CN112949721A - Power equipment static data quality assessment method and system - Google Patents
Power equipment static data quality assessment method and system Download PDFInfo
- Publication number
- CN112949721A CN112949721A CN202110240160.3A CN202110240160A CN112949721A CN 112949721 A CN112949721 A CN 112949721A CN 202110240160 A CN202110240160 A CN 202110240160A CN 112949721 A CN112949721 A CN 112949721A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- data
- data quality
- static data
- detection
- 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.)
- Withdrawn
Links
- 230000003068 static effect Effects 0.000 title claims abstract description 111
- 238000001303 quality assessment method Methods 0.000 title claims description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 85
- 238000001514 detection method Methods 0.000 claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 68
- 238000013441 quality evaluation Methods 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000007637 random forest analysis Methods 0.000 claims abstract description 25
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 230000005611 electricity Effects 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000003066 decision tree Methods 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013210 evaluation model Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000001174 ascending effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003252 repetitive effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of data quality evaluation, and discloses a static data quality evaluation method for power equipment, which comprises the following steps: acquiring static data of the power equipment, and calculating to obtain a quality index of the static data of the power equipment; constructing a plurality of power equipment abnormal data detection submodels, and detecting power equipment abnormal data on static data quality indexes of power equipment by using the power equipment abnormal data detection submodels; correcting the wrong discrimination result according to the detection discrimination results of the plurality of submodels; evaluating the data quality of the power equipment by using a power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment; and according to the evaluation result of the data quality of the power equipment, evaluating the grade of the power equipment by utilizing a random forest algorithm combined with an optimization algorithm. The invention also provides a system for evaluating the static data quality of the power equipment. The invention realizes the evaluation of data quality.
Description
Technical Field
The invention relates to the technical field of data quality evaluation, in particular to a static data quality evaluation method and system for power equipment.
Background
At present, with the annual increase of power loads, clean energy utilization and distributed power generation technologies are rapidly developed, more distributed power sources and nonlinear loads are connected to a power distribution network to influence the quality of electric energy, and the evaluation of the quality of electric energy data of electric power equipment becomes a current popular research topic.
Because the data of the power equipment is changed all the time, each index is complex and changeable. This randomness and uncertainty is difficult to describe with a deterministic index system, and thus there is no deterministic index system to fully describe the power data quality. Meanwhile, weighting methods for power equipment data quality evaluation are various and are easily influenced by main and objective factors, and how to obtain accurate index weight needs to be further researched.
In view of this, how to obtain more accurate power equipment data evaluation index weight to evaluate the quality of power equipment data becomes a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a static data quality assessment method for electrical equipment, which is characterized in that abnormal data of the electrical equipment is detected by using an abnormal data detection algorithm of the electrical equipment based on a machine learning mixed model, the data quality of the electrical equipment is assessed by using a data quality assessment method of the electrical equipment based on combined empowerment, and the grade of the electrical equipment is assessed by using a random forest algorithm combined with an optimization algorithm.
In order to achieve the above object, the present invention provides a method for evaluating static data quality of an electrical device, including:
acquiring static data of the power equipment, and calculating to obtain a quality index of the static data of the power equipment;
constructing a plurality of power equipment abnormal data detection submodels, and detecting the power equipment abnormal data of the static data quality indexes of the power equipment by using the power equipment abnormal data detection submodels to obtain a submodel detection judgment result;
correcting the wrong discrimination result according to the detection discrimination results of the plurality of submodels to obtain the detection result of the abnormal data of the power equipment;
evaluating the data quality of the power equipment by using a power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment;
and according to the evaluation result of the data quality of the power equipment, evaluating the grade of the power equipment by utilizing a random forest algorithm combined with an optimization algorithm.
Optionally, the obtaining, by calculation, a static data quality index of the power equipment includes:
the static data of the power equipment comprises a voltage value, frequency, harmonic waves and the like of the power equipment;
the power equipment data quality index calculation formula is as follows:
1) voltage deviation:
wherein:
Δ U is a voltage deviation of the power equipment;
Ureis a voltage measurement of the electrical device;
u is the nominal voltage of the power equipment;
2) voltage fluctuation:
d=(Umax-Umin)/U×100%
wherein:
Umax,Uminthe voltage difference value of two adjacent extreme values on a voltage square mean root value curve of the power equipment is obtained;
d is a voltage fluctuation value;
u is the nominal voltage of the power equipment;
3) frequency deviation:
the frequency is the number of times that the sine quantity alternates in unit time, wherein the alternating time is called a period;
Δf=fre-f
wherein:
freis a measurement of the frequency of the power equipment;
f is the nominal value of the frequency of the power equipment;
4) voltage harmonics:
wherein:
UHthe harmonic content of the power equipment;
THDUthe total distortion rate of harmonic voltage of the power equipment;
Uhthe voltage effective value of the h-th harmonic component is obtained;
U1is the voltage effective value of the 1 st harmonic component.
Optionally, the detecting the abnormal data of the electrical equipment on the static data quality index of the electrical equipment by using the electrical equipment abnormal data detection submodel includes:
the power equipment abnormal data detection process of the LOF model comprises the following steps:
the LOF model inputs the electricity data characteristics of the current month containing short time span power equipment, the specific characteristic dimensions comprise the maximum value and the minimum value of daily electricity consumption in the current month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the current month, 25 percent quantiles, 50 percent quantiles and 75 percent quantiles of daily electricity consumption sequencing in the current month, the maximum value and the minimum value of the change percentage of the daily electricity consumption in the current month, the image characteristics (including the maximum value point number, the minimum value point number, the longest continuous repetitive sequence length, the longest continuous ascending sequence length and the longest continuous descending sequence length) of the daily electricity consumption in the current month, the statistical value of the indexes in each week in the current month, and the output is the judgment result of whether the data of each power equipment is abnormal or not;
the detection process of the abnormal data of the power equipment of the SVM model comprises the following steps:
the input of the SVM model is the electricity data characteristics of all normal power equipment in the same period of the last year, the specific characteristic dimensions comprise the maximum value and the minimum value of daily electricity consumption in the month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the month, 25 percent quantiles, 50 percent quantiles and 75 percent quantiles of daily electricity consumption sequencing in the month, the maximum value and the minimum value of the change percentage of the daily electricity consumption in the month, the image characteristics (comprising the maximum value point number, the minimum value point number, the maximum continuous repetitive sequence length, the maximum continuous ascending sequence length and the maximum continuous descending sequence length) of the daily electricity consumption in the month and the statistical value of the indexes every week in the month, the output is a model file for recording the learning condition of the model for the characteristic data, and in the detection stage, the input of the SVM model is a short-time span data index of the power equipment comprising the same characteristic dimensions in the month, outputting a result of judging whether the data of each power device is abnormal or not;
the detection process of the abnormal data of the electric power equipment of the LSTM model comprises the following steps:
the training input of the LSTM model comprises the average value, the average absolute deviation, the standard deviation, the skewness, the standard deviation-free kurtosis, the unbiased error and the maximum power consumption of all normal power equipment in the kth-1 month and the average value of the monthly power consumption of all normal power equipment in the kth month, and the output is a model file for recording the learning condition of the model to the characteristic data; in the detection stage, the input of the LSTM model is monthly power consumption data of all normal electric power equipment with the same characteristic dimension in the previous month, the output is prediction of a monthly power consumption average value of all normal electric power equipment in the current month, and after the monthly power consumption average value of the normal electric power equipment in the current month is obtained through prediction, a formula for judging whether the short-time span electric power equipment data is abnormal or not is as follows:
wherein:
the data label of the normal power equipment is 0, and the data label of the abnormal power equipment is 1;
ρ is an anomaly coefficient, which is set to 0.4;
Etthe actual total power consumption of the power equipment in the current month;
Eeand predicting the total amount of the power consumption of the power equipment in the current month.
Optionally, the correcting the erroneous determination result according to the detection determination results of the plurality of submodels includes:
according to the detection and discrimination results of the sub-models, storing the detection and discrimination results as model files for recording the learning of the model on the characteristic data;
when prediction is carried out, the discrimination result of the grating LOF is measured, and the model of the SVM and the LSTM is called to give out the discrimination;
and finally, correcting by taking the classification judgment result of the SVM as a reference, if the density of the abnormal data of the electric power equipment judged by the SVM is normal in the LOF and the difference between the total monthly power consumption and the power consumption of the electric power equipment predicted by the LSTM is within a reasonable range, correcting the abnormal data of the electric power equipment into normal equipment, and if the SVM judges that the abnormal data of the electric power equipment is normal, not correcting the abnormal data of the electric power equipment, and finally outputting all the judged abnormal data of the electric power equipment.
Optionally, the evaluating the data quality of the power equipment by using the power equipment data quality evaluation method based on the combined weighting includes:
1) constructing a power equipment data quality evaluation matrix X, wherein XijThe value of the static data quality index i of the power equipment corresponding to the power equipment j is as follows:
wherein:
m represents the number of static data quality indexes of the power equipment;
n represents the number of electrical devices;
2) weighting static data quality indexes of different power equipment by using a combined weighting method, wherein the calculation formula of the combined weighting method is as follows:
wherein:
withe weight is the static data quality index i of the power equipment;
qijthe method comprises the steps of obtaining a correlation coefficient between a static data quality index i of the power equipment and a static data quality index j of the power equipment;
σithe standard deviation is the standard deviation of the static data quality index i of the power equipment;
eithe entropy of the static data quality index i of the power equipment is obtained;
3) for xijIn a specific embodiment of the present invention, different standardization formulas are adopted for different types of data quality evaluation indexes of the power equipment:
the standardized formula of the benefit type index is as follows:
the standardized formula of the cost index is as follows:
wherein:
max(xj),min(xj) The maximum value and the minimum value of the jth power equipment data quality index are obtained; v. ofijRepresents a normalized value;
weighting the index wjIs the same as vijMultiplying to obtain a weighting matrix R, wherein:
rij=wj×vij
4) calculating weighted Euclidean distance s from different power equipment to positive and negative ideal solutionsi +And si:
Wherein:
smaxmax (r) as a benefit indexij);
sminMin (r) as a cost-type indicatorij);
5) Calculating grey correlation degrees of different power equipment i to positive and negative ideal solutionsAnd
wherein:
gray correlation coefficient from different power equipment i to positive and negative ideal solutions;
γ is a resolution coefficient, which is set to 0.3;
6) will weight Euclidean distance siDegree of association with Gray EiCombining to obtain the characteristic vector of the power equipment iAnd
7) calculating the evaluation result of the data quality of each power device:
wherein:
ηifor the power equipment data quality evaluation index, in an embodiment of the present invention, the larger the value is, the closer the power equipment data quality is to the positive ideal solution is, the better the power equipment data quality result is, otherwise, the power equipment data quality is worse.
Optionally, the evaluating the power equipment level by using a random forest algorithm combined with an optimization algorithm includes:
the power equipment grades are divided into four grades of 1, 2, 3 and 4, wherein the grade 1 is the optimal grade, and the grade 1 is the rest grade of the optimal grade, namely the grade 1 represents that the power equipment meets the high-level power quality requirement of a special industry, the grade 2 represents that the power quality of the power equipment meets the national standard, the grade 3 represents that each evaluation index of the power quality of the power equipment meets the power quality limit value requirement specified by the national standard, and the grade 4 represents that the power quality of the power equipment does not meet the national standard;
the random forest algorithm flow of the combined optimization algorithm is as follows:
determining the number nt of decision trees and the subset size mt of attribute features in a random forest comprehensive evaluation model according to data in a training power equipment data set U, wherein mt is less than or equal to m, and m is the number of power equipment data quality evaluation indexes;
adopting a CART algorithm to establish nt decision trees, and selecting a characteristic variable with the minimum Gini index as an optimal splitting node;
calculating the average out-of-bag error of the model, if the iteration number of the model is smaller than the preset maximum iteration number, updating the values of nt and mt by using a particle swarm algorithm, repeating the steps until the maximum iteration number is reached, and outputting a final random forest model;
and inputting the data quality evaluation result of the power equipment into a random forest model to perform grade evaluation decision, and determining the final power equipment grade according to the results of all decision trees.
In addition, to achieve the above object, the present invention further provides a system for evaluating static data quality of an electrical device, the system including:
the power equipment data acquisition device is used for acquiring the static data of the power equipment and calculating to obtain the quality index of the static data of the power equipment;
the data processor is used for constructing a plurality of power equipment abnormal data detection submodels, carrying out power equipment abnormal data detection on static data quality indexes of the power equipment by using the power equipment abnormal data detection submodels to obtain submodel detection judgment results, and correcting wrong judgment results according to the detection judgment results of the plurality of submodels to obtain detection results of power equipment abnormal data;
and the data quality evaluation device is used for evaluating the data quality of the power equipment by using the power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment, so that the evaluation of the grade of the power equipment is carried out by using a random forest algorithm combined with an optimization algorithm.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium, which stores thereon power device data quality assessment program instructions, which are executable by one or more processors to implement the steps of the implementation method of power device static data quality assessment as described above.
Compared with the prior art, the invention provides a static data quality evaluation method for power equipment, which has the following advantages:
firstly, the invention constructs a plurality of power equipment abnormal data detection submodels, the power equipment abnormal data detection submodels are used for detecting the power equipment abnormal data of the static data quality index of the power equipment, for the plurality of power equipment abnormal data detection submodels, whether individual data are abnormal or not is judged on the basis of density through an LOF model, an egg type model is used for judging the abnormality through an SVM model, an LSTM neural network is constructed, the power utilization mean value of normal power equipment in the month is predicted according to the power utilization characteristics of the normal power equipment in the previous month, and then a threshold value is set to divide the normal power equipment data and the abnormal power equipment data:
wherein: the data label of the normal power equipment is 0, and the data label of the abnormal power equipment is 1; ρ is an anomaly coefficient, which is set to 0.4; etThe actual total power consumption of the power equipment in the current month; eePredicting the total amount of power consumption of the power equipment in the current month; the classification hyperplane of the SVM model is too strict, that is, most abnormal data can be correctly judged, but more normal data are judged to be abnormal by mistake, so the classification hyperplane of the SVM model is corrected by taking the classification judgment result of the SVM as a reference, if the density of the abnormal data of the electric power equipment judged by the SVM is normal in the LOF and the difference between the total monthly power consumption and the predicted electric power consumption of the electric power equipment by the LSTM is in a reasonable range, the abnormal data of the electric power equipment is corrected to be normal equipment, if the SVM judges to be the normal electric power equipment data, the abnormal data of the electric power equipment does not