremely difficult; therefore, in the calculation method, in order to reduce the calculation difficulty, the intelligent power distribution network system performs classification processing on the power distribution equipment, so that the power distribution equipment in the same category has high similarity, a monitoring algorithm can be established for the category, and the monitoring algorithm is used for operating conditions of all the power distribution equipment in the category, so that the calculation method is easier. For example, the lines are divided into urban lines and suburban lines, unique monitoring algorithms are respectively established for the urban lines and the suburban lines, the same monitoring algorithm is used for each line in the urban lines, the same monitoring algorithm is used for each line in the suburban lines, and the complexity of the monitoring algorithms is greatly reduced.
The intelligent power distribution network system classifies the power distribution equipment by using a clustering algorithm, so that the similarity of the power distribution equipment in the same class is as large as possible, and the similarity between the power distribution equipment in different classes is as small as possible. Hierarchical clustering algorithms, segmentation clustering algorithms, constraint-based clustering algorithms, clustering algorithms in machine learning, and clustering algorithms for high dimensionality, among others, may be used herein.
Because the power distribution equipment in the same category has high similarity, in the intelligent power distribution network system, the common index parameters in all the power distribution equipment in the category to be monitored can be obtained, and the operating conditions of all the power distribution equipment in the category to be monitored are represented by the common index parameters. For example: the common index parameters of the plant station comprise: n-1 power supply capacity, full-stop power supply capacity, contact rate with adjacent stations and the like;
step 104: calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values.
Since the power distribution devices in the same category have similarity, the same monitoring algorithm is applied to all the power distribution devices in the same category, and therefore, index values of the common index parameters of the power distribution devices need to be provided. As an alternative embodiment, it is also possible to normalize the index values of all the common index parameters so that they have the same dimension, and to convert qualitative values into quantitative values.
After the intelligent power distribution network system calculates the operating condition of the power distribution equipment, the operating condition can be presented to an administrator, and the administrator can judge the probability of the fault of the power distribution equipment according to the operating condition value of the power distribution equipment, so that the power distribution equipment can be timely maintained and/or replaced.
As an alternative embodiment, since the number of power distribution devices in the power distribution network is large and each power distribution device continuously transmits monitoring data, a time-series database may be used to store the monitoring data.
In the embodiment of the present invention, the clustering all the power distribution devices into different categories according to the index parameters of the monitoring data of all the power distribution devices and the clustering algorithm includes: and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
Here, the step of using the K-Mean clustering algorithm may be:
1. determining an initial clustering center for each category, such that there are k initial category centers; in reality, some power distribution devices have been determined to belong to a certain category without error, such as: according to the geographic position, the line can be determined to belong to an urban line or a suburban line, and therefore the power distribution equipment can be set as k initial clustering centers;
2. distributing the power distribution equipment to the nearest category according to the minimum distance principle; because the power distribution equipment in the same category has similar state indexes, for example, the number and the types of the index parameters in the state indexes have similarity, and the values of the index parameters of the same type are in the same range; thus, the distance between two power distribution devices may be calculated using the similarity of the index parameters;
3. using the mean value of the power distribution equipment in each category as a new category center;
4. and repeating the steps 2 and 3 until the category center is not changed any more.
In an actual power distribution network, since the purpose of each power distribution equipment is determined, usually one power distribution equipment belongs to a certain exact category, that is, few power distribution equipment simultaneously belong to a plurality of different categories, so that the K-Means clustering algorithm used in the calculation method can be converged quickly.
In an embodiment of the present invention, calculating an operation index value of each power distribution device in the category to be monitored according to the index value of the common index parameter of each power distribution device in the category to be monitored and the preset weight value corresponding to each common index parameter, includes:
according to the index values of the common index parameters of all the monitoring data of all the power distribution equipment in the category to be monitored, obtaining first weight values corresponding to the common index parameters of all the power distribution equipment according to an entropy weight method, and calculating final weight values corresponding to the common index parameters of all the power distribution equipment based on the preset weight values and the corresponding first weight values of all the common index parameters; and obtaining the operation index value of each power distribution equipment based on the preset value of the common index parameter and the corresponding final weight value in each power distribution equipment.
