CN115392715A - Power utilization data risk assessment method, device, equipment and storage medium - Google Patents
Power utilization data risk assessment method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115392715A CN115392715A CN202211027287.8A CN202211027287A CN115392715A CN 115392715 A CN115392715 A CN 115392715A CN 202211027287 A CN202211027287 A CN 202211027287A CN 115392715 A CN115392715 A CN 115392715A
- Authority
- CN
- China
- Prior art keywords
- data
- data set
- characteristic value
- encoder
- self
- 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 51
- 238000012502 risk assessment Methods 0.000 title claims abstract description 24
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000005611 electricity Effects 0.000 claims abstract description 64
- 238000013210 evaluation model Methods 0.000 claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 238000003062 neural network model Methods 0.000 claims abstract description 28
- 238000009826 distribution Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power utilization data risk assessment method, a device, equipment and a storage medium. The method comprises the following steps: reading historical power consumption data of each user in the power distribution network, and constructing an evaluation model according to the historical power consumption data, wherein the evaluation model comprises a first self-encoder, a second self-encoder and a full-connection neural network model; acquiring power consumption data to be detected, and grading the power consumption data to be detected through an evaluation model to generate a grading result; and determining the risk level of the electricity consumption data to be measured according to the grading result. An evaluation model is built through historical electricity utilization data, electricity utilization data to be detected are scored through the pre-built evaluation model, finally, the risk grade can be accurately determined through the scoring result according to the mode that the risk grade is determined according to the scoring result, the evaluation accuracy is improved, personnel do not need to go to the site for inspection, manpower resources are saved, and meanwhile, the risk evaluation efficiency is improved.
Description
Technical Field
The invention relates to the field of risk assessment, in particular to a method, a device, equipment and a storage medium for assessing power consumption data risk.
Background
The power resource is an important social resource applied to various production activities and daily activities in the current social development of China, and is objectively related to industrial production efficiency of China to a certain extent, and the current power enterprise faces the situation that the users of the power enterprise have illegal power utilization behaviors in the power utilization process.
However, in actual work, after an electric power enterprise finds that users have illegal abnormal electricity utilization behaviors, personnel are usually assigned to the electric power metering devices corresponding to all abnormal users to perform on-site investigation and eliminate abnormal risks, or the abnormal degree of the risks of the users is analyzed and classified according to original historical data, manual experience and priori knowledge, so as to evaluate the inspection level of the electricity utilization users.
In the prior art, the method for on-site investigation of the delegation personnel is low in efficiency, and error is large when the delegation personnel is divided by only depending on historical data and manual experience through manpower, so that misjudgment is easily caused on risk levels.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for evaluating the risk of electricity utilization data, which are used for evaluating the risk level of an electricity utilization user.
According to an aspect of the present invention, there is provided a power consumption data risk assessment method, including:
reading historical power consumption data of each user in the power distribution network, and constructing an evaluation model according to the historical power consumption data, wherein the evaluation model comprises a first self-encoder, a second self-encoder and a full-connection neural network model;
acquiring power consumption data to be detected, and grading the power consumption data to be detected through an evaluation model to generate a grading result;
and determining the risk level of the electricity consumption data to be detected according to the grading result.
Preferably, the method for obtaining the electricity data to be measured and scoring the electricity data to be measured through the evaluation model to generate a scoring result includes: preprocessing power consumption data to be detected to generate a data set; processing the data set through a first self-encoder to obtain a data reconstruction error and a first characteristic value of the data set, wherein the first self-encoder comprises an encoding layer and a decoding layer; processing the first characteristic value of the data set through a second self-encoder to obtain a characteristic reconstruction error, a hidden characteristic value of the first characteristic value and a second characteristic value of the data set; processing the second characteristic value through a full-connection neural network model to generate a Gaussian score; and generating a grading result according to the data reconstruction error, the characteristic reconstruction error and the Gaussian score.
Preferably, the processing the data set by the first self-encoder to obtain the data reconstruction error and the first characteristic value of the data set includes: performing feature extraction on the data set through the coding layer to obtain a first feature value of the data set; reconstructing the data set through a decoding layer to obtain a reconstructed data set; data reconstruction errors are obtained from the data set and the reconstructed data set.
