CN113449793A - Method and device for determining power utilization state - Google Patents
Method and device for determining power utilization state Download PDFInfo
- Publication number
- CN113449793A CN113449793A CN202110723360.4A CN202110723360A CN113449793A CN 113449793 A CN113449793 A CN 113449793A CN 202110723360 A CN202110723360 A CN 202110723360A CN 113449793 A CN113449793 A CN 113449793A
- Authority
- CN
- China
- Prior art keywords
- data
- determining
- clustering
- cluster
- target
- 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 46
- 230000005611 electricity Effects 0.000 claims abstract description 66
- 238000012549 training Methods 0.000 claims abstract description 57
- 239000013598 vector Substances 0.000 claims abstract description 52
- 238000012545 processing Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 11
- 230000002159 abnormal effect Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for determining a power utilization state. Wherein, the method comprises the following steps: acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency; constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; and determining a cluster set matched with the current electricity utilization data of the target user, and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user.
Description
Technical Field
The invention relates to the field of electric power operation and maintenance, in particular to a method and a device for determining an electricity utilization state.
Background
The existing operation and maintenance method cannot realize real-time analysis of the electricity utilization condition of the power users, although a power supply company can call and measure the voltage and the current of the users in real time, the power supply company can only carry out preliminary analysis, and the method has the defects of low efficiency, poor purposiveness, high blindness and the like, and cannot find the abnormal condition of the electricity utilization in the homes of the users in time.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining a power utilization state, which at least solve the technical problem that abnormal power utilization conditions of a user at home cannot be found in time due to the fact that the power utilization conditions of power users cannot be analyzed in real time.
According to an aspect of an embodiment of the present invention, there is provided a method for determining a power consumption state, including: acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency; constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; and determining a cluster set matched with the current electricity utilization data of the target user, and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user.
Optionally, before constructing the training data set according to the plurality of electricity consumption data, the method further includes: and judging whether blank data exist in the power consumption data corresponding to each target user in the target user group, generating reasonable power consumption data corresponding to the blank data according to a target fitting function when the blank data exist, and replacing the blank data with the reasonable power consumption data, wherein the target fitting function is used for representing the functional relation between the type of the power consumption data corresponding to the blank data and the acquisition time.
Optionally, generating the electricity equitable data in place of the blank data comprises: determining the type of the electricity consumption data corresponding to the blank data and an acquisition time point; extracting power consumption data of a power consumption data type from multiple power consumption data of a target user, and constructing a target fitting function, wherein the independent variable of the target fitting function is acquisition time, and the dependent variable is the power consumption data of the power consumption data type; and determining that the electricity utilization data corresponding to the acquisition time points in the fitting function are reasonable electricity utilization data, and replacing blank data.
Optionally, clustering elements in the training data set to obtain a preset number of cluster sets, including: randomly selecting a preset number of initial clustering centers from each element in a training data set; respectively calculating the distance between each element in the remaining elements in the training data set and the initial clustering center, and allocating each element to the initial clustering center with the minimum distance to obtain a preset number of initial clustering sets; determining the average value of the values of all elements in all the elements in each initial cluster set in a preset number of initial cluster sets on each dimension, taking the average value of the values on each dimension as the value of a feature vector corresponding to a new cluster center on each dimension, calculating the distance between each element in the training data set and the new cluster center again, and distributing each element to the cluster center with the minimum distance to obtain a plurality of second cluster sets; and repeating the steps of determining the clustering centers and obtaining new clustering sets for the plurality of second clustering sets until each element in the training data set does not change the clustering set to which the element belongs, and determining the clustering set at the moment as a final clustering set, wherein the clustering center at the moment is the final clustering center.
Optionally, determining a set of clusters that match the current electricity usage data of the target user comprises: determining a target characteristic vector of current electricity utilization data; and obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
Optionally, after determining that the current cluster set is the final cluster set and the current cluster center is the final cluster center, the method further includes: and when the element increment in the training data set reaches a preset threshold value, repeating the steps of determining the clustering center and obtaining a new clustering set to obtain an updated final clustering set and a final clustering center.
Optionally, before clustering elements in the training data set to obtain a preset number of cluster sets, the method further includes: dividing a target user group into a plurality of types of power users according to historical power utilization data of the target user group; determining a characteristic parameter corresponding to each type of power consumer in multiple types of power consumers, wherein the characteristic parameter is the influence weight of values of different dimensions of a characteristic vector on a distance when the distance between any two characteristic vectors is determined; and determining the power consumer type corresponding to each element in the training data set, thereby determining the characteristic parameter corresponding to each element.
Optionally, determining a set of clusters that match the current electricity usage data of the target user comprises: determining a user type of a target user, and determining corresponding characteristic parameters according to the user type; determining a target characteristic vector of current electricity utilization data; and according to the characteristic parameters, obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for determining a power consumption state, including: the acquisition module is used for acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency; the processing module is used for constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; the clustering module is used for clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; and the matching module is used for determining a cluster set matched with the current electricity utilization data of the target user and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user.
According to another aspect of the embodiment of the present invention, there is also provided a nonvolatile storage medium, including a stored program, and a method for controlling a device in which the nonvolatile storage medium is located to perform power utilization state determination when the program is executed.
In the embodiment of the invention, various power consumption data of a target user group acquired according to a preset acquisition frequency are acquired; constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; the method comprises the steps of determining a cluster set matched with current power utilization data of a target user, determining a mode of determining the current power utilization state of the target user according to the power utilization state of the cluster set, clustering the power utilization data of a target user group and determining the corresponding power utilization state, achieving the purpose of determining the corresponding power utilization state according to the collected power utilization data, achieving the technical effect of determining the power utilization state of the user in real time, and further solving the technical problem that abnormal conditions of power utilization in the home of the user cannot be found in time due to the fact that the power utilization conditions of the power users cannot be analyzed in real time.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic flow chart of a method for determining a power usage status according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an apparatus for determining a power consumption state according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above 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 is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or 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 elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided a method embodiment of a method for determining a power usage state, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a method for determining a power usage state according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency;
in some embodiments of the present application, High-frequency, High-accuracy real-time collection of multiple Power consumption data of a target user group may be achieved based on an HPLC (High speed Power Line Communication) technology. For example, based on HPLC, it may be set to collect electricity usage data for a user every 15 minutes and store all collected electricity usage data in a database.
In some embodiments of the present application, the plurality of electricity consumption data of the target user group at least includes current data, voltage data, power factor, electricity consumption period and electricity consumption abnormal condition. The power utilization time interval can be used for determining whether the collected multiple types of power utilization data are data of a power utilization peak section or data of a power utilization valley section, and the power utilization abnormal conditions comprise that the current of a user is continuously zero, the current fluctuation is large, the voltage is too low or too high, and the like.
Step S104, constructing a training data set according to the multiple types of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple types of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the type quantity of the multiple types of power utilization data;
in some embodiments of the present application, multiple types of power consumption data acquired by a target user in a target acquisition time period are converted into corresponding feature vectors, and similarity between any two sets of data can be measured based on a distance between the feature vectors, where each set of data is multiple types of power consumption data acquired by the target user in any one target acquisition time period.
In some embodiments of the application, before a training data set is constructed according to multiple power consumption data, it is further required to determine whether blank data exists in the power consumption data corresponding to each group of data, and when it is determined that blank data exists, generate reasonable power consumption data corresponding to the blank data according to a target fitting function, and replace the blank data with the reasonable power consumption data, where the target fitting function is used to represent a functional relationship between a type of the power consumption data corresponding to the blank data and acquisition time.
In some embodiments of the present application, when collecting user data, if some data is not collected successfully, when the collected data is uploaded to the system, the system may find that blank data bits exist in the collected data, where the blank data bits are the blank data.
Specifically, the method for generating the reasonable electricity consumption data to replace the blank data comprises the following steps: determining the type of the electricity consumption data corresponding to the blank data and an acquisition time point; extracting power consumption data of a power consumption data type from multiple power consumption data of a target user, and constructing a target fitting function, wherein the independent variable of the target fitting function is acquisition time, and the dependent variable is the power consumption data of the power consumption data type; and determining that the electricity utilization data corresponding to the acquisition time points in the fitting function are reasonable electricity utilization data, and replacing blank data.
In some embodiments of the present application, the target fitting function is obtained by fitting according to historical electricity consumption data of a target user.
Step S106, clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to an electricity utilization state;
in some embodiments of the present application, the power utilization status includes a normal power utilization condition, an excessively long duration of zero current, an abnormal start of the user electrical appliance, an aging of the user electrical appliance, and the like.
In some embodiments of the application, the current power utilization state of the user can be preliminarily determined through the abnormal power utilization condition of the user collected by the HPLC, for example, when the current of the user is continuously zero, the user can analyze whether the user has a potential safety hazard through big data. When the current fluctuation occurs to the user, whether the user electrical appliance has the hidden danger of use aging can be analyzed. When the voltage of a user is too low or too high, the abnormal condition of the starting and the use of the electric appliance can be analyzed.
In some embodiments of the present application, clustering elements in a training data set to obtain a preset number of cluster sets is performed as follows: randomly selecting the preset number of initial clustering centers from each element in the training data set; respectively calculating the distance between each element in the remaining elements in the training data set and the initial clustering center, and allocating each element to the initial clustering center with the minimum distance to obtain the preset number of initial clustering sets; determining an average value of values of all elements in each initial cluster set in the preset number of initial cluster sets in each dimension, taking the average value of the values in each dimension as a value of a feature vector corresponding to a new cluster center in each dimension, calculating the distance between each element in the training data set and the new cluster center again, and allocating each element to the cluster center with the minimum distance to obtain a plurality of second cluster sets; and repeating the steps of determining the clustering centers and obtaining new clustering sets for the plurality of second clustering sets until each element in the training data set does not change the clustering set to which the element belongs, and determining the clustering set at the moment as a final clustering set, wherein the clustering center at the moment is the final clustering center.
In some embodiments of the application, since the collected power data is continuously increased along with the increase of time, in order to ensure the accuracy of the clustering result, after determining that the current cluster set is the final cluster set and that the current cluster center is the final cluster center, when the element increase in the training data set reaches a preset threshold value, the step of determining the cluster center repeatedly and obtaining a new cluster set is further required, so as to obtain the updated final cluster set and the updated final cluster center.
In some embodiments of the present application, different types of users have different electricity usage habits, for example, some users may have more business trips, and each item of electricity usage data may be 0 for a long time, but for the type of users, the state that each item of electricity usage data is 0 for a long time is a normal electricity usage state. Therefore, in clustering, the electricity consumption behavior characteristics of different types of power consumers also need to be considered. Specifically, before clustering elements in the training data set to obtain a preset number of cluster sets, the following steps are required: dividing the target user group into a plurality of types of power users according to the historical power utilization data of the target user group; determining a characteristic parameter corresponding to each type of power consumer in the multiple types of power consumers, wherein the characteristic parameter is the influence weight of values of different dimensions of a characteristic vector on a distance when the distance between any two characteristic vectors is determined; and determining the power consumer type corresponding to each element in the training data set, thereby determining the characteristic parameter corresponding to each element. The distance between the above feature vectors may be a euclidean distance, a manhattan distance, a chebyshev distance, a cosine distance, or the like, which is commonly used when performing K-means clustering.
To facilitate understanding of the above process, the above clustering process is explained below with reference to a specific example:
assuming that the feature vector corresponding to the final cluster center is (A, B) and the feature vector corresponding to a certain element is (C, D), the distance between the element and the cluster center is (A, B) when the influence of the user type on the feature parameter is not considered
When considering the influence of the user category on the characteristic parameter, the distance between the element and the cluster center is
Wherein k and l are characteristic parameters and take the real number more than or equal to zero. In this way, if the user type corresponding to the element is assumed, and there is no correlation between the data in the first dimension and the power consumption behavior, k may be set to 0, so as to avoid the influence of the data in the first dimension on the distance.
Step S108, determining a cluster set matched with the current electricity utilization data of the target user, and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user, wherein the target user can be all users in the target user group.
In some embodiments of the present application, the method of determining the cluster set that matches the current electricity usage data of the target user is: determining a target characteristic vector of current electricity utilization data; and obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
In some embodiments of the present application, determining a set of clusters that match the current electricity usage data of the target user while taking into account the impact of the user type on the matching results includes: determining a user type of a target user, and determining corresponding characteristic parameters according to the user type; determining a target characteristic vector of current electricity utilization data; and according to the characteristic parameters, obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
In some embodiments of the application, after the current power utilization state is obtained, if the worker considers that the determination result does not conform to the actual situation, the worker may feed back the actual power utilization state to the determination model, and then the determination model may re-execute the clustering process based on the feedback.
In some embodiments of the application, after the power consumption condition of the target user is determined, a diagnosis and analysis result can be automatically generated according to the power consumption condition and automatically sent to each company and staff in a supervision mode, and the staff can carry out targeted service work according to the diagnosis result. Through to electric current, voltage data acquisition and intelligent diagnosis analysis, go to the diagnostic result and supervise and manage, all realized real-time, automated processing, realized current, the voltage curve that exists in real-time supervision user's family to accurate locking power consumption anomaly user, and provide professional technical support, go on the door to the customer when necessary and serve, investigate power consumption potential safety hazard, eliminate the power consumption trouble. The problem in the user power consumption process has been solved to the efficient, has improved staff's quality of service and service efficiency.
Through the steps, various power consumption data of the target user group acquired according to the preset acquisition frequency are acquired; constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; the method comprises the steps of determining a cluster set matched with current power utilization data of a target user, determining a mode of determining the current power utilization state of the target user according to the power utilization state of the cluster set, clustering the power utilization data of a target user group and determining the corresponding power utilization state, achieving the purpose of determining the corresponding power utilization state according to the collected power utilization data, achieving the technical effect of determining the power utilization state of the user in real time, and further solving the technical problem that abnormal conditions of power utilization in the home of the user cannot be found in time due to the fact that the power utilization conditions of the power users cannot be analyzed in real time.
Example 2
According to an embodiment of the present invention, there is provided an apparatus embodiment of a device for determining a power consumption state, and fig. 2 is a method for determining a power consumption state according to an embodiment of the present invention, as shown in fig. 2, the device includes: the acquisition module 20 is used for acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency; the processing module 22 is configured to construct a training data set according to multiple types of power consumption data, where each element in the training data set is any one target user in a target user group, and a feature vector of multiple types of power consumption data is acquired in any one target acquisition time period, and a dimension of the feature vector is the same as the number of the types of the multiple types of power consumption data; the clustering module 24 is configured to cluster elements in the training data set to obtain a preset number of cluster sets, where each cluster set in the preset number of cluster sets corresponds to an electricity utilization state; and the matching module 26 is used for determining a cluster set matched with the current electricity utilization data of the target user and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user.
Since the determination device of the power consumption state described in the embodiment of the present application can be used to execute the determination method of the power consumption state described in the above embodiment 1, the description related to embodiment 1 is also applicable to the embodiment of the present application.
In some embodiments of the present application, there is also provided a nonvolatile storage medium for storing a program, wherein the program controls, when executed, an apparatus in which the nonvolatile storage medium is located to perform the following determination method of the power usage state: acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency; constructing a training data set according to the multiple kinds of power utilization data, wherein each element in the training data set is any one target user in a target user group, the feature vectors of the multiple kinds of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple kinds of power utilization data; clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state; and determining a cluster set matched with the current electricity utilization data of the target user, and determining the electricity utilization state of the cluster set as the current electricity utilization state of the target user.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for determining a power usage state, comprising:
acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency;
constructing a training data set according to the multiple types of power utilization data, wherein each element in the training data set is any one target user in the target user group, the feature vectors of the multiple types of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the multiple types of power utilization data;
clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to one power utilization state;
and determining a target cluster set matched with the current electricity utilization data of the target user from the preset number of cluster sets, and determining the electricity utilization state of the target cluster set as the current electricity utilization state of the target user.
2. The method of claim 1, wherein prior to constructing a training data set from the plurality of electricity usage data, the method further comprises:
and judging whether blank data exist in the power consumption data corresponding to each target user in the target user group, generating reasonable power consumption data corresponding to the blank data according to a target fitting function when the blank data exist, and replacing the blank data with the reasonable power consumption data, wherein the target fitting function is used for representing a functional relation between the type of the power consumption data corresponding to the blank data and acquisition time.
3. The method of claim 2, wherein generating legitimate power usage data to replace the blank data comprises:
determining the type of the electricity consumption data corresponding to the blank data and an acquisition time point;
extracting power utilization data of the power utilization data type from multiple types of power utilization data of the target user, and constructing the target fitting function, wherein the independent variable of the target fitting function is acquisition time, and the dependent variable is the power utilization data of the power utilization data type;
and determining the electricity utilization data corresponding to the acquisition time points in the fitting function as the reasonable electricity utilization data, and replacing the blank data.
4. The method of claim 1, wherein clustering elements in the training data set to obtain a preset number of cluster sets comprises:
randomly selecting the preset number of initial clustering centers from each element in the training data set;
respectively calculating the distance between each element in the remaining elements in the training data set and the initial clustering center, and allocating each element to the initial clustering center with the minimum distance to obtain the preset number of initial clustering sets;
determining an average value of values of all elements in each initial cluster set in the preset number of initial cluster sets in each dimension, taking the average value of the values in each dimension as a value of a feature vector corresponding to a new cluster center in each dimension, calculating the distance between each element in the training data set and the new cluster center again, and allocating each element to the cluster center with the minimum distance to obtain a plurality of second cluster sets;
and repeating the steps of determining the clustering centers and obtaining new clustering sets for the plurality of second clustering sets until each element in the training data set does not change the clustering set to which the element belongs, and determining the clustering set at the moment as a final clustering set, wherein the clustering center at the moment is the final clustering center.
5. The method of claim 4, wherein determining a set of clusters that match current electricity usage data of a target user comprises:
determining a target feature vector of the current electricity utilization data;
and obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
6. The method of claim 4, wherein after determining that the cluster set at the time is the final cluster set and the cluster center at the time is the final cluster center, the method further comprises:
and when the element increment in the training data set reaches a preset threshold value, repeating the steps of determining the clustering center and obtaining a new clustering set to obtain an updated final clustering set and a final clustering center.
7. The method of claim 4, wherein before clustering the elements in the training data set to obtain a predetermined number of cluster sets, the method further comprises:
dividing the target user group into a plurality of types of power users according to the historical power utilization data of the target user group;
determining a characteristic parameter corresponding to each type of power consumer in the multiple types of power consumers, wherein the characteristic parameter is the influence weight of values of different dimensions of a characteristic vector on a distance when the distance between any two characteristic vectors is determined;
and determining the power consumer type corresponding to each element in the training data set, thereby determining the characteristic parameter corresponding to each element.
8. The method of claim 7, wherein determining a set of clusters that match current electricity usage data of a target user comprises:
determining the user type of the target user, and determining corresponding characteristic parameters according to the user type;
determining a target feature vector of the current electricity utilization data;
and according to the characteristic parameters, obtaining the distance between the target characteristic vector and each final clustering center, and determining the final clustering set corresponding to the final clustering center closest to the target characteristic vector as the clustering set corresponding to the current power utilization data.
9. An apparatus for determining a power consumption state, comprising:
the acquisition module is used for acquiring various power consumption data of a target user group acquired according to a preset acquisition frequency;
the processing module is used for constructing a training data set according to the multiple types of power utilization data, wherein each element in the training data set is any one target user in the target user group, the feature vectors of the multiple types of power utilization data are acquired in any one target acquisition time period, and the dimensionality of the feature vectors is the same as the number of the types of the multiple types of power utilization data;
the clustering module is used for clustering elements in the training data set to obtain a preset number of cluster sets, wherein each cluster set in the preset number of cluster sets corresponds to an electricity utilization state;
and the matching module is used for determining a target cluster set matched with the current electricity utilization data of the target user from the preset number of cluster sets and determining the electricity utilization state of the target cluster set as the current electricity utilization state of the target user.
10. A non-volatile storage medium, comprising a stored program, wherein when the program runs, a device in which the non-volatile storage medium is located is controlled to execute the power usage state determination method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110723360.4A CN113449793A (en) | 2021-06-28 | 2021-06-28 | Method and device for determining power utilization state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110723360.4A CN113449793A (en) | 2021-06-28 | 2021-06-28 | Method and device for determining power utilization state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113449793A true CN113449793A (en) | 2021-09-28 |
Family
ID=77813595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110723360.4A Pending CN113449793A (en) | 2021-06-28 | 2021-06-28 | Method and device for determining power utilization state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449793A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681186A (en) * | 2023-08-03 | 2023-09-01 | 深圳友讯达科技股份有限公司 | Power quality analysis method and device based on intelligent terminal |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229602A (en) * | 2017-05-22 | 2017-10-03 | 湘潭大学 | A kind of recognition methods of intelligent building microgrid electricity consumption behavior |
| CN108460410A (en) * | 2018-02-08 | 2018-08-28 | 合肥工业大学 | Electricity consumption mode identification method and system, the storage medium of citizen requirement side |
| CN108765194A (en) * | 2018-05-29 | 2018-11-06 | 深圳源广安智能科技有限公司 | A kind of effective residential electricity consumption behavior analysis system |
| CN108830324A (en) * | 2018-06-20 | 2018-11-16 | 国网上海市电力公司 | A kind of public building multiplexing electric abnormality method of discrimination based on data mining technology |
| CN108920790A (en) * | 2018-06-20 | 2018-11-30 | 国网上海市电力公司 | A kind of public building electricity consumption pattern recognition model method for building up based on historical data |
| CN109241190A (en) * | 2018-09-12 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Electric power big data mixes computing architecture |
| CN109492048A (en) * | 2019-01-21 | 2019-03-19 | 国网河北省电力有限公司经济技术研究院 | A kind of extracting method, system and the terminal device of power consumer electrical characteristics |
| CN109829571A (en) * | 2019-01-11 | 2019-05-31 | 国网浙江省电力有限公司 | A kind of short-term electricity demand forecasting method of user based on multilist fused data |
| CN110321934A (en) * | 2019-06-12 | 2019-10-11 | 深圳供电局有限公司 | Method and system for detecting abnormal data of user electricity consumption |
| CN110674999A (en) * | 2019-10-08 | 2020-01-10 | 国网河南省电力公司电力科学研究院 | Cell load prediction method based on improved clustering and long-short term memory deep learning |
| CN110781332A (en) * | 2019-10-16 | 2020-02-11 | 三峡大学 | Electric power resident user daily load curve clustering method based on composite clustering algorithm |
| CN111126499A (en) * | 2019-12-25 | 2020-05-08 | 国网河北省电力有限公司 | Secondary clustering-based power consumption behavior pattern classification method |
| CN111476438A (en) * | 2020-05-18 | 2020-07-31 | 南方电网科学研究院有限责任公司 | Method, system and equipment for predicting power consumption of user |
| CN111626614A (en) * | 2020-05-27 | 2020-09-04 | 国网上海市电力公司 | User classification method based on electric charge recovery |
| CN111667022A (en) * | 2020-06-30 | 2020-09-15 | 腾讯科技（深圳）有限公司 | User data processing method and device, computer equipment and storage medium |
| CN111914900A (en) * | 2020-07-03 | 2020-11-10 | 深圳供电局有限公司 | User power consumption mode classification method |
| CN112308462A (en) * | 2020-11-23 | 2021-02-02 | 国网北京市电力公司 | Power consumer classification method and device |
| CN112365029A (en) * | 2019-09-03 | 2021-02-12 | 深圳市得益节能科技股份有限公司 | Missing value processing method for air conditioner load prediction and air conditioner load prediction system |
| CN112733969A (en) * | 2021-03-31 | 2021-04-30 | 北京达佳互联信息技术有限公司 | Object class identification method and device and server |
-
2021
- 2021-06-28 CN CN202110723360.4A patent/CN113449793A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229602A (en) * | 2017-05-22 | 2017-10-03 | 湘潭大学 | A kind of recognition methods of intelligent building microgrid electricity consumption behavior |
| CN108460410A (en) * | 2018-02-08 | 2018-08-28 | 合肥工业大学 | Electricity consumption mode identification method and system, the storage medium of citizen requirement side |
| CN108765194A (en) * | 2018-05-29 | 2018-11-06 | 深圳源广安智能科技有限公司 | A kind of effective residential electricity consumption behavior analysis system |
| CN108830324A (en) * | 2018-06-20 | 2018-11-16 | 国网上海市电力公司 | A kind of public building multiplexing electric abnormality method of discrimination based on data mining technology |
| CN108920790A (en) * | 2018-06-20 | 2018-11-30 | 国网上海市电力公司 | A kind of public building electricity consumption pattern recognition model method for building up based on historical data |
| CN109241190A (en) * | 2018-09-12 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Electric power big data mixes computing architecture |
| CN109829571A (en) * | 2019-01-11 | 2019-05-31 | 国网浙江省电力有限公司 | A kind of short-term electricity demand forecasting method of user based on multilist fused data |
| CN109492048A (en) * | 2019-01-21 | 2019-03-19 | 国网河北省电力有限公司经济技术研究院 | A kind of extracting method, system and the terminal device of power consumer electrical characteristics |
| CN110321934A (en) * | 2019-06-12 | 2019-10-11 | 深圳供电局有限公司 | Method and system for detecting abnormal data of user electricity consumption |
| CN112365029A (en) * | 2019-09-03 | 2021-02-12 | 深圳市得益节能科技股份有限公司 | Missing value processing method for air conditioner load prediction and air conditioner load prediction system |
| CN110674999A (en) * | 2019-10-08 | 2020-01-10 | 国网河南省电力公司电力科学研究院 | Cell load prediction method based on improved clustering and long-short term memory deep learning |
| CN110781332A (en) * | 2019-10-16 | 2020-02-11 | 三峡大学 | Electric power resident user daily load curve clustering method based on composite clustering algorithm |
| CN111126499A (en) * | 2019-12-25 | 2020-05-08 | 国网河北省电力有限公司 | Secondary clustering-based power consumption behavior pattern classification method |
| CN111476438A (en) * | 2020-05-18 | 2020-07-31 | 南方电网科学研究院有限责任公司 | Method, system and equipment for predicting power consumption of user |
| CN111626614A (en) * | 2020-05-27 | 2020-09-04 | 国网上海市电力公司 | User classification method based on electric charge recovery |
| CN111667022A (en) * | 2020-06-30 | 2020-09-15 | 腾讯科技（深圳）有限公司 | User data processing method and device, computer equipment and storage medium |
| CN111914900A (en) * | 2020-07-03 | 2020-11-10 | 深圳供电局有限公司 | User power consumption mode classification method |
| CN112308462A (en) * | 2020-11-23 | 2021-02-02 | 国网北京市电力公司 | Power consumer classification method and device |
| CN112733969A (en) * | 2021-03-31 | 2021-04-30 | 北京达佳互联信息技术有限公司 | Object class identification method and device and server |
Non-Patent Citations (2)
| Title |
|---|
| SUNGSIK PARK等: "Photovoltaic Power Data Analysis Using Hierarchical Clustering", 《ICOIN》, pages 727 - 731 * |
| 顾玮: "基于海量数据挖掘的居民用电行为分析与互动方法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, pages 042 - 1243 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681186A (en) * | 2023-08-03 | 2023-09-01 | 深圳友讯达科技股份有限公司 | Power quality analysis method and device based on intelligent terminal |
| CN116681186B (en) * | 2023-08-03 | 2024-01-12 | 深圳友讯达科技股份有限公司 | Power quality analysis method and device based on intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310120B (en) | Abnormal electricity utilization user identification method, device, terminal and medium based on big data | |
| CN111244954A (en) | Non-invasive load identification method and device | |
| CN114819665B (en) | Distributed energy management-based abnormity early warning method and system | |
| CN107248086A (en) | Advertisement putting aided analysis method based on user power utilization behavioural analysis | |
| CN107945050B (en) | Method and device for identifying and identifying type of electricity customer and central server | |
| CN110068117B (en) | Air conditioner performance continuous monitoring system and method | |
| CN116976707A (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| CN112308459A (en) | Power grid household transformation relation identification method and identification device, and electronic equipment | |
| CN113449793A (en) | Method and device for determining power utilization state | |
| CN111476438A (en) | Method, system and equipment for predicting power consumption of user | |
| Kojury-Naftchali et al. | Identifying susceptible consumers for demand response and energy efficiency policies by time-series analysis and supplementary approaches | |
| Fernandes et al. | Analysis of residential natural gas consumers using fuzzy c-means clustering | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| Lima de Menezes et al. | Electricity consumption forecasting using singular spectrum analysis | |
| CN111080487A (en) | Electricity sales market electricity quantity prediction method and device | |
| Islam et al. | Load profile segmentation using residential energy consumption data | |
| CN115935267A (en) | Load data identification method and device and storage medium | |
| CN113326296B (en) | Load decomposition method and system suitable for industrial and commercial users | |
| CN115420988A (en) | Method, device, equipment and storage medium for identifying abnormal electricity users | |
| CN111612221B (en) | Factory work efficiency statistical method based on current fingerprint technology | |
| CN111580839B (en) | Upgrading method and device for electrical equipment | |
| Neagu et al. | Data Mininig Tools in Electricity Distribution Systems | |
| CN105160024A (en) | Big data power utilization analysis system and method | |
| Davarzani et al. | Study of missing meter data impact on domestic load profiles clustering and characterization | |
| CN110807589A (en) | Case analysis system of electric power spot market |
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 |