CN117196540A - Method, system, equipment and storage medium for identifying running state of platform area - Google Patents
Method, system, equipment and storage medium for identifying running state of platform area Download PDFInfo
- Publication number
- CN117196540A CN117196540A CN202311460992.1A CN202311460992A CN117196540A CN 117196540 A CN117196540 A CN 117196540A CN 202311460992 A CN202311460992 A CN 202311460992A CN 117196540 A CN117196540 A CN 117196540A
- Authority
- CN
- China
- Prior art keywords
- feature
- rate
- data
- running state
- situation awareness
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 120
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 230000008447 perception Effects 0.000 claims abstract description 6
- 238000007726 management method Methods 0.000 claims description 95
- 230000008569 process Effects 0.000 claims description 44
- 238000004458 analytical method Methods 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 23
- 238000012797 qualification Methods 0.000 claims description 21
- 238000007689 inspection Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 18
- 230000005611 electricity Effects 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000000513 principal component analysis Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 7
- 230000000295 complement effect Effects 0.000 claims description 7
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000012850 discrimination method Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000011160 research Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000003064 k means clustering Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure relates to the technical field of power market zone management, and discloses a zone running state identification method, a system, equipment and a storage medium, wherein the method comprises the following steps: combining the data characteristics of the situation awareness data to construct a situation awareness feature library; clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature; calculating the score of each feature based on the mapping relation between the assignment interval and the score; constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value; and based on the grading of each feature and the final weight value of the feature, adopting a multi-element linear weighting algorithm to realize the state perception of the running state of the platform region. According to the exemplary embodiment of the disclosure, comprehensive research and judgment are performed on the system operation situation, a manager is helped to get through data of each field, grid management of a platform area is established, intelligent and efficient decision-making is assisted, and working quality and working efficiency of the manager of the platform area are improved.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of power market zone management, in particular to a zone running state identification method, system, equipment and storage medium based on situation awareness.
Background
With the gradual expansion and improvement of the electricity consumption information acquisition range and the electricity consumption information acquisition success rate, the intelligent, efficient and visual large screen is needed for real-time monitoring of business data for mass data basis and business management requirements. On one hand, the basic condition and business characteristics of the new generation electricity information acquisition system are displayed in a multi-azimuth, multi-angle and panoramic mode, and on the other hand, the overall running state and condition of the platform area are comprehensively judged from multi-dimension, and the overall running state condition of the platform area is timely presented. The increase of the data information volume means the improvement of calculation efficiency, calculation complexity and the like, and the problems that the data distortion cannot be effectively solved, the comprehensive information of the platform area cannot be displayed in multiple directions and the management efficiency of the platform area under a large amount of data is low in the traditional mode are solved.
Disclosure of Invention
The embodiment of the disclosure provides a method, a system, equipment and a storage medium for identifying the running state of a platform area, which are used for solving or relieving one or more technical problems in the prior art.
According to one aspect of the present disclosure, there is provided a method for identifying a running state of a station, including:
acquiring situation awareness data of the running state of the platform region;
combining the data characteristics of the situation awareness data to construct a situation awareness feature library;
clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature;
calculating the score of each feature based on the mapping relation between the assignment interval and the score;
constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value;
and based on the grading of each feature and the final weight value of the feature, adopting a multi-element linear weighting algorithm to realize the state perception of the running state of the platform region.
In one possible implementation, the method includes: processing the characteristic data deletion and abnormality:
for quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
in the method, in the process of the invention,to be complemented withData,/->For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
In one possible implementation manner, the situation awareness data of the running state of the platform area includes an acquisition time rate, an acquisition coverage rate, a metering equipment fault rate, a fault list exchange rate, a platform area line loss qualification rate, a platform area availability rate and a theft line loss checking rate.
In one possible implementation manner, the situation awareness feature library includes seven dimensions of metering management, collection management, line loss management, anti-electricity-stealing monitoring, state evaluation, field management and operation detection management, wherein:
the metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
the acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
the state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
The operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
In one possible implementation manner, based on the situation awareness feature library, clustering the situation awareness features to form an assignment interval of each feature includes:
taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
in the formula, a sampleK represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
combining the profile coefficient, the intra-class compactness and the intra-class cohesion analysis to form the characteristic optimal clustering class number;
and completing the division of the feature assignment interval based on the formed cluster category.
In one possible implementation, constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value includes:
Respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
In one possible implementation, the weighting analysis using the principal component analysis method includes:
extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: />；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Calculating contribution rate of each principal component based on load matrix：
；
In the method, in the process of the invention,represents the i-th principal component feature value, and h represents the total number of principal component features.
Calculating the importance of each feature：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
In one possible implementation, the weight value in the site management dimension is automatically updated in real time based on the platform region running state identification model running frequency, and a real-time dynamic weight value is generated.
In one possible implementation manner, based on the score of each feature and the final weight value of the feature, a multi-element linear weighting algorithm is adopted, and a formula for realizing the situation awareness of the running state of the platform is as follows:
；
wherein:scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
According to one aspect of the present disclosure, there is provided a system for identifying a running state of a zone, including:
the acquisition unit is used for acquiring situation awareness data of the running state of the platform area;
the construction unit is used for combining the data characteristics of the situation awareness data to construct a situation awareness feature library;
the clustering unit is used for clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature;
the score calculating unit is used for calculating the score of each feature based on the mapping relation between the assigned interval and the score;
the weight calculation unit is used for constructing a feature weight system based on the situation awareness feature library and calculating a feature final weight value;
and the weighting calculation unit is used for realizing the situation awareness of the running state of the platform area by adopting a multi-element linear weighting algorithm based on the score of each feature and the final weight value of the feature.
In one possible implementation, the method includes: the processing unit is used for processing the characteristic data deletion and the abnormality;
the processing unit is specifically configured to:
for quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
；
in the method, in the process of the invention,for data to be complemented, < >>For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
In one possible implementation manner, the situation awareness data of the running state of the platform area includes an acquisition time rate, an acquisition coverage rate, a metering equipment fault rate, a fault list exchange rate, a platform area line loss qualification rate, a platform area availability rate and a theft line loss checking rate.
In one possible implementation manner, the situation awareness feature library includes seven dimensions of metering management, collection management, line loss management, anti-electricity-stealing monitoring, state evaluation, field management and operation detection management, wherein:
the metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
The acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
the state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
the operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
In a possible implementation manner, the clustering unit is configured to:
taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
in the formula, a sample K represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
combining the profile coefficient, the intra-class compactness and the intra-class cohesion analysis to form the characteristic optimal clustering class number;
and completing the division of the feature assignment interval based on the formed cluster category.
In one possible implementation manner, the weight calculation unit is configured to:
respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
In one possible implementation, the weighting analysis using the principal component analysis method includes:
extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: />；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Calculating contribution rate of each principal component based on load matrix ：
；
In the method, in the process of the invention,represents the i-th principal component feature value, and h represents the total number of principal component features.
Calculating the importance of each feature：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
In one possible implementation manner, the method includes a generating unit, configured to automatically update a weight value in a site management dimension in real time based on a platform running state identification model running frequency, and generate a real-time dynamic weight value.
In one possible implementation, the formula of the weight calculation unit is:
；
wherein:scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
According to an aspect of the present disclosure, there is provided a zone operating state identifying apparatus including:
a processor and a memory;
the memory is used for storing a computer program, and the processor calls the computer program stored in the memory to execute the platform running state identification method according to any one of the above.
According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored therein a computer program which, when executed by a processor, enables the processor to perform the method of identifying a running state of a bay as set forth in any one of the above.
Exemplary embodiments of the present disclosure have the following advantageous effects: according to the method, mass data of a new generation electricity information acquisition system is used as a fulcrum, intelligent sensing construction of the panoramic state of the new generation electricity information acquisition system is carried out, a platform region running state situation sensing characteristic system is constructed and formed by starting from different object levels such as metering management, acquisition management, line loss management, anti-electricity stealing monitoring, state evaluation, field management and operation inspection management, weight analysis and assignment interval analysis are carried out on different dimension characteristics of the platform region based on a K-means clustering technology, principal component analysis and entropy weight discrimination weight technology, real-time dynamic weight is generated on the basis of model running frequency aiming at the field management dimension characteristics, and on the basis, a platform region running state recognition score is comprehensively formed, so that the whole-field coverage of daily monitoring and intelligent decision is realized, comprehensive research and judgment of the system running situation are realized, managers are helped to break through data of various fields, grid management of the platform region is established, intelligent assistance and efficient decision is carried out, and the working quality and working efficiency of a platform region manager are improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the accompanying drawings of the specification. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
Fig. 1 is a flowchart of a method for identifying a running state of a zone according to the present exemplary embodiment;
fig. 2 is a flowchart of the offline analysis method and the online analysis method of the present exemplary embodiment;
fig. 3 is a block diagram of a platform running state identification system of the present exemplary embodiment;
fig. 4 is a schematic structural diagram of a station area operation state identifying apparatus of the present exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware units or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only and not necessarily all steps are included. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein.
Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or sub-modules is not necessarily limited to those steps or sub-modules that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or sub-modules that are not expressly listed.
Fig. 1 is a flowchart of a method for identifying a running state of a platform according to the present exemplary embodiment, and as shown in fig. 1, an exemplary embodiment of the present disclosure provides a method for identifying a running state of a platform, including:
s1, situation awareness data of the running state of a platform area are obtained;
s2, combining the data characteristics of the situation awareness data to construct a situation awareness feature library;
s3, clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature;
s4, calculating the score of each feature based on the mapping relation between the assignment interval and the score;
s5, constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value;
and S6, based on the grading of each feature and the final weight value of the feature, adopting a multi-element linear weighting algorithm to realize the state perception of the running state of the platform region.
The system is worth to say, the running state situation awareness data of the platform area are collected through an energy internet marketing service system, a new generation electricity information acquisition system and a PMS3.0 system.
The embodiment aims to provide a situation awareness-based platform region running state identification method, which aims to solve the problems that a power grid informationized lower platform region manager is large in management workload and low in efficiency, and comprehensive information of a platform region cannot be displayed in multiple directions.
Specifically, the method comprises the following steps: processing the characteristic data deletion and abnormality:
for quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
；
in the method, in the process of the invention,for data to be complemented, < >>For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
Specifically, the situation awareness data of the running state of the transformer area comprises acquisition time rate, acquisition coverage rate, metering equipment fault rate, fault list change rate, transformer area line loss qualification rate, transformer area calculation rate and wire theft loss inspection rate.
Specifically, the situation awareness feature library comprises seven dimensions of metering management, acquisition management, line loss management, anti-electricity-stealing monitoring, state evaluation, field management and operation and inspection management, wherein:
The metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
the acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
the state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
the operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
Specifically, S3, based on the situational awareness feature library, performs clustering processing on the situational awareness features, and forming an assignment interval of each feature includes:
Taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
in the formula, a sampleK represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
combining Silhouett eCoefficient, calinski-Harabasz and inartia score to analyze to form the characteristic optimal cluster category number;
and completing the division of the feature assignment interval based on the formed cluster category.
Specifically, S5, based on the situation awareness feature library, constructs a feature weight system, and calculating a feature final weight value includes:
respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
Specifically, the weight analysis using the principal component analysis method includes:
Extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: />；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Calculating contribution rate of each principal component based on load matrix：
；
In the method, in the process of the invention,representing the characteristic value of the ith main component, and h represents the total number of the characteristics of the main component;
calculating the importance of each feature：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
Specifically, the weight value under the on-site management dimension is automatically updated in real time based on the running frequency of the platform region running state identification model, and a real-time dynamic weight value is generated.
Specifically, based on the score of each feature and the final weight value of the feature, S6 adopts a multi-element linear weighting algorithm to realize the state perception of the running state of the platform region as follows:
；
wherein:scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
As shown in fig. 2, the invention discloses a situation awareness-based platform running state identification method, which comprises the following steps:
Step S1: collecting the running state analysis characteristic data of the platform region in the energy Internet marketing service system and the new generation electricity information acquisition system;
step S2: combining the feature classification mode to construct and form a state perception feature system of the running state of the platform region;
step S3: establishing a characteristic data deletion and exception handling strategy;
step S4: clustering the features based on a K-means clustering technology, and forming an assignment interval of each feature by combining descriptive statistical analysis;
step S5: constructing a feature weight system based on situation awareness features;
step S6: and (3) combining the step 4 and the step 5, and adopting a multi-element linear weighting algorithm to realize the situation awareness of the running state of the platform region.
Further, the characteristic data in the step S1 comprises the characteristics of acquisition time rate, acquisition coverage rate, metering equipment fault rate, fault meter change rate, station area line loss qualification rate, station area calculation rate, wire theft loss inspection rate and the like;
in the step S2, the 'platform region running state situation awareness characteristic system' comprises seven dimensions of metering management, acquisition management, line loss management, anti-electricity-stealing monitoring, state evaluation, field management and operation and inspection management. Wherein:
the metering management dimension covers the characteristics of metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio during transportation, high-voltage out-of-date duty ratio and the like;
The acquisition management dimension covers the characteristics of acquisition time rate, acquisition coverage rate, total acquisition success rate, continuous missing meter number and the like;
the state evaluation dimension covers the characteristics of the station area availability ratio, the electric energy meter availability ratio, the misalignment work order hit rate and the like;
the line loss management dimension covers the characteristics of the line loss qualification rate of the area, the daily line loss rate of the area, the monthly line loss rate of the area and the like;
the anti-electricity-stealing monitoring covers the characteristics of checking rate of wire theft, generating the number of electricity theft bill and the like;
the field management covers the characteristics of ' matching the power consumption requirement of a client side with the number of types of work orders, the average processing duration of an extended service work order, the number of ' suspected misalignment work orders ' out-of-date work orders and the like;
the operation and inspection management covers the characteristics of checking the unqualified quantity, the voltage qualification rate, the three-phase imbalance degree abnormality, the low-voltage power supply reliability and the like of one graph of the distribution network;
in step S3, "establishing a feature data missing and exception handling policy" specifically includes:
for quantitative non-unbalanced characteristics, such as remote recharging success rate, taking an average value of the last two non-null values before and after the leakage point as leakage point complement data, and adopting the following formula:
；
in the method, in the process of the invention,for data to be complemented, < >>For the previous time point data, +.>Is the next time point data.
For unbalanced features (e.g., file integrity rate, etc.), first, data observation is performed on the distribution of the qualitative features under the area, then the qualitative feature nulls are interpolated with feature values with relatively high distribution occupancy, and here filled with 100.
In the step S4, the characteristics are clustered based on the K-means clustering technology, and an assignment interval of each characteristic is formed by combining descriptive statistical analysis, wherein the K-means clustering process comprises the following steps:
(1) firstly, taking k sample points of a feature as initial centers of k clusters, wherein k is set to 3-9;
(2) for each sample point, the distance from k centers is calculated, and it is classified into the cluster where the center with the smallest distance is located, and the distance formula (euclidean distance) is as follows:
；
wherein the sample is；
(3) Waiting until all sample points are classified, and recalculating the centers of k clusters;
(4) the above process is repeated until the cluster into which the sample point belongs no longer changes.
Through the step, the characteristics are subjected to clustering analysis, and the characteristics are combined with silhouetteCoefficient analysis, calinski-Harabasz analysis and inartia score analysis to form the optimal clustering category number, so that the characteristic scoring is completed on the basis.
In step S5, "constructing a feature weight system based on situation awareness features" specifically includes:
and respectively adopting an analytic hierarchy process, a principal component analysis and an entropy weight discrimination method to carry out weight analysis, and finally carrying out weight fusion on the basis of a plurality of different weight algorithms to form a final weight. Wherein the main component analysis method comprises the following steps:
(1) Extracting standardized data, and standardizing a data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: />；/>；/>m；
(2) Calculating a load matrix between features by using principal component analysis；
(3) Calculating contribution rate of each principal component based on load matrix：
；
In the method, in the process of the invention,representing the characteristic value of the ith main component, and h represents the total number of the characteristics of the main component;
(4) calculating the importance of each feature：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
(5) calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
Based on the result, a gray correlation algorithm is adopted to fuse the results of a plurality of different weight algorithms, so as to form the final weight of the feature.
For the characteristics of the on-site management dimension (including the work order processing success rate, the work order processing time rate, the remote recharging work order completion rate and the like), the data characteristics have a certain amplitude change along with the time, and the weight value under the characteristic dimension is automatically updated in real time based on the model running frequency, so that the real-time dynamic weight is generated.
The step S6 of realizing the state sensing of the running state of the platform by adopting a multi-element linear weighting algorithm specifically comprises the steps of realizing the state sensing of the running state of the platform by adopting a linear regression algorithm on the basis of the steps S4 and S5, wherein the formula is as follows:
；
Wherein:、/>… … is a specific score for a feature, +.>、/>… … is a specific feature weight.
Fig. 3 is a block diagram of a system for identifying a running state of a zone according to the present exemplary embodiment, and as shown in fig. 3, the exemplary embodiment of the present disclosure provides a system for identifying a running state of a zone, including:
an acquiring unit 10, configured to acquire situation awareness data of an operation state of a platform area;
a construction unit 20, configured to combine the data characteristics of the situational awareness data to construct a situational awareness feature library;
the clustering unit 30 is configured to perform clustering processing on the situational awareness features based on the situational awareness feature library, so as to form an assignment interval of each feature;
a score calculating unit 40 for calculating a score of each feature based on a mapping relation between the assigned section and the score;
the weight calculation unit 50 is configured to construct a feature weight system based on the situation awareness feature library, and calculate a feature final weight value;
the weighting calculation unit 60 is configured to implement the situation awareness of the running state of the platform area by adopting a multi-element linear weighting algorithm based on the score of each feature and the final weight value of the feature.
Specifically, the method comprises the following steps: the processing unit is used for processing the characteristic data deletion and the abnormality;
The processing unit is specifically configured to:
for quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
；
in the method, in the process of the invention,for data to be complemented, < >>For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
Specifically, the situation awareness data of the running state of the transformer area comprises acquisition time rate, acquisition coverage rate, metering equipment fault rate, fault list change rate, transformer area line loss qualification rate, transformer area calculation rate and wire theft loss inspection rate.
Specifically, the situation awareness feature library comprises seven dimensions of metering management, acquisition management, line loss management, anti-electricity-stealing monitoring, state evaluation, field management and operation and inspection management, wherein:
the metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
the acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
The state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
the operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
Specifically, the clustering unit 30 is configured to:
taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
in the formula, a sampleK represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
Combining Silhouett eCoefficient, calinski-Harabasz and inartia score to analyze to form the characteristic optimal cluster category number;
and completing the division of the feature assignment interval based on the formed cluster category.
Specifically, the weight calculation unit 50 is configured to:
respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
Specifically, the weight analysis using the principal component analysis method includes:
extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines and n represents the matrix of the data lineThe number of three-level features, the matrix has the attribute: />；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Calculating contribution rate of each principal component based on load matrix：
；
In the method, in the process of the invention,represents the i-th principal component feature value, and h represents the total number of principal component features.
Calculating the importance of each feature：
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
Calculating feature weights：
；/>
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
The method specifically comprises a generation unit for automatically updating the weight value in the on-site management dimension in real time based on the running frequency of the platform region running state identification model to generate a real-time dynamic weight value.
Specifically, the formula of the weight calculation unit 60 is:
；
wherein:scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
To sum up, the situation awareness feature system is formed based on the related data features of the energy internet marketing service system, the new generation electricity information acquisition system and the PMS3.0 system carding platform area. And then clustering the features by adopting a K-means clustering algorithm, analyzing a feature assignment interval, carrying out weight analysis on a feature system by combining a plurality of weight algorithms, analyzing dynamic weights in real time aiming at on-site management dimensions, finally forming feature comprehensive weights, analyzing by utilizing a multi-element linear regression algorithm to form a platform situation sensing result, carrying out multi-azimuth, multi-angle and panoramic service display and real-time data monitoring on the basis, pushing the service terminal to efficiently cooperate, and timely finding out the existing problems through an imaging interface display, so as to realize the transition of 'finding' information to a system automatic 'pushing' information mode, help managers to get through data in all fields, improve the working quality and the working efficiency of a power-assisted platform manager, provide a guiding direction for the novel metering acquisition equipment to play on-site effect, and improve the management lean level of the platform in a multi-azimuth.
According to the invention, through 7 analysis dimensions of the platform region and combining with a big data analysis platform, situation awareness is carried out on the running state of the platform region in real time, the platform regions with different health degrees can be effectively screened under the conditions of large data quantity and data distortion, compared with the traditional management mode, the management efficiency is greatly improved, and the management efficiency is particularly improved for the platform regions such as a table 1 (management platform region information comparison table) and a table 2 (management platform region efficiency comparison table):
TABLE 1
TABLE 2
Fig. 4 is a schematic structural diagram of a station area operation state identifying apparatus of the present exemplary embodiment. As shown in fig. 4, the present invention further provides a device for identifying a running state of a platform, corresponding to the above-provided method for identifying a running state of a platform. Since the embodiments of the apparatus are similar to the method embodiments described above, the description is relatively simple, and reference should be made to the description of the method embodiments section described above, the apparatus described below being merely illustrative. The apparatus may include: a processor (processor) 1, a memory (memory) 2, and a communication bus (i.e., the above-mentioned device bus), and a search engine, wherein the processor 1 and the memory 2 complete communication with each other through the communication bus, and communicate with the outside through a communication interface. Processor 1 may invoke logic instructions in memory 2 to perform the zone operating state identification method.
Further, the logic instructions in the memory 2 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a Memory chip, a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
On the other hand, the embodiment of the present invention further provides a processor readable storage medium, on which a computer program 3 is stored, the computer program 3 being implemented when executed by the processor 1 to perform the method for identifying a running state of a platform provided in each of the above embodiments.
The processor-readable storage medium may be any available medium or data storage device that can be accessed by the processor 1 including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, nonvolatile storage (NANDFLASH), solid State Disk (SSD)), etc.
The above is only a preferred embodiment of the present disclosure, and the protection scope of the present disclosure is not limited to the above examples, but all technical solutions belonging to the concept of the present disclosure belong to the protection scope of the present disclosure. It should be noted that several modifications and adaptations to those skilled in the art without departing from the principles of the present disclosure should and are intended to be within the scope of the present disclosure.
Claims (20)
1. A method for identifying the running state of a station area, comprising the following steps:
acquiring situation awareness data of the running state of the platform region;
combining the data characteristics of the situation awareness data to construct a situation awareness feature library;
clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature;
calculating the score of each feature based on the mapping relation between the assignment interval and the score;
Constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value;
and based on the grading of each feature and the final weight value of the feature, adopting a multi-element linear weighting algorithm to realize the state perception of the running state of the platform region.
2. The method for identifying the running state of a station according to claim 1, comprising: processing the characteristic data deletion and abnormality:
for quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->For data to be complemented, < >>For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
3. The method for identifying the running state of a platform according to claim 2, wherein the situation awareness data of the running state of the platform comprises a collection time rate, a collection coverage rate, a metering equipment failure rate, a failure list change rate, a platform line loss qualification rate, a platform calculability rate and a theft line loss inspection rate.
4. The method for identifying a running state of a platform according to claim 3, wherein the situation awareness feature library comprises seven dimensions of metering management, collection management, line loss management, anti-electricity-theft monitoring, state evaluation, field management and operation inspection management, wherein:
The metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
the acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
the state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
the operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
5. The method for recognizing a running state of a platform according to claim 4, wherein clustering the situation awareness features based on the situation awareness feature library, forming an assignment interval of each feature comprises:
Taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
in the formula, a sampleK represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
combining the profile coefficient, the intra-class compactness and the intra-class cohesion analysis to form the characteristic optimal clustering class number;
and completing the division of the feature assignment interval based on the formed cluster category.
6. The method for recognizing a running state of a platform according to claim 4, wherein constructing a feature weight system based on the situation awareness feature library, and calculating a feature final weight value comprises:
respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
7. The method for recognizing an operation state of a station according to claim 6, wherein the weight analysis using the principal component analysis method comprises:
Extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: />；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Calculating contribution rate of each principal component based on load matrix：
；
In the method, in the process of the invention,representing the characteristic value of the ith main component, and h represents the total number of the characteristics of the main component;
calculate eachImportance of individual features：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
8. The method for recognizing the running state of a platform according to claim 6, wherein the weight value in the on-site management dimension is automatically updated in real time based on the running frequency of the running state recognition model of the platform, and a real-time dynamic weight value is generated.
9. The method for identifying a running state of a platform according to any one of claims 1 to 8, wherein a formula for realizing the situation awareness of the running state of the platform by adopting a multi-element linear weighting algorithm based on the score of each feature and the final weight value of the feature is as follows:
；
wherein: Scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
10. A system for identifying the operational status of a bay, comprising:
the acquisition unit is used for acquiring situation awareness data of the running state of the platform area;
the construction unit is used for combining the data characteristics of the situation awareness data to construct a situation awareness feature library;
the clustering unit is used for clustering the situation awareness features based on the situation awareness feature library to form an assignment interval of each feature;
the score calculating unit is used for calculating the score of each feature based on the mapping relation between the assigned interval and the score;
the weight calculation unit is used for constructing a feature weight system based on the situation awareness feature library and calculating a feature final weight value;
and the weighting calculation unit is used for realizing the situation awareness of the running state of the platform area by adopting a multi-element linear weighting algorithm based on the score of each feature and the final weight value of the feature.
11. The station operating state identification system of claim 10, comprising: the processing unit is used for processing the characteristic data deletion and the abnormality;
the processing unit is specifically configured to:
For quantitative non-unbalance characteristics, taking an average value of two non-null values before and after a leakage point as leakage point complement data, and adopting the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->For data to be complemented, < >>For the previous time point data, +.>Is the next time point data;
and for the unbalance characteristics, carrying out data observation on the distribution situation of the unbalance characteristics of the current station area, and interpolating the null value of the current unbalance characteristics by adopting the characteristic values with the distribution duty ratio meeting the set condition.
12. The system of claim 11, wherein the situational awareness data of the operational status of the area includes a time-of-acquisition rate, an acquisition coverage rate, a metering device failure rate, a failure list rate, an area line loss qualification rate, an area availability rate, and an electricity theft loss inspection rate.
13. The system for identifying the running state of a platform according to claim 12, wherein the situation awareness feature library comprises seven dimensions of metering management, collection management, line loss management, anti-electricity-theft monitoring, state evaluation, field management and operation inspection management, wherein:
the metering management dimension includes the features: metering equipment failure rate, failure meter change rate, file synchronization complete rate, old electricity meter duty ratio and high-voltage out-of-date duty ratio;
The acquisition management dimension includes the features: the acquisition time rate, the acquisition coverage rate, the total acquisition success rate and the number of continuous missing electric energy meters;
the state evaluation dimension includes the features: the station area calculation rate, the electric energy meter calculation rate and the misalignment work order hit rate;
the line loss management dimension includes the features: the station area line loss qualification rate, the station area daily line loss rate and the station area monthly line loss rate;
the anti-electricity-theft monitoring includes the following features: the checking rate of the wire theft cable and the number of the wire theft cable theft bill are generated;
the field management includes the features: the power consumption requirement of the client side is matched with the number of the type work orders, the average processing time length of the extended service work orders and the number of the suspected misaligned work orders exceeding the time length;
the operation and inspection management comprises the following characteristics: the distribution network has the advantages of overlong cable length of one graph, unconnected connection points, non-communication graph topology, untimely graph edge distribution, voltage qualification rate, abnormal three-phase unbalance degree and low-voltage power supply reliability.
14. The system for identifying a running state of a station according to claim 13, wherein the clustering unit is configured to:
taking k sample points of the feature as initial centers of k clusters;
calculating the distance between each sample point and k centers, and classifying each sample point into a cluster where the center with the smallest distance is located, wherein the distance formula is as follows:
；
In the formula, a sampleK represents the number of clusters, n represents the number of characteristic columns, p represents the Euclidean distance square and the evolution times, and 2 is taken here;
when all the sample points are classified, the centers of k clusters are recalculated until the clusters into which the sample points belong are no longer changed;
combining the profile coefficient, the intra-class compactness and the intra-class cohesion analysis to form the characteristic optimal clustering class number;
and completing the division of the feature assignment interval based on the formed cluster category.
15. The station operating state identification system according to claim 13, wherein the weight calculation unit is configured to:
respectively adopting an analytic hierarchy process, principal component analysis and an entropy weight discrimination method to carry out weight analysis;
based on a plurality of different weight algorithms, the gray correlation algorithm is adopted to fuse the results of the plurality of different weight algorithms to form a final weight value of the feature.
16. The system for identifying a running state of a station according to claim 15, wherein the weight analysis using the principal component analysis method comprises:
extracting the standardized data to form a standardized data matrix:
；
in the method, in the process of the invention,is +.>M represents the number of data lines, n represents the number of three-level features, and the matrix has the attribute: / >；/>；/>m；
Calculating a load matrix between features by using principal component analysis；
Load matrix based meterCalculating the contribution rate of each principal component：
；
In the method, in the process of the invention,representing the characteristic value of the ith main component, and h represents the total number of the characteristics of the main component;
calculating the importance of each feature：
；
In the method, in the process of the invention,linear combination coefficient as main component, +.>The contribution rate of the h main component is represented;
calculating feature weights：
；
In the method, in the process of the invention,the importance degree of each three-level characteristic is represented, and n represents the number of the three-level characteristics.
17. The system for recognizing the running state of a platform according to claim 15, comprising a generating unit for automatically updating the weight value in the on-site management dimension in real time based on the running frequency of the model for recognizing the running state of the platform, and generating a real-time dynamic weight value.
18. The system according to any one of claims 10 to 16, wherein the formula of the weight calculation unit is:
；
wherein:scoring the running state of the area,/->For a specific score of feature n, +.>Is the weight value of feature n.
19. A station operating state identifying apparatus, characterized by comprising:
a processor and a memory;
the memory is used for storing a computer program, and the processor calls the computer program stored in the memory to execute the method for identifying the running state of the area according to any one of claims 1 to 9.
20. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, enables the processor to perform the zone operating state identification method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311460992.1A CN117196540A (en) | 2023-11-06 | 2023-11-06 | Method, system, equipment and storage medium for identifying running state of platform area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311460992.1A CN117196540A (en) | 2023-11-06 | 2023-11-06 | Method, system, equipment and storage medium for identifying running state of platform area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117196540A true CN117196540A (en) | 2023-12-08 |
Family
ID=88990862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311460992.1A Pending CN117196540A (en) | 2023-11-06 | 2023-11-06 | Method, system, equipment and storage medium for identifying running state of platform area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196540A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN113159162A (en) * | 2021-04-19 | 2021-07-23 | 南京理工大学紫金学院 | Fault diagnosis method and system based on information fusion and grey correlation |
| CN114219245A (en) * | 2021-12-02 | 2022-03-22 | 国网浙江省电力有限公司 | Village power index evaluation method and device based on big data and storage medium |
| CN116862137A (en) * | 2023-05-29 | 2023-10-10 | 广东电网有限责任公司广州供电局 | Charging pile load flexible scheduling method and device based on data fusion |
-
2023
- 2023-11-06 CN CN202311460992.1A patent/CN117196540A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN113159162A (en) * | 2021-04-19 | 2021-07-23 | 南京理工大学紫金学院 | Fault diagnosis method and system based on information fusion and grey correlation |
| CN114219245A (en) * | 2021-12-02 | 2022-03-22 | 国网浙江省电力有限公司 | Village power index evaluation method and device based on big data and storage medium |
| CN116862137A (en) * | 2023-05-29 | 2023-10-10 | 广东电网有限责任公司广州供电局 | Charging pile load flexible scheduling method and device based on data fusion |
Non-Patent Citations (1)
| Title |
|---|
| 赵佩 等: "基于多维指标数据分析的台区健康智能体检研究设计", 《供用电》, pages 1 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN106384210B (en) | A kind of power transmission and transforming equipment maintenance prioritization method based on maintenance risk income | |
| CN107832855B (en) | Line loss multi-source diagnosis method and system based on correlation analysis | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN108376982B (en) | Load phase sequence identification method and device | |
| CN109856299A (en) | A kind of transformer online monitoring differentiation threshold value dynamic setting method, system | |
| CN107340492A (en) | Electric power meter failure analysis methods with scene anticipation are excavated based on big data | |
| CN106067088A (en) | E-bank accesses detection method and the device of behavior | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN108347352B (en) | Method for diagnosing performance of information system and equipment in power system | |
| Williams et al. | Electricity consumption and load profile segmentation analysis for rural micro grid customers in Tanzania | |
| CN108765189A (en) | Open shelf depreciation big data based on intelligent diagnostics algorithm manages system | |
| Babu et al. | Detecting unusual customer consumption profiles in power distribution systems—APSPDCL | |
| CN109816233A (en) | User tag model generating method and device for power grid | |
| CN107895212A (en) | Lead-acid battery life-span prediction method based on sliding window and various visual angles Fusion Features | |
| CN114386537A (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| CN111612326A (en) | Comprehensive evaluation method for power supply reliability of distribution transformer | |
| CN116205226A (en) | Power equipment state evaluation method, device, equipment and readable storage medium | |
| CN110348683A (en) | The main genetic analysis method, apparatus equipment of electrical energy power quality disturbance event and storage medium | |
| CN115563477A (en) | Harmonic data identification method and device, computer equipment and storage medium | |
| CN111178690A (en) | Electricity stealing risk assessment method for electricity consumers based on wind control scoring card model | |
| CN110555619A (en) | Power supply capacity evaluation method based on intelligent power distribution network | |
| Grigoras et al. | Processing of smart meters data for peak load estimation of consumers | |
| CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN112965990A (en) | Low-voltage contact cabinet fault solution generation method and device |
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 |