Preferably, the processing, by the second encoder, the first feature value of the data set to obtain the feature reconstruction error, the hidden feature value of the first feature value, and the second feature value of the data set includes: reconstructing the first characteristic value through a second self-encoder to obtain a reconstructed characteristic value of the data set; coding the first characteristic value through a second self-coder to obtain a hidden characteristic value of the first characteristic value; acquiring a characteristic reconstruction error according to the reconstruction characteristic value and the first characteristic value of the data set; and acquiring the Euclidean distance and cosine similarity of the reconstructed characteristic value and the first characteristic value of the data set, and acquiring a second characteristic value of the data set according to the Euclidean distance, the cosine similarity and the hidden characteristic value.
Preferably, the processing the second feature value through the fully connected neural network model to generate a gaussian score includes: calculating a second characteristic value of the data set by adopting a maximum expectation algorithm EM through a full-connection neural network model, and acquiring an attribution probability corresponding to the second characteristic value of the data set; calculating through the attribution probability and a second characteristic value of the data set to obtain a score calculation correlation parameter of the full-connection neural network model; and generating a Gaussian score according to the correlation parameter and the second characteristic value of the data set.
Preferably, generating a scoring result according to the data reconstruction error, the feature reconstruction error and the gaussian score includes: taking the data reconstruction error, the characteristic reconstruction error and the Gaussian fraction as evaluation indexes, and acquiring a weighted value corresponding to each evaluation index; and sequentially adding the products of the evaluation indexes and the weighted values corresponding to the evaluation indexes to obtain a scoring result.
Preferably, the determining the risk level of the electricity consumption data to be measured according to the scoring result includes: determining a score interval corresponding to a scoring result; and determining the risk grade of the power utilization data to be detected according to the fraction interval.
According to another aspect of the present invention, there is provided an electricity data risk assessment apparatus, including:
the evaluation model building module is used for reading historical power consumption data of each user in the power distribution network and building an evaluation model according to the historical power consumption data, wherein the evaluation model comprises a first self-encoder, a second self-encoder and a fully-connected neural network model;
the scoring result generation module is used for acquiring the power consumption data to be detected and scoring the power consumption data to be detected through the evaluation model to generate a scoring result;
and the risk grade determining module is used for determining the risk grade of the power consumption data to be measured according to the grading result.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method for risk assessment of electricity consumption data according to any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a method for risk assessment of electricity consumption data according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme of the embodiment of the invention, the evaluation model is constructed through the historical electricity utilization data, the electricity utilization data to be detected is graded through the pre-constructed evaluation model, and finally the risk grade can be accurately determined through the grading result in a mode of determining the risk grade according to the grading result, so that the evaluation accuracy is improved, personnel are not required to go to the site for inspection, the manpower resource is saved, and the risk evaluation efficiency is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for risk assessment of electricity consumption data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an evaluation model according to an embodiment of the present invention;
FIG. 3 is a flow chart of another method for risk assessment of electricity consumption data according to an embodiment of the present invention;
FIG. 4 is a flowchart of another electricity consumption data risk assessment method according to the second embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electricity consumption data risk assessment apparatus according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device implementing the electricity consumption data risk assessment method according to the embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, 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 obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, 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 one
Fig. 1 is a flowchart of an electricity consumption data risk assessment method according to an embodiment of the present invention, where the present embodiment is applicable to a situation of assessing a risk level of an electricity consumption user, and the method may be performed by an electricity consumption data risk assessment apparatus, which may be implemented in a form of hardware and/or software, and may be configured in a computer. As shown in fig. 1, the method includes:
and S110, reading historical electricity utilization data of each user in the power distribution network, and constructing an evaluation model according to the historical electricity utilization data.
The power distribution network is a power grid with a voltage grade of 35KV and below, the power distribution network is used for supplying power to each power distribution station and various power loads in a city, a user is a power supply user in the power distribution network, historical power consumption data refers to historical power consumption data of the power supply user in the power distribution network, and the power consumption data comprises but is not limited to daily power, operation capacity, daily load and the like. The controller establishes an evaluation model by reading historical electricity consumption data of each user in the power distribution network, fig. 2 is a schematic diagram of the structure of the evaluation model, and in fig. 2, the evaluation model comprises a first self-encoder, a second self-encoder and a fully-connected neural network model.