Here, the final weight is related to not only the preset weight value, but also the monitoring data of the power distribution equipment, so that the final weight value can be obtained by adaptively modifying the preset weight value according to the actual situation.
Next, an example of calculating the first weight value is shown in fig. 2, which is monitoring data of a line, and includes 12 sets of second state index values, each of which includes 4 index parameters, that is, a line load rate, a terminal online rate, a line loss rate, and a contact condition; the calculation process is as follows:
1. standardizing each index parameter:
wherein n is the number of the monitoring data of the line and has a value of 12, m is the total number of the common index parameters and has a value of 4, xijThe index value x 'of the j index parameter of the i monitoring data'ijNormalizing the index value of the jth index parameter of the ith monitoring data;
2. calculating an index entropy value:
here, ejThe index entropy value of the jth index parameter of the ith monitoring data is obtained; in this example, it is meant that the values are as shown in FIG. 3;
3. calculating the weight of each index parameter:
(1) calculating an information utility value:
(2) in the first weighted value, the weighted value of each index parameter is:
in an embodiment of the present invention, the calculating a final weight value corresponding to each common indicator parameter of each power distribution device based on the preset weight value and the corresponding first weight value of each common indicator parameter includes:
the product of the preset weight value of each common index parameter of each power distribution equipment and the corresponding first weight value is a first numerical value, the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, and then the medium weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value.
4. In the final weight values, the weight value of each index parameter is:
In an embodiment of the present invention, the obtaining an operation index value of each distribution device based on a preset value of the common index parameter and a final weight value corresponding to each distribution device includes: and when the preset value of any one common index parameter in each power distribution device is smaller than the preset threshold value, the operation index value of each power distribution device is the minimum value of the product of the preset values and the final weight values of all the common index parameters, otherwise, the operation index value of each power distribution device is the sum of the product of the preset values and the final weight values of all the common index parameters.
Then the health of the distribution equipment is scored as:
wherein C isiF is a preset threshold value, and is the score of the ith index parameter in the common index parameters.
The embodiment of the invention provides a monitoring device for the running condition of distribution equipment in a power distribution network, which comprises the following modules as shown in fig. 4:
the monitoring data receiving module 1 is used for receiving monitoring data sent by a monitoring unit arranged in the power distribution equipment, wherein the monitoring data comprises all index parameters for representing the operation condition of the power distribution equipment and index values corresponding to the index parameters;
in the running process of the power distribution equipment, the set monitoring unit can continuously monitor the running state of the power distribution equipment and send the running state to the intelligent power distribution network system in the form of monitoring data, so that the intelligent power distribution network system can receive the monitoring data of all the power distribution equipment; the monitoring data of each power distribution device has a fixed format, and includes fixed index parameters and index values corresponding to the fixed index parameters, for example, the status indexes of the plant station include: n-1 power supply capability, full shutdown power supply capability, etc.
In the monitoring method, the intelligent power distribution network system needs to collect monitoring data of all power distribution equipment in the power distribution network, and as an optional technical scheme, a data transmission network, such as an optical network and the like, can be built for specially transmitting the monitoring data; or the monitoring data above the high-voltage side of the transformer area are transmitted by using the existing intelligent distribution network system, and for other monitoring data, a new data transmission network is needed.
Due to different purposes of each power distribution device, different manufacturers and the like, each power distribution device can have unique index parameters for representing the operation condition.
The clustering module 2 is used for clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
the common index parameter acquisition module 3 is used for acquiring common index parameters of all power distribution equipment in the category to be monitored;
in practice, different power distribution equipment has different index parameters representing the operation conditions, the formats, types, semantics and the like of monitoring data are different, and in the low-voltage distribution network part, the number and the types of the power distribution equipment are numerous and complicated, so that a unique monitoring algorithm must be established for each power distribution equipment to monitor the operation conditions of the power distribution equipment, but the operation is extremely difficult; therefore, in the calculation method, in order to reduce the calculation difficulty, the intelligent power distribution network system performs classification processing on the power distribution equipment, so that the power distribution equipment in the same category has high similarity, a monitoring algorithm can be established for the category, and the monitoring algorithm is used for operating conditions of all the power distribution equipment in the category, so that the calculation method is easier. For example, the lines are divided into urban lines and suburban lines, unique monitoring algorithms are respectively established for the urban lines and the suburban lines, the same monitoring algorithm is used for each line in the urban lines, the same monitoring algorithm is used for each line in the suburban lines, and the complexity of the monitoring algorithms is greatly reduced.
