CN117171682A - Method and system for identifying abnormal electricity utilization users in electric power system - Google Patents
Method and system for identifying abnormal electricity utilization users in electric power system Download PDFInfo
- Publication number
- CN117171682A CN117171682A CN202310977886.4A CN202310977886A CN117171682A CN 117171682 A CN117171682 A CN 117171682A CN 202310977886 A CN202310977886 A CN 202310977886A CN 117171682 A CN117171682 A CN 117171682A
- Authority
- CN
- China
- Prior art keywords
- electricity
- user
- users
- clustering
- power system
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 187
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000013598 vector Substances 0.000 claims abstract description 93
- 230000006399 behavior Effects 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000003064 k means clustering Methods 0.000 claims abstract description 7
- 230000005856 abnormality Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001632422 Radiola linoides Species 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The method and the system for identifying the abnormal electricity utilization user in the electric power system are characterized by comprising the following steps: step 1, building an association relation between the electricity consumption of the electricity user and a scheduling plan of an electric power system based on historical electricity consumption data of the electricity user, and building a feature vector of the electricity user based on the association relation; step 2, classifying the electricity utilization users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity utilization users, and extracting typical characteristic vectors from the classification results; and step 3, calculating the similarity between the current electricity utilization user and the plurality of clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets a preset standard. The application accurately identifies abnormal electricity consumption of the user, organically connects with a dispatching plan of the power grid, realizes reasonable benefit maintenance for the electricity consumption user, realizes power supply protection and ensures safe and stable operation of the power grid.
Description
Technical Field
The application relates to the field of power systems, in particular to a method and a system for identifying abnormal electricity users in a power system.
Background
Currently, the power scheduling scheme of the peak-valley time of the traditional user side is formulated and executed by the electric power operation company, even the authority, and should be kept relatively fixed for a certain period of time. The abnormality of the user in the process of purchasing and using the electric energy may be not only from the abnormality of the used electric energy or the purchased electric energy itself, but also may be an abnormal factor caused in the process of trading the electric energy. For example, the power system does not reasonably collect the electricity purchasing behavior of the user, or the power system achieves the over-supply of the electric energy or the shortage supply of the electric energy, etc. in an abnormal mode, such as a mode not conforming to the schedule plan.
However, the method for identifying the abnormality of the supply and transaction of the user power in the prior art mainly aims at identifying the structural abnormality of the peak-valley time-sharing power, and focuses on analysis on the aspects of the user power consumption behavior, the power data and the like.
The electric energy users can be used as demand response centers to participate in the supply of electric energy under the situation of peak-valley time division, and the decisive role of the power grid terminal in the power resource optimization configuration is played from the user side. At this time, the problems of the demand of the user power, the power supply plan of the power grid and the like are more complex, and the influencing factors influencing the power grid dispatching relate to not only the simple power consumption demand of the user side, but also the power supply balance of the power grid side, the peak-valley adjusting capability of the power grid, the design of the spare capacity in the power grid, the climbing capability of the power generation equipment and the like. For example, the regulation of grid peaks and valleys by electricity prices can also affect to some extent the normal and safe operation of the electrical energy and power system.
In view of the foregoing, there is a need for a method and a system for identifying abnormal electricity users in an electric power system.
Disclosure of Invention
In order to solve the defects in the prior art, the application provides a method and a system for identifying abnormal electricity utilization users in an electric power system, and the classification of the electricity utilization users and the mining of typical users are realized by searching the association and the characteristics between the electricity utilization amount of the users and a power grid dispatching plan, so that the judgment of the abnormal electricity utilization behavior of single electricity utilization user is realized.
The application adopts the following technical scheme.
The first aspect of the application relates to a method for identifying abnormal electricity users in an electric power system, which comprises the following steps: step 1, based on historical electricity consumption data of electricity consumption users, constructing an association relation between electricity consumption of the electricity consumption users and a scheduling plan of an electric power system, and constructing a feature vector of the electricity consumption users based on the association relation; step 2, classifying the electricity users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity users, and extracting typical characteristic vectors from the classification result; and step 3, calculating the similarity between the current electricity utilization user and the clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets the preset standard.
Preferably, constructing the association relationship between the electricity consumption of the electricity consumer and the scheduling plan of the electric power system further includes: and extracting the electricity utilization time from the current electricity utilization data of the electricity utilization user, and acquiring a scheduling plan under the corresponding time based on the electricity utilization time.
Preferably, the characteristic vector of the electricity user comprises the peak-valley time-sharing electricity consumption characteristic of the electricity user and the peak-valley time-sharing scheduling plan characteristic of the electricity user.
Preferably, the feature vector is
Wherein, gamma n,i For the proportion of electricity at Gu Ping minutes from the peak of electricity consumer n at month iAnd->A vector formed by the two vectors; ρ n,i Scheduling parameters +.> And (5) a vector formed by the vector.
Preferably, feature vectors are built for all power utilization users in the power system, and clustering is realized on the basis of Euclidean distance between the feature vectors and a clustering center; and when the sum of the distances between all the seed points and the cluster centers where the seed points are positioned is smaller than a set threshold value, ending the current clustering, and obtaining a clustering result, wherein the clustering result comprises the positions of a plurality of cluster centers.
Preferably, presetting a value range of the number of clustering centers of a clustering algorithm, and carrying out current clustering on each value in the value range once; recording the clustering result of each current cluster, and evaluating the clustering result based on CH indexes; and sorting the rationality of the number of the clustering centers according to the evaluation.
Preferably, the positions of a plurality of cluster centers in all cluster center results are set as typical feature vectors, and the similarity between the feature vector of the current user and the typical feature vector is calculated; if the similarity between the characteristic vector of the current user and each typical characteristic vector is smaller than a set threshold value, judging that abnormal electricity utilization behaviors exist in the current user; and if the similarity between the characteristic vector of the current user and at least one typical characteristic vector is greater than or equal to a set threshold value, judging that the current user does not have abnormal electricity utilization behavior.
Preferably, the similarity is obtained by calculating a cosine similarity algorithm; and respectively calculating the similarity of the peak-valley time-sharing electricity consumption characteristics and the similarity of the peak-valley time-sharing scheduling plan characteristics in the characteristic vector.
Preferably, when the similarity between the peak-valley time-sharing electricity consumption characteristics of the current user and the typical characteristic vector is smaller than a set threshold value, judging that the current user has abnormal electricity consumption; and when the similarity between the peak-valley time-sharing scheduling plan features and the typical feature vectors of the current user is smaller than a set threshold value, judging that the current user has an abnormal electricity consumption plan.
The second aspect of the application relates to an identification system of abnormal electricity users in an electric power system, wherein the system is used for realizing the steps in the method of the first aspect of the application, and comprises a feature extraction module, a clustering module and an abnormality judgment module; the characteristic extraction module is used for constructing an association relation between the electricity consumption of the electricity user and a dispatching plan of the power system based on historical electricity consumption data of the electricity user, and constructing a characteristic vector of the electricity user based on the association relation; the clustering module is used for classifying the electricity utilization users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity utilization users, and extracting typical characteristic vectors from the classification results; and the abnormality judging module is used for calculating the similarity between the current electricity utilization user and the plurality of clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets a preset standard.
Compared with the prior art, the method and the system for identifying the abnormal electricity utilization users in the electric power system have the beneficial effects that the classification of the electricity utilization users and the mining of typical users are realized by searching the association and the characteristics between the electricity utilization amount of the users and the power grid dispatching plan, so that the judgment of the abnormal electricity utilization behaviors of the single electricity utilization user is realized. The method is effective and reliable, can accurately identify the abnormal electricity consumption behavior of the user, organically links the abnormal behavior with the scheduling plan of the power grid, can realize reasonable benefit maintenance for the electricity consumption user, realizes power supply protection, and ensures safe and stable operation of the power grid.
Drawings
FIG. 1 is a schematic flow chart of steps of a method for identifying abnormal electricity users in an electric power system according to the present application;
fig. 2 is a schematic diagram of an architecture of an identification system for abnormal electricity users in an electric power system according to the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. The described embodiments of the application are only some, but not all, embodiments of the application. All other embodiments of the application not described herein, which are obtained from the embodiments described herein, should be within the scope of the application by those of ordinary skill in the art without undue effort based on the spirit of the present application.
Fig. 1 is a schematic flow chart of steps of a method for identifying abnormal electricity users in an electric power system according to the present application. As shown in fig. 1, the first aspect of the present application relates to a method for identifying abnormal electricity users in an electric power system, and the method includes steps 1 to 3.
And step 1, based on historical electricity consumption data of the electricity consumption user, constructing an association relation between the electricity consumption of the electricity consumption user and a scheduling plan of the power system, and constructing a feature vector of the electricity consumption user based on the association relation.
It can be understood that the user electricity consumption in the application can be obtained from the platforms of the electricity collection system of the existing power grid, and in the process of obtaining, all the electricity consumption data in a period of time can be extracted according to the requirements of the accuracy degree and the like of judgment. For example, all power usage data for each user over a year. The electricity consumption data here should be able to represent the peak-to-valley difference of electricity consumption within 24 hours of a day. For example, the granularity of the electricity consumption data can be based on a period of 1 hour or 15 minutes, etc., and the data at different times in 24 hours a day can be collected and analyzed in a summarizing way.
It should be noted that, the scheduling plan of the power system in the present application may be one or more actual or virtual parameters, where the parameters can essentially reflect the power supply wish of the power system for the user at the current moment. And, this will to supply power should be determined according to the total demand of all consumers of power in the power system for the current period of time. According to the total power demand of the user in the current period, the power grid can be under consideration of various factors on the premise of meeting the load capacity of the power grid, such as whether equipment maintenance and outage are needed, whether more or less standby capacity is needed to be reserved, whether peak clipping and valley filling are needed, and the like, so as to determine the scheduling plan parameters.
In addition, the scheduling plan parameters in the application can be pre-calculated and generated according to various intelligent algorithms according to the operation and maintenance experience of the power grid.
Preferably, constructing the association relationship between the electricity consumption of the electricity consumer and the scheduling plan of the electric power system further includes: and extracting the electricity utilization time from the current electricity utilization data of the electricity utilization user, and acquiring a scheduling plan under the corresponding time based on the electricity utilization time.
In the application, after the association relation between the electricity consumption of the electricity consumption user and the scheduling plan of the power system is established, the electricity consumption distribution characteristics of different time periods can be obtained. Preferably, the characteristic vector of the electricity user comprises the peak-valley time-sharing electricity consumption characteristic of the electricity user and the peak-valley time-sharing scheduling plan characteristic of the electricity user.
Preferably, the feature vector is
Wherein, gamma n,i For the proportion of electricity at Gu Ping minutes from the peak of electricity consumer n at month iAnd->A vector formed by the two vectors;
ρ n,i scheduling plan parameters for peak-valley bisection by electricity consumer n at month iAnd (5) a vector formed by the vector.
It will be appreciated that vector R may be set n =(γ n,1 γ n,2 …γ n,11 γ n,12 ) In this vector, there is
In particular the number of the elements,the electric quantity ratios of peak section, flat section and valley Duan Fenshi of the user n months i respectively, q n For the annual energy of user n +.>The peak, flat and valley Duan Fenshi electric quantities of the user n months i respectively.
In addition, a vector P can also be set n =(ρ n,1 ρ n,2 … ρ n,11 ρ n,12 ) In the vector,
That is, the peak-to-valley bisecting scheduling plan parametersThe vectors mentioned above are composed.
In addition, the application can also design an overall anomaly index as follows:
the above index indicates, for any user n in an entire year, the matching degree between the overall electricity consumption situation and the power system scheduling plan, and the index can reflect the contribution degree of the power system to the individual electricity consumption users in the entire year.
And step 2, classifying the electricity users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity users, and extracting typical characteristic vectors from the classification result.
After the feature indexes are acquired, the application can realize the clustering of the users according to the feature vectors. Specifically, feature vectors are built for all power utilization users in the power system, and clustering is realized by taking Euclidean distance between the feature vectors and a clustering center as a basis; and when the sum of the distances between all the seed points and the cluster centers where the seed points are positioned is smaller than a set threshold value, ending the current clustering, and obtaining a clustering result, wherein the clustering result comprises the positions of a plurality of cluster centers.
It is understood that the clustering algorithm of the present application may first set the numerical interval and the initial iteration number of the user classification number. Then, each cluster center is initialized according to the number of user classifications. And then sequentially calculating Euclidean distance between the feature vector and the initial clustering center, distributing the user, namely the seed point, to different centers, and updating the clustering center under the condition that iteration is not completed.
The calculation formula of the Euclidean distance is as follows:
D(c k ,x n )=‖c k -x n ‖ 2
wherein c k Feature vector, x, of kth cluster center n Is the feature vector of user n. It is easily conceivable that the cluster center is obtained by averaging the positions of the feature vectors of all the seed points within the class, that is
In addition, the iteration ending of the clustering algorithm in the application should follow the aim that the value result of the objective function meets the requirement. In particular, the sum of the distances between all seed points and the cluster center in which they are located can be calculated, i.e
Finally, if the calculated result is smaller than the set threshold value, the calculated result can be judged to meet the requirement.
Preferably, a value range of the number of clustering centers of a clustering algorithm is preset, and each value in the value range is clustered once; recording the clustering result of each current cluster, and evaluating the clustering result based on CH indexes; and sorting the rationality of the number of the clustering centers according to the evaluation.
It can be understood that the clustering number of the clustering algorithm can be designed to meet a certain standard in the application. The criteria may be determined based on actual requirements, for example, based on experience of grid operators, and based on the various power loads connected to the power system. If there are only conventional commercial, industrial and residential users, the number of clusters may be relatively small, and if there are also various interruptible loads, including various electricity users participating in demand response, such as electric vehicles, new energy sources, etc., the number of clusters may also be increased accordingly.
The application can analyze whether the classification result is accurate or not by adopting the CH index. For example, using a calculation formula
In the formula, H is CH index value, B is covariance matrix between cluster center eigenvectors and eigenvectors of users contained in the cluster center eigenvectors, W is covariance matrix among the cluster center eigenvectors, tr (·) is trace of matrix, s is number of users, and u is number of user classifications.
It is easy to think that, after the CH values of the various clustering results are obtained, the sorting of the clustering results can also be implemented according to the situation of the CH index. The ranking can confirm the importance degree of the plurality of typical feature vectors in the step 3, and after the importance degree is determined, whether the user has abnormal electricity utilization behavior can be determined in a more simplified or more accurate manner according to the importance degree.
And step 3, calculating the similarity between the current electricity utilization user and the clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets the preset standard.
Preferably, the positions of a plurality of cluster centers in all cluster center results are set as typical feature vectors, and the similarity between the feature vector of the current user and the typical feature vector is calculated; if the similarity between the characteristic vector of the current user and each typical characteristic vector is smaller than a set threshold value, judging that abnormal electricity utilization behaviors exist in the current user; and if the similarity between the characteristic vector of the current user and at least one typical characteristic vector is greater than or equal to a set threshold value, judging that the current user does not have abnormal electricity utilization behavior.
By adopting the method of the application, the relation between each user and a plurality of typical users can be calculated.
It is easy to think that if the characteristics of a user are similar to all the cluster centers, it is explained that the user has a high probability of adopting various different electricity utilization modes or violating the willingness of the grid dispatching plan. On this basis, therefore, it can be determined that the user has an abnormality, such as power consumption not according to the requirements and will of the scheduling plan, or the like.
Preferably, the similarity is obtained by calculating a cosine similarity algorithm; and respectively calculating the similarity of the peak-valley time-sharing electricity consumption characteristics and the similarity of the peak-valley time-sharing scheduling plan characteristics in the characteristic vector.
The similarity calculation formula can be
Further, when the similarity between the peak-valley time-sharing electricity consumption characteristics of the current user and the typical characteristic vectors is smaller than a set threshold value, judging that the current user has abnormal electricity consumption; and when the similarity between the peak-valley time-sharing scheduling plan features and the typical feature vectors of the current user is smaller than a set threshold value, judging that the current user has an abnormal electricity consumption plan.
As described above, the method of the present application can more specifically determine whether the electricity consumption of the user has an abnormality in the peak-valley period or a conflict or difference with the scheduling plan.
Fig. 2 is a schematic diagram of an architecture of an identification system for abnormal electricity users in an electric power system according to the present application. As shown in fig. 2, in a second aspect of the present application, an identification system of an abnormal electricity user in an electric power system is provided, where the system is used to implement the steps in the method in the first aspect of the present application, and the system includes a feature extraction module, a clustering module, and an abnormality discrimination module; the characteristic extraction module is used for constructing an association relation between the electricity consumption of the electricity user and a dispatching plan of the power system based on historical electricity consumption data of the electricity user, and constructing a characteristic vector of the electricity user based on the association relation; the clustering module is used for classifying the electricity utilization users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity utilization users, and extracting typical characteristic vectors from the classification results; and the abnormality judging module is used for calculating the similarity between the current electricity utilization user and the plurality of clustering centers by taking the typical feature vector as a reference, and judging that abnormal electricity utilization behaviors exist in the current electricity utilization user if the similarity meets a preset standard.
It may be understood that, in order to implement each function in the method provided in the embodiment of the present application, the identification system in the present application includes a hardware structure and/or a software module that perform each function. Those of skill in the art will readily appreciate that the various illustrative algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The embodiment of the application can divide the functional modules of the identification system according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.
The system may be comprised of one or more devices connected by a communication link and the devices include at least one processor, a bus system, and at least one communication interface. The processor is comprised of a central processing unit, field programmable gate array, application specific integrated circuit, or other hardware. The memory is composed of a read-only memory, a random access memory and the like. The memory may be stand alone and coupled to the processor via a bus. The memory may also be integrated with the processor. The hard disk can be a mechanical disk or a solid state disk, etc. The embodiment of the present application is not limited thereto. The above embodiments are typically implemented in software, hardware. When implemented using a software program, may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions.
When the computer program instructions are loaded and executed on a computer, the corresponding functions are implemented according to the procedures provided by the embodiments of the present application. The computer program instructions referred to herein may be assembly instructions, machine instructions, or code written in a programming language implementation, or the like.
Compared with the prior art, the method and the system for identifying the abnormal electricity utilization users in the electric power system have the beneficial effects that the classification of the electricity utilization users and the mining of typical users are realized by searching the association and the characteristics between the electricity utilization amount of the users and the power grid dispatching plan, so that the judgment of the abnormal electricity utilization behaviors of the single electricity utilization user is realized. The method is effective and reliable, can accurately identify the abnormal electricity consumption behavior of the user, organically links the abnormal behavior with the scheduling plan of the power grid, can realize reasonable benefit maintenance for the electricity consumption user, realizes power supply protection, and ensures safe and stable operation of the power grid.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the specific embodiments of the application without departing from the spirit and scope of the application, which is intended to be covered by the claims.
Claims (10)
1. A method for identifying abnormal electricity users in an electric power system, the method comprising the steps of:
step 1, building an association relation between the electricity consumption of the electricity user and a scheduling plan of an electric power system based on historical electricity consumption data of the electricity user, and building a feature vector of the electricity user based on the association relation;
step 2, classifying the electricity utilization users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity utilization users, and extracting typical characteristic vectors from the classification results;
and step 3, calculating the similarity between the current electricity utilization user and the plurality of clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets a preset standard.
2. The method for identifying abnormal electricity users in an electric power system according to claim 1, wherein:
the building of the association relation between the electricity consumption of the electricity consumer and the scheduling plan of the power system further comprises:
and extracting electricity utilization time from the current electricity utilization amount data of the electricity utilization user, and acquiring a scheduling plan under the corresponding time based on the electricity utilization time.
3. The method for identifying abnormal electricity users in an electric power system according to claim 2, wherein:
the characteristic vector of the electricity user comprises the peak-valley time-sharing electricity consumption characteristic of the electricity user and the peak-valley time-sharing scheduling plan characteristic of the electricity user.
4. A method for identifying abnormal electricity users in an electrical power system according to claim 3, wherein:
the feature vector is
Wherein, gamma n,i For the proportion of electricity at Gu Ping minutes from the peak of electricity consumer n at month iAnd->A vector formed by the two vectors;
ρ n,i for peak-valley bisection time adjustment by electricity user n in month iDegree plan parametersAnd (5) a vector formed by the vector.
5. The method for identifying abnormal electricity users in an electric power system according to claim 4, wherein:
constructing feature vectors for all power utilization users in the power system, and clustering according to Euclidean distance between the feature vectors and a clustering center;
and when the sum of the distances between all the seed points and the cluster centers where the seed points are positioned is smaller than a set threshold value, ending the current clustering, and obtaining a clustering result, wherein the clustering result comprises the positions of the plurality of cluster centers.
6. The method for identifying abnormal electricity users in an electric power system according to claim 5, wherein:
presetting a value range of the number of clustering centers of a clustering algorithm, and carrying out one-time current clustering on each value in the value range;
recording a clustering result of each current cluster, and evaluating the clustering result based on CH indexes;
and sequencing the rationality of the number of the clustering centers according to the evaluation.
7. The method for identifying abnormal electricity users in an electric power system according to claim 6, wherein:
setting the positions of the plurality of clustering centers in all clustering center results as typical feature vectors, and calculating the similarity between the feature vectors of the current user and the typical feature vectors; wherein,
if the similarity between the characteristic vector of the current user and each typical characteristic vector is smaller than a set threshold value, judging that abnormal electricity utilization behaviors exist in the current user;
and if the similarity between the characteristic vector of the current user and at least one typical characteristic vector is greater than or equal to a set threshold value, judging that the current user does not have abnormal electricity utilization behavior.
8. The method for identifying abnormal electricity users in an electrical power system according to claim 7, wherein:
the similarity is obtained by adopting a cosine similarity algorithm; and, in addition, the processing unit,
and respectively calculating the similarity of the peak-valley time-sharing electricity consumption characteristics and the similarity of the peak-valley time-sharing scheduling plan characteristics in the characteristic vector.
9. The method for identifying abnormal electricity users in an electric power system according to claim 8, wherein:
when the similarity between the peak-valley time-sharing electricity consumption characteristics of the current user and the typical characteristic vector is smaller than a set threshold value, judging that the current user has abnormal electricity consumption;
and when the similarity between the peak-valley time-sharing scheduling plan features and the typical feature vectors of the current user is smaller than a set threshold value, judging that an abnormal electricity utilization plan exists for the current user.
10. An identification system of abnormal electricity users in an electric power system is characterized in that:
the system being for implementing the steps of the method of any one of claims 1-9, and,
the system comprises a feature extraction module, a clustering module and an abnormality discrimination module; wherein,
the characteristic extraction module is used for constructing an association relation between the electricity consumption of the electricity user and a dispatching plan of the power system based on historical electricity consumption data of the electricity user, and constructing a characteristic vector of the electricity user based on the association relation;
the clustering module is used for classifying the electricity utilization users by adopting a K-means clustering algorithm based on the characteristic vectors of the electricity utilization users, and extracting typical characteristic vectors from the classification results;
and the abnormality judging module is used for calculating the similarity between the current electricity utilization user and the plurality of clustering centers by taking the typical feature vector as a reference, and judging that the current electricity utilization user has abnormal electricity utilization behaviors if the similarity meets a preset standard.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310977886.4A CN117171682A (en) | 2023-08-04 | 2023-08-04 | Method and system for identifying abnormal electricity utilization users in electric power system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310977886.4A CN117171682A (en) | 2023-08-04 | 2023-08-04 | Method and system for identifying abnormal electricity utilization users in electric power system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117171682A true CN117171682A (en) | 2023-12-05 |
Family
ID=88942078
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310977886.4A Pending CN117171682A (en) | 2023-08-04 | 2023-08-04 | Method and system for identifying abnormal electricity utilization users in electric power system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117171682A (en) |
-
2023
- 2023-08-04 CN CN202310977886.4A patent/CN117171682A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhou et al. | Residential demand response targeting using machine learning with observational data | |
US10664931B2 (en) | Data analyzing system and method | |
CN111832861A (en) | Resident load variable-scale portrait method and system based on big data platform | |
CN116579590B (en) | Demand response evaluation method and system in virtual power plant | |
CN111582655B (en) | Power utilization system based on multi-user schedulable potential analysis | |
CN107248031B (en) | Rapid power consumer classification method aiming at load curve peak-valley difference | |
CN108428055B (en) | Load clustering method considering load longitudinal characteristics | |
Gao et al. | Spectral clustering based demand-oriented representative days selection method for power system expansion planning | |
CN114336651A (en) | Power dispatching method and device based on peak clipping potential | |
CN111028004A (en) | Market assessment analysis method based on big data technology | |
CN116821660A (en) | Power management method, system, terminal equipment and storage medium | |
CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
CN114611738A (en) | Load prediction method based on user electricity consumption behavior analysis | |
CN109389517B (en) | Analysis method and device for quantifying line loss influence factors | |
CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
CN117171682A (en) | Method and system for identifying abnormal electricity utilization users in electric power system | |
CN111861587A (en) | System and method for analyzing residential electricity consumption behavior based on hidden Markov model and forward algorithm | |
Colley et al. | Queensland load profiling by using clustering techniques | |
CN115081893A (en) | User electricity consumption data analysis method and device, electronic equipment and readable storage medium | |
Palakonda et al. | Differential evolution with stochastic selection for uncertain environments: A smart grid application | |
Ribeiro et al. | Data mining for prosumers aggregation considering the self-generation | |
CN114048200A (en) | User electricity consumption behavior analysis method considering missing data completion | |
CN113505943A (en) | Method, system, equipment and medium for predicting short-term load of power grid | |
Wang et al. | A Portrait-Based Method for Constructing Multi-Time Scale Demand Response Resource Pools | |
Tascikaraoglu | On Data-Driven Approaches for Demand Response |
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 |