Specifically, the first self-encoder may be a multi-layer cyclic neural network self-encoder, the encoder includes an encoding layer and a decoding layer, the encoding layer is used for compressing and extracting the feature values, the decoding layer is used for restoring the reconstructed data, the second self-encoder may be a depth self-encoder, and the feature values may be further compressed and extracted by the depth self-encoder.
And S120, acquiring power consumption data to be detected, and grading the power consumption data to be detected through the evaluation model to generate a grading result.
Specifically, the electricity consumption data to be detected refers to new data with unknown risk levels, after the controller obtains the electricity consumption data to be detected, the electricity consumption data to be detected can be scored through the established evaluation model to generate a scoring result, and the risk levels can be further judged through the scoring result.
Fig. 3 is a flowchart of a method for determining risk of industrial control network data according to an embodiment of the present invention, where step S120 mainly includes steps S121 to S125 as follows:
and S121, preprocessing the electricity utilization data to be detected to generate a data set.
Specifically, the controller performs preprocessing on the electricity consumption data to be detected, the preprocessing refers to performing data cleaning operations such as missing value filling and abnormal value removing on the user data and data transformation operations such as normalization and normalization, and finally, the data set is normalized to be X = (X =) 1 ,X 2 ,…X N ) Where N is the number of users, X i ＝(x 1 ,x 2 ,…x k ) T Time series data of T x k for each user.
Exemplarily, taking the number of users N as 4 as an example, X = (X) 1 ,X 2 ,X 3 ,X 4 ) Wherein X is 1 、X 2 、X 3 And X 4 Respectively represent four users, and X 1 ＝(x 1 ,x 2 ,x 3 ) T ，x 1 、x 2 And x 3 Respectively representing daily electricity consumption, running capacity and daily load.
And S122, processing the data set through a first self-encoder to obtain a data reconstruction error and a first characteristic value of the data set.
Preferably, the processing the data set by the first self-encoder to obtain the data reconstruction error and the first characteristic value of the data set includes: performing feature extraction on the data set through the coding layer to obtain a first feature value of the data set; reconstructing the data set through a decoding layer to obtain a reconstructed data set; and acquiring a data reconstruction error according to the data set and the reconstruction data set.
Specifically, the controller processes the data set through the first self-encoder, that is, the data set is subjected to feature extraction through an encoding layer of a multi-layer cyclic neural network self-encoder to obtain a first feature value of the data set, the first feature value refers to a hidden feature value of a potential space of the data set, then the data set is reconstructed through a decoding layer to obtain a reconstructed data set, the reconstructed data set is the total output of a user in a next T period of time of data predicted by a model, and the reconstructed data set is close to the data set under the condition that the user data is normal, but the reconstructed data set is deviated in different degrees due to abnormal data, so the controller obtains a data reconstruction error according to the data set and the reconstructed data set, for example, when the input data set is X i The first characteristic value H can be obtained through an encoding layer of a multilevel cyclic neural network self-encoder, and the reconstructed data set X 'can be obtained through a decoding layer' i And calculating a data reconstruction error by adopting the following formula (1):
wherein,
representing data reconstruction errors, X i Represents a data set, X' i Representing a reconstructed data set.
And S123, processing the first characteristic value of the data set through a second self-encoder to obtain a characteristic reconstruction error, a hidden characteristic value of the first characteristic value and a second characteristic value of the data set.
Preferably, the processing, by the second encoder, the first feature value of the data set to obtain the feature reconstruction error, the hidden feature value of the first feature value, and the second feature value of the data set includes: reconstructing the first characteristic value through a second self-encoder to obtain a reconstructed characteristic value of the data set; coding the first characteristic value through a second self-coder to obtain a hidden characteristic value of the first characteristic value; acquiring a characteristic reconstruction error according to the reconstruction characteristic value and a first characteristic value of the data set; and acquiring the Euclidean distance and cosine similarity of the reconstructed characteristic value and the first characteristic value of the data set, and acquiring a second characteristic value of the data set according to the Euclidean distance, the cosine similarity and the hidden characteristic value.