The intelligent power distribution network system classifies the power distribution equipment by using a clustering algorithm, so that the similarity of the power distribution equipment in the same class is as large as possible, and the similarity between the power distribution equipment in different classes is as small as possible. Hierarchical clustering algorithms, segmentation clustering algorithms, constraint-based clustering algorithms, clustering algorithms in machine learning, and clustering algorithms for high dimensionality, among others, may be used herein.
Because the power distribution equipment in the same category has high similarity, in the intelligent power distribution network system, the common index parameters in all the power distribution equipment in the category to be monitored can be obtained, and the operating conditions of all the power distribution equipment in the category to be monitored are represented by the common index parameters. For example: the common index parameters of the plant station comprise: n-1 power supply capacity, full-stop power supply capacity, contact rate with adjacent stations and the like;
and the operation module 4 is configured to calculate an operation index value of each power distribution device in the category to be monitored according to the index value of the common index parameter of each power distribution device in the category to be monitored and a preset weight value corresponding to each common index parameter, and determine an operation status of each power distribution device in the category to be monitored based on the operation index value.
Since the power distribution devices in the same category have similarity, the same monitoring algorithm is applied to all the power distribution devices in the same category, and therefore, index values of the common index parameters of the power distribution devices need to be provided. As an alternative embodiment, it is also possible to normalize the index values of all the common index parameters so that they have the same dimension, and to convert qualitative values into quantitative values.
After the intelligent power distribution network system calculates the operating condition of the power distribution equipment, the operating condition can be presented to an administrator, and the administrator can judge the probability of the fault of the power distribution equipment according to the operating condition value of the power distribution equipment, so that the power distribution equipment can be timely maintained and/or replaced.
As an alternative embodiment, since the number of power distribution devices in the power distribution network is large and each power distribution device continuously transmits monitoring data, a time-series database may be used to store the monitoring data.
In an embodiment of the present invention, the clustering module is specifically configured to: and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
Here, the step of using the K-Mean clustering algorithm may be:
1. determining an initial clustering center for each category, such that there are k initial category centers; in reality, some power distribution devices have been determined to belong to a certain category without error, such as: according to the geographic position, the line can be determined to belong to an urban line or a suburban line, and therefore the power distribution equipment can be set as k initial clustering centers;
2. distributing the power distribution equipment to the nearest category according to the minimum distance principle; because the power distribution equipment in the same category has similar state indexes, for example, the number and the types of the index parameters in the state indexes have similarity, and the values of the index parameters of the same type are in the same range; thus, the distance between two power distribution devices may be calculated using the similarity of the index parameters;
3. using the mean value of the power distribution equipment in each category as a new category center;
4. and repeating the steps 2 and 3 until the category center is not changed any more.
In an actual power distribution network, since the purpose of each power distribution equipment is determined, usually one power distribution equipment belongs to a certain exact category, that is, few power distribution equipment simultaneously belong to a plurality of different categories, so that the K-Means clustering algorithm used in the calculation method can be converged quickly.
In an embodiment of the present invention, the operation module is specifically configured to: according to the index values of the common index parameters of all the monitoring data of all the power distribution equipment in the category to be monitored, obtaining first weight values corresponding to the common index parameters of all the power distribution equipment according to an entropy weight method, and calculating final weight values corresponding to the common index parameters of all the power distribution equipment based on the preset weight values and the corresponding first weight values of all the common index parameters; and obtaining the operation index value of each power distribution equipment based on the preset value of the common index parameter and the corresponding final weight value in each power distribution equipment.
Here, the final weight is related to not only the preset weight value, but also the monitoring data of the power distribution equipment, so that the final weight value can be obtained by adaptively modifying the preset weight value according to the actual situation.
Next, an example of calculating the first weight value is shown in fig. 2, which is monitoring data of a line, and includes 12 sets of second state index values, each of which includes 4 index parameters, that is, a line load rate, a terminal online rate, a line loss rate, and a contact condition; the calculation process is as follows:
1. standardizing each index parameter:
wherein n is the number of the monitoring data of the line and has a value of 12, m is the total number of the common index parameters and has a value of 4, xijThe index value x 'of the j index parameter of the i monitoring data'ijNormalizing the index value of the jth index parameter of the ith monitoring data;
2. calculating an index entropy value:
here, ejThe index entropy value of the jth index parameter of the ith monitoring data is obtained; in this example, it is meant that the values are as shown in FIG. 3;
3. calculating the weight of each index parameter:
(1) calculating an information utility value:
(2) in the first weighted value, the weighted value of each index parameter is:
in an embodiment of the present invention, the operation module is specifically configured to: the product of the preset weight value of each common index parameter of each power distribution equipment and the corresponding first weight value is a first numerical value, the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, and then the medium weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value.
4. In the final weight values, the weight value of each index parameter is:
In an embodiment of the present invention, the operation module is specifically configured to: and when the preset value of any one common index parameter in each power distribution device is smaller than the preset threshold value, the operation index value of each power distribution device is the minimum value of the product of the preset values and the final weight values of all the common index parameters, otherwise, the operation index value of each power distribution device is the sum of the product of the preset values and the final weight values of all the common index parameters.
Then the health of the distribution equipment is scored as:
wherein C isiF is a preset threshold value, and is the score of the ith index parameter in the common index parameters.
The embodiment of the invention provides a monitoring device for the running condition of distribution equipment in a power distribution network, which comprises the following modules as shown in fig. 5:
the intelligent power distribution network scheduling technology support system is used for storing related data and providing interfaces for inputting and reading the data outwards, and comprises a time sequence database for storing monitoring data, a time sequence database access interface for inputting and reading the monitoring data, a relational database for storing relational data and a relational database access interface for inputting and reading the relational data; in order to quickly access the relational database, a memory arranged in the relational database is cached, namely a memory bank access interface, a file server for storing files, a file access interface for providing file input and reading, an application server for storing applications and a message bus for providing the application input and reading interfaces are provided;
the data access layer is used for providing uniform data access interfaces upwards, and comprises uniform data access services and alarm services, the uniform data access services provide the uniform data access interfaces upwards, the difference of each interface of the intelligent power distribution network scheduling technology support system is shielded, and the alarm services are used for providing warning information if data storage fails;
the basic support layer comprises a data preprocessing module, a cluster analysis module, an evaluation model and an evaluation algorithm, wherein the data and processing module is used for converting received monitoring data to form a uniform format, the cluster analysis module is used for clustering all power distribution equipment monitoring data into different categories according to the cluster algorithm, the evaluation model is used for setting common index parameters for the different categories, and the evaluation algorithm is used for calculating the operation index value of each power distribution equipment in the category to be monitored according to the index value of the common index parameter of each power distribution equipment and the preset weight value corresponding to each common index parameter;
the fault reporting layer is used for determining the operation condition of each power distribution device in the category to be monitored based on the operation index value;
and the visual display layer is used for graphically displaying the operating condition of the power distribution equipment to a user.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (4)
1. A method for monitoring the operation condition of power distribution equipment in a power distribution network is characterized by comprising the following steps:
receiving monitoring data sent by a monitoring unit arranged in power distribution equipment, wherein the monitoring data comprises all index parameters for representing the running state of the power distribution equipment and index values corresponding to the index parameters;
clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
acquiring common index parameters of all power distribution equipment in the category to be monitored;
calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values;
the calculating the operation index value of each power distribution equipment in the category to be monitored according to the index value of the common index parameter of each power distribution equipment in the category to be monitored and the preset weight value corresponding to each common index parameter comprises the following steps: according to the index values of the common index parameters of all the monitoring data of all the power distribution equipment in the category to be monitored, obtaining first weight values corresponding to the common index parameters of all the power distribution equipment according to an entropy weight method, and calculating final weight values corresponding to the common index parameters of all the power distribution equipment based on the preset weight values and the corresponding first weight values of all the common index parameters; obtaining operation index values of the distribution equipment based on preset values of the common index parameters and the corresponding final weight values in the distribution equipment;
the step of calculating a final weight value corresponding to each common index parameter of each power distribution device based on the preset weight value and the corresponding first weight value of each common index parameter includes: the product of the preset weight value of each common index parameter of each power distribution equipment and the corresponding first weight value is a first numerical value, and the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, so that the weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value;
the obtaining of the operation index value of each distribution equipment based on the preset value of the common index parameter and the corresponding final weight value in each distribution equipment comprises: and when the preset value of any one common index parameter in each power distribution device is smaller than the preset threshold value, the operation index value of each power distribution device is the minimum value of the product of the preset values and the final weight values of all the common index parameters, otherwise, the operation index value of each power distribution device is the sum of the product of the preset values and the final weight values of all the common index parameters.
2. The method for monitoring the operating conditions of the power distribution equipment in the power distribution network according to claim 1, wherein the step of clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and the clustering algorithm comprises the steps of:
and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
3. A monitoring device for the operation condition of power distribution equipment in a power distribution network is characterized by comprising the following modules:
the monitoring data receiving module is used for receiving monitoring data sent by a monitoring unit arranged in the power distribution equipment, and the monitoring data comprises all index parameters for representing the running state of the power distribution equipment and index values corresponding to the index parameters;
the clustering module is used for clustering all the power distribution equipment into different categories according to the index parameters of the monitoring data of all the power distribution equipment and a clustering algorithm;
the common index parameter acquisition module is used for acquiring common index parameters of all the power distribution equipment in the category to be monitored;
the operation module is used for calculating operation index values of the power distribution equipment in the category to be monitored according to the index values of the common index parameters of the power distribution equipment in the category to be monitored and the preset weight values corresponding to the common index parameters, and determining the operation conditions of the power distribution equipment in the category to be monitored based on the operation index values; the power distribution equipment monitoring system is used for obtaining a first weight value corresponding to each common index parameter of each power distribution equipment according to an entropy weight method and index values of the common index parameters of all monitoring data of each power distribution equipment in the category to be monitored, and calculating a final weight value corresponding to each common index parameter of each power distribution equipment based on a preset weight value and the corresponding first weight value of each common index parameter; obtaining operation index values of the distribution equipment based on preset values of the common index parameters and the corresponding final weight values in the distribution equipment; the product of the preset weight value of each common index parameter used for each power distribution equipment and the corresponding first weight value is a first numerical value, and the sum of the products of the preset weight values of all the common index parameters and the corresponding first weight values is a second numerical value, so that the medium weight value of each common index parameter of each power distribution equipment is the quotient of the first numerical value and the second numerical value; and the operation index value of each power distribution equipment is the minimum value of the product of the preset values and the final weight value of all the common index parameters when the preset value of any common index parameter in each power distribution equipment is smaller than the preset threshold value, otherwise, the operation index value of each power distribution equipment is the sum of the product of the preset values and the final weight value of all the common index parameters.
4. The apparatus for monitoring the operating condition of the power distribution equipment in the power distribution network according to claim 3, wherein the clustering module is specifically configured to:
and clustering all the power distribution equipment into different categories based on a K-Means clustering algorithm according to the number and the types of the index parameters of the monitoring data of the power distribution equipment and the corresponding index values.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611241803.1A CN108258802B (en) | 2016-12-29 | 2016-12-29 | Method and device for monitoring running condition of power distribution equipment in power distribution network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611241803.1A CN108258802B (en) | 2016-12-29 | 2016-12-29 | Method and device for monitoring running condition of power distribution equipment in power distribution network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108258802A CN108258802A (en) | 2018-07-06 |
CN108258802B true CN108258802B (en) | 2020-07-03 |
Family
ID=62720458
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611241803.1A Active CN108258802B (en) | 2016-12-29 | 2016-12-29 | Method and device for monitoring running condition of power distribution equipment in power distribution network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108258802B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110247477B (en) * | 2019-06-19 | 2021-03-12 | 广东电网有限责任公司 | Method and device for monitoring online condition of equipment |
CN110221173B (en) * | 2019-06-20 | 2021-06-04 | 国网上海市电力公司 | Power distribution network intelligent diagnosis method based on big data drive |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8078567B1 (en) * | 2008-12-31 | 2011-12-13 | John Cadick | System and method for condition based maintenance for electrical equipment |
CN105406461A (en) * | 2015-10-21 | 2016-03-16 | 广西电网有限责任公司北海供电局 | Adaptive dynamic load monitoring method for power distribution network power failure events |
CN106203867A (en) * | 2016-07-19 | 2016-12-07 | 国家电网公司 | Grid division methods based on power distribution network assessment indicator system and cluster analysis |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509178B (en) * | 2011-11-25 | 2014-12-17 | 江苏省电力公司淮安供电公司 | Distribution network device status evaluating system |
CN103514368B (en) * | 2013-09-18 | 2017-04-26 | 燕山大学 | Real-time and stage theory line loss fast estimation method with clustering technique adopted |
CN103617561A (en) * | 2013-12-02 | 2014-03-05 | 深圳供电局有限公司 | System and method for evaluating state of secondary device of power grid intelligent substation |
CN104123678A (en) * | 2014-07-12 | 2014-10-29 | 东北电力大学 | Electricity relay protection status overhaul method based on status grade evaluation model |
CN104268367B (en) * | 2014-08-06 | 2018-01-16 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Transformer state evaluation weight modification method and system based on multiple linear regression |
CN106204330A (en) * | 2016-07-18 | 2016-12-07 | 国网山东省电力公司济南市历城区供电公司 | A kind of power distribution network intelligent diagnosis system |
-
2016
- 2016-12-29 CN CN201611241803.1A patent/CN108258802B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8078567B1 (en) * | 2008-12-31 | 2011-12-13 | John Cadick | System and method for condition based maintenance for electrical equipment |
CN105406461A (en) * | 2015-10-21 | 2016-03-16 | 广西电网有限责任公司北海供电局 | Adaptive dynamic load monitoring method for power distribution network power failure events |
CN106203867A (en) * | 2016-07-19 | 2016-12-07 | 国家电网公司 | Grid division methods based on power distribution network assessment indicator system and cluster analysis |
Also Published As
Publication number | Publication date |
---|---|
CN108258802A (en) | 2018-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
CN108320043A (en) | A kind of distribution network equipment state diagnosis prediction method based on electric power big data | |
CN105894177A (en) | Decision-making-tree-algorithm-based analysis and evaluation method for operation risk of power equipment | |
CN115640915B (en) | Intelligent gas pipe network compressor safety management method and Internet of things system | |
CN104468220A (en) | Early warning control platform of power telecommunication network | |
CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
CN105488118A (en) | Electrical equipment fault information display method and device | |
CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
CN111311133B (en) | Monitoring system applied to power grid production equipment | |
CN108258802B (en) | Method and device for monitoring running condition of power distribution equipment in power distribution network | |
CN109974780A (en) | A kind of electrical equipment status monitoring system based on Internet of Things | |
CN114140094A (en) | Intelligent risk monitoring and early warning system for food enterprises | |
CN115442212A (en) | Intelligent monitoring analysis method and system based on cloud computing | |
CN108647860A (en) | Power equipment state monitoring based on OpenStack and assessment cloud platform | |
CN115860694A (en) | Business expansion process management and control method and system based on instant message technology | |
CN115130847A (en) | Equipment portrait modeling method and system | |
CN111709597B (en) | Power grid production domain operation monitoring system | |
CN117391675A (en) | Data center infrastructure operation and maintenance management method | |
CN106649034B (en) | Visual intelligent operation and maintenance method and platform | |
CN109460915A (en) | It is a kind of based on big data driving city elevator intelligent send work checking system | |
CN115730749A (en) | Electric power dispatching risk early warning method and device based on fused electric power data | |
CN109299863A (en) | BTM appraisal of equipment system | |
CN107358329A (en) | The determination methods and device of POWER SYSTEM STATE | |
CN113887861A (en) | Power transmission and transformation main equipment quasi-real-time data monitoring system |
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 |