Specifically, the controller may input the first feature value of the data set output by the first encoder to the second encoder, that is, the depth self-encoder may reconstruct the first feature value to obtain a reconstructed feature value of the data set, and encode the first feature value by the second self-encoder to generate a hidden feature value of the potential space, and then obtain a feature reconstruction error according to the reconstructed feature value and the first feature value of the data set, that is, calculate the feature reconstruction error by using the following formula (2):
wherein, in the process,
representing the characteristic reconstruction error, H i Denotes a first characteristic value, H' i Representing the reconstructed feature value.
Further, after the controller obtains the hidden eigenvalue and the reconstructed eigenvalue, the controller may further calculate an euclidean distance and a cosine similarity between the reconstructed eigenvalue and the first eigenvalue, and since the hidden eigenvalue, the euclidean distance and the cosine similarity are in the same dimension, the controller may concatenate the hidden eigenvalue, the euclidean distance, and the cosine similarity to obtain a second eigenvalue, for example, the calculated euclidean distance is a = (A1, A2, A3), the cosine similarity is B = (B1, B2, B3), and the hidden eigenvalue is C = (C1, C2, C3), and the controller may concatenate two matrices to obtain a feature Z, that is, the feature Z = (a, B, C).
And S124, processing the second characteristic value through the full-connection neural network model to generate a Gaussian score.
Preferably, the processing the second feature value through the fully connected neural network model to generate a gaussian score includes: calculating a second characteristic value of the data set by adopting a maximum expectation algorithm EM through a full-connection neural network model, and acquiring an attribution probability corresponding to the second characteristic value of the data set; calculating through the attribution probability and a second characteristic value of the data set to obtain a score calculation correlation parameter of the fully-connected neural network model; and generating a Gaussian score according to the correlation parameter and the second characteristic value of the data set.
Specifically, the controller may input a second feature value of the data set output by the second encoder to the fully-connected neural network model, and the fully-connected neural network model may process the second feature value and calculate the logic value by using the following formula (3):
P＝MLBP(Z,θ) (3)
wherein MLBP (·) denotes a multi-layer neural network, θ denotes a neural network parameter, Z denotes a second characteristic value, and P denotes a logical value of the second characteristic value.
Further, the controller inputs the obtained logic value into a SoftMax layer of the fully-connected neural network model and outputs gamma by adopting the following formula (4) n Attribution probability:
γ n ＝Softmax(P) (4)
wherein P represents a logical value of the second characteristic value, γ n Representing the attribution probability, after obtaining the attribution probability, the controller may calculate through the attribution probability and a second eigenvalue of the data set, to obtain a score calculation correlation parameter of the fully-connected neural network model, where the correlation parameter includes a priori, a mean value, a covariance matrix, and the like, in this embodiment, the description is given only by taking the correlation parameter as the priori, the mean value, and the covariance matrix, and the type of the correlation parameter is not limited, and for example, the controller may calculate the priori by using the following formula (5):
wherein phi n Denotes the prior of the data set to be measured, N denotes the total number of users, i denotes the number of users, i =1,2, \\ 8230n, γ i,n Representing the probability of belonging.
Further, the controller may calculate a mean value according to the attribution probability and the second feature value of the data set, and calculate the mean value using the following equation (6):
wherein, mu n Mean value of the measured data set is shown, N is the total number of users, i is the number of users, i =1,2, \ 8230; N, γ i,n Denotes the probability of ownership, Z i Representing the second characteristic value.
Further, after calculating the mean value, the controller may calculate a covariance matrix according to the mean value, the second eigenvalue, and the attribution probability, and calculate the covariance matrix by using the following formula (7):
wherein, sigma n Representing the covariance matrix, T representing the time period of the data set under test, γ i,n Indicating the probability of ownership, Z i Representing a second characteristic value, mu n The mean value of the data set to be measured is represented, N represents the total number of users, i represents the number of users, i =1,2, \ 8230n.
Further, after the controller calculates the prior, mean and covariance matrices, the associated parameters and the second eigenvalue of the data set may be used to generate a gaussian score, and the gaussian score may be calculated by using the following formula (8):
wherein E (Z) represents a Gaussian score, T represents a time period of a data set to be measured, and mu n Represents the mean value of the data set to be measured, Z represents the second characteristic value, N represents the total number of users, sigma n Represents a covariance matrix, phi n Representing a priori the data set to be measured.
And S125, generating a grading result according to the data reconstruction error, the feature reconstruction error and the Gaussian score.
Preferably, generating a scoring result according to the data reconstruction error, the feature reconstruction error and the gaussian score includes: taking the data reconstruction error, the characteristic reconstruction error and the Gaussian fraction as evaluation indexes, and acquiring a weighted value corresponding to each evaluation index; and sequentially adding the products of the evaluation indexes and the weighted values corresponding to the evaluation indexes to obtain a scoring result.
Specifically, after the controller calculates the data reconstruction error, the feature reconstruction error and the gaussian score, the numerical values are used as evaluation indexes, a weight value corresponding to each evaluation index is obtained, the weight value is input into the controller by research personnel according to the importance degree of each index, the controller sequentially adds the products of each evaluation index and the weight value corresponding to each evaluation index to obtain a scoring result, further, the controller performs minimum training on the evaluation model when constructing the evaluation model, so that the controller can directly output the value of the scoring result when calculating the power consumption data to be measured, namely, the scoring result is calculated by adopting the following formula (9):
wherein E (Z) represents a Gaussian score, N represents the total number of users,
which is indicative of the error in the reconstruction of the data,
representing the characteristic reconstruction error, i representing the number of users, i =1,2, \ 8230h, n, λ 1 Weight value, lambda, representing the correspondence of data reconstruction errors 2 Weight value, lambda, representing the characteristic reconstruction error 3 A weight value corresponding to the Gaussian score, e.g., a weight value λ corresponding to a data reconstruction error of 20 for the electricity consumption data M to be measured 1 0.2, and a characteristic reconstruction error of 30 pairsCorresponding weight value lambda 2 0.1, a weight value lambda corresponding to a Gaussian score of 50 3 At 0.7, the final score of the electrical data M to be measured =20, 0.2+30, 0.1+50, 0.7=42.
And S130, determining the risk level of the electricity consumption data to be measured according to the grading result.
Specifically, the controller may determine the risk level of the user data to be measured according to the scoring result, where the risk level is classified into no risk, low risk, medium risk, and high risk, for example, when it is determined that the final score of the electricity data M to be measured is 42, the risk level of the electricity data to be measured may be obtained as medium risk.
Further, when the controller determines that the risk level of the electricity consumption data to be detected is medium risk or high risk, a risk prompt is generated and sent to a display connected with the controller, for example, the prompt content is as follows: and risks in the electricity utilization data M to be detected.
According to the technical scheme of the embodiment of the invention, the evaluation model is constructed through the historical electricity utilization data, the electricity utilization data to be tested is graded through the pre-constructed evaluation model, and finally the risk grade can be accurately determined through the grading result in a mode of determining the risk grade according to the grading result, so that the evaluation accuracy is improved, personnel do not need to go to the site for inspection, the human resources are saved, and the risk evaluation efficiency is improved.
Example two
Fig. 4 is a flowchart of a method for evaluating a risk of electricity consumption data according to a second embodiment of the present invention, where this embodiment is added with a specific description of determining a risk level of electricity consumption data to be tested according to a scoring result on the basis of the first embodiment, and specific contents of steps S210 to S220 are substantially the same as those of steps S110 to S120 in the first embodiment, and therefore, details are not repeated in this embodiment.
As shown in fig. 4, the method includes:
s210, reading historical electricity utilization data of each user in the power distribution network, and constructing an evaluation model according to the historical electricity utilization data.
And S220, acquiring power consumption data to be detected, and grading the power consumption data to be detected through the evaluation model to generate a grading result.
And S230, determining a score interval corresponding to the scoring result.
Specifically, after the controller calculates the scoring result through the above formula (9), it may further determine a corresponding score interval according to the scoring result, where the score interval is divided into four score intervals, i.e., 0-10, 10-30, 30-80, and more than 80, and for example, when the scoring result of the power consumption data M to be measured is 42 minutes, the controller may determine the scoring interval corresponding to the power consumption data M to be measured is 30-80 minutes.
And S240, determining the risk level of the power utilization data to be detected according to the score interval.
Specifically, each score interval has a corresponding risk grade, the risk grades are divided into no risk, low risk, medium risk and high risk, the scoring result is 0-10 time-sharing corresponding no risk, the scoring result is 10-30 time-sharing corresponding low risk, the scoring result is 30-80 time-sharing corresponding medium risk, and the scoring result is greater than 80 time-sharing corresponding high risk.
According to the technical scheme of the embodiment of the invention, the evaluation model is constructed through the historical electricity consumption data, the electricity consumption data to be detected is graded through the pre-constructed evaluation model, and finally, the score interval can be accurately determined through the grading result in a mode of determining the risk level according to the grading result, and then the risk level corresponding to the score interval is determined, so that the evaluation accuracy is improved, personnel do not need to go to check on site, the manpower resource is saved, and the risk evaluation efficiency is improved.
EXAMPLE III
Fig. 5 is a schematic structural diagram of an electricity consumption data risk assessment apparatus according to a third embodiment of the present invention. As shown in fig. 5, the apparatus includes: the evaluation model building module 310 is configured to read historical power consumption data of each user in the power distribution network, and build an evaluation model according to the historical power consumption data, where the evaluation model includes a first self-encoder, a second self-encoder, and a fully-connected neural network model; the scoring result generation module 320 is used for acquiring the power consumption data to be measured, scoring the power consumption data to be measured through the evaluation model and generating a scoring result; and the risk level determining module 330 is configured to determine a risk level of the power consumption data to be measured according to the scoring result.
Preferably, the scoring result generating module 320 specifically includes: the data set generating unit is used for preprocessing the electricity consumption data to be detected to generate a data set; the first self-encoder unit is used for processing the data set through the first self-encoder to obtain a data reconstruction error and a first characteristic value of the data set, wherein the first self-encoder comprises an encoding layer and a decoding layer; the second self-encoder unit is used for processing the first characteristic value of the data set through the second self-encoder to obtain a characteristic reconstruction error, a hidden characteristic value of the first characteristic value and a second characteristic value of the data set; the fully-connected neural network model unit is used for processing the second characteristic value through a fully-connected neural network model to generate a Gaussian score; and the scoring result generating unit is used for generating a scoring result according to the data reconstruction error, the characteristic reconstruction error and the Gaussian score.
Preferably, the first self-encoder unit is specifically configured to: performing feature extraction on the data set through the coding layer to obtain a first feature value of the data set; reconstructing the data set through a decoding layer to obtain a reconstructed data set; and acquiring a data reconstruction error according to the data set and the reconstruction data set.
Preferably, the second self-encoder unit is specifically configured to: reconstructing the first characteristic value through a second self-encoder to obtain a reconstructed characteristic value of the data set; coding the first characteristic value through a second self-coder to obtain a hidden characteristic value of the first characteristic value; acquiring a characteristic reconstruction error according to the reconstruction characteristic value and a first characteristic value of the data set; and acquiring the Euclidean distance and cosine similarity of the reconstructed characteristic value and the first characteristic value of the data set, and acquiring a second characteristic value of the data set according to the Euclidean distance, the cosine similarity and the hidden characteristic value.
Preferably, the fully-connected neural network model unit is specifically configured to: calculating a second characteristic value of the data set by adopting a maximum expectation algorithm EM through a full-connection neural network model, and acquiring an attribution probability corresponding to the second characteristic value of the data set; calculating through the attribution probability and a second characteristic value of the data set to obtain a score calculation correlation parameter of the fully-connected neural network model; and generating a Gaussian score according to the correlation parameter and the second characteristic value of the data set.
Preferably, the scoring result generating unit is specifically configured to: taking the data reconstruction error, the characteristic reconstruction error and the Gaussian fraction as evaluation indexes, and acquiring a weighted value corresponding to each evaluation index; and sequentially adding the products of the evaluation indexes and the weighted values corresponding to the evaluation indexes to obtain a scoring result.
Preferably, the risk level determining module 330 is specifically configured to: determining a score interval corresponding to a scoring result; and determining the risk grade of the power utilization data to be detected according to the fraction interval.
According to the technical scheme of the embodiment of the invention, the evaluation model is constructed through the historical electricity utilization data, the electricity utilization data to be detected is graded through the pre-constructed evaluation model, and finally the risk grade can be accurately determined through the grading result in a mode of determining the risk grade according to the grading result, so that the evaluation accuracy is improved, personnel are not required to go to the site for inspection, the manpower resource is saved, and the risk evaluation efficiency is improved.
The electricity consumption data risk assessment device provided by the embodiment of the invention can execute the electricity consumption data risk assessment method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
FIG. 6 illustrates a schematic structural diagram of an electronic device 10 that may be used to implement an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. Processor 11 performs the various methods and processes described above, such as a power usage data risk assessment method.
In some embodiments, a method of risk assessment of electricity usage data may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When loaded into RAM 13 and executed by processor 11, may perform one or more of the steps of a power usage data risk assessment method described above. Alternatively, in other embodiments, processor 11 may be configured to perform a power usage data risk assessment method by any other suitable means (e.g., by way of firmware). .
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A power consumption data risk assessment method is characterized by comprising the following steps:
reading historical power consumption data of each user in the power distribution network, and constructing an evaluation model according to the historical power consumption data, wherein the evaluation model comprises a first self-encoder, a second self-encoder and a full-connection neural network model;
acquiring power consumption data to be detected, and grading the power consumption data to be detected through the evaluation model to generate a grading result;
and determining the risk level of the electricity consumption data to be detected according to the grading result.
2. The method according to claim 1, wherein the obtaining of the electricity data to be measured and the scoring of the electricity data to be measured by the evaluation model to generate a scoring result comprise:
preprocessing the electricity data to be detected to generate a data set;
processing the data set through the first self-encoder to obtain a data reconstruction error and a first characteristic value of the data set, wherein the first self-encoder comprises an encoding layer and a decoding layer;
processing the first characteristic value of the data set through the second self-encoder to obtain a characteristic reconstruction error, a hidden characteristic value of the first characteristic value and a second characteristic value of the data set;
processing the second characteristic value through the full-connection neural network model to generate a Gaussian score;
and generating the scoring result according to the data reconstruction error, the characteristic reconstruction error and the Gaussian score.
3. The method of claim 2, wherein the processing the data set by the first self-encoder to obtain a data reconstruction error and a first eigenvalue of the data set comprises:
performing feature extraction on the data set through the coding layer to obtain a first feature value of the data set;
reconstructing the data set through the decoding layer to obtain a reconstructed data set;
and acquiring the data reconstruction error according to the data set and the reconstruction data set.
4. The method according to claim 3, wherein the processing the first eigenvalue of the data set by the second encoder to obtain a feature reconstruction error, a hidden eigenvalue of the first eigenvalue, and a second eigenvalue of the data set comprises:
reconstructing the first characteristic value through the second self-encoder to obtain a reconstructed characteristic value of the data set;
coding the first characteristic value through the second self-coder to obtain a hidden characteristic value of the first characteristic value;
acquiring the characteristic reconstruction error according to the reconstruction characteristic value and a first characteristic value of the data set;
and acquiring Euclidean distance and cosine similarity of the reconstructed characteristic value and a first characteristic value of the data set, and acquiring a second characteristic value of the data set according to the Euclidean distance, the cosine similarity and the hidden characteristic value.
5. The method of claim 4, wherein the processing the second eigenvalue by the fully-connected neural network model generates a Gaussian score comprising:
calculating a second characteristic value of the data set by adopting a maximum expectation algorithm EM through the fully-connected neural network model, and acquiring an attribution probability corresponding to the second characteristic value of the data set;
calculating through the attribution probability and a second characteristic value of the data set to obtain a score calculation correlation parameter of the full-connection neural network model;
generating the Gaussian score according to the correlation parameter and a second eigenvalue of the data set.
6. The method of claim 2, wherein the generating the scoring result from the data reconstruction error, the feature reconstruction error, and the Gaussian score comprises:
taking the data reconstruction error, the feature reconstruction error and the Gaussian score as evaluation indexes, and acquiring weight values corresponding to the evaluation indexes;
and sequentially adding the products of the evaluation indexes and the weighted values corresponding to the evaluation indexes to obtain the evaluation result.
7. The method according to claim 6, wherein the determining the risk level of the electricity consumption data to be tested according to the grading result comprises:
determining a score interval corresponding to the scoring result;
and determining the risk grade of the electricity consumption data to be detected according to the fraction interval.
8. An electricity consumption data risk assessment device, comprising:
the evaluation model building module is used for reading historical electricity utilization data of each user in the power distribution network and building an evaluation model according to the historical electricity utilization data, wherein the evaluation model comprises a first self-encoder, a second self-encoder and a fully-connected neural network model;
the scoring result generation module is used for acquiring power consumption data to be measured and scoring the power consumption data to be measured through the evaluation model to generate a scoring result;
and the risk grade determining module is used for determining the risk grade of the electricity consumption data to be detected according to the grading result.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of claims 1-7.
10. A computer storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a processor, when executed, to implement the method as claimed in claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211027287.8A CN115392715A (en) | 2022-08-25 | 2022-08-25 | Power utilization data risk assessment method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211027287.8A CN115392715A (en) | 2022-08-25 | 2022-08-25 | Power utilization data risk assessment method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115392715A true CN115392715A (en) | 2022-11-25 |
Family
ID=84122882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211027287.8A Pending CN115392715A (en) | 2022-08-25 | 2022-08-25 | Power utilization data risk assessment method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392715A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050946A (en) * | 2023-03-29 | 2023-05-02 | 东莞先知大数据有限公司 | Water service user collection management method and device, electronic equipment and storage medium |
-
2022
- 2022-08-25 CN CN202211027287.8A patent/CN115392715A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050946A (en) * | 2023-03-29 | 2023-05-02 | 东莞先知大数据有限公司 | Water service user collection management method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106803799B (en) | Performance test method and device | |
| CN112990330A (en) | User energy abnormal data detection method and device | |
| CN115392715A (en) | Power utilization data risk assessment method, device, equipment and storage medium | |
| CN115878958A (en) | Transformer oil temperature prediction method, device, equipment and storage medium | |
| CN109447512B (en) | Large power grid reliability assessment method based on uniform design | |
| CN112528159B (en) | Feature quality assessment method and device, electronic equipment and storage medium | |
| CN117455067A (en) | Electric quantity consumption prediction method and device, electronic equipment and storage medium | |
| CN116703109A (en) | Method, device, equipment and storage medium for selecting power distribution network project | |
| CN115809818A (en) | Multidimensional diagnosis and evaluation method and device for auxiliary equipment of pumped storage power station | |
| CN116258167A (en) | Data detection method, device, electronic equipment and medium | |
| CN115759373A (en) | Gas daily load prediction method, device and equipment | |
| CN115146997A (en) | Evaluation method and device based on power data, electronic equipment and storage medium | |
| CN115563507A (en) | Generation method, device and equipment for renewable energy power generation scene | |
| CN115481767A (en) | Operation data processing method and device for power distribution network maintenance and computer equipment | |
| CN115085368A (en) | Transformer health state monitoring method and device, computer equipment and storage medium | |
| CN117909717B (en) | Engineering quantity auxiliary acceptance settlement method based on deep learning and data mining | |
| CN117251809A (en) | Power grid time sequence data anomaly detection method, device, equipment and storage medium | |
| CN115576830A (en) | Method and device for determining quality of use case, electronic equipment and storage medium | |
| CN116842837A (en) | Transformer fault diagnosis method and device, electronic equipment and storage medium | |
| CN117705178A (en) | Wind power bolt information detection method and device, electronic equipment and storage medium | |
| CN115730245A (en) | Fault diagnosis method, device, equipment and medium for oil-immersed power transformer | |
| CN118191616A (en) | Method, device, equipment and storage medium for predicting battery health state | |
| CN118033461A (en) | Method and device for evaluating battery health state and electronic equipment | |
| CN116845287A (en) | Method, device, equipment and medium for predicting test data of fuel cell | |
| CN115218958A (en) | Method and device for judging state of rack transformer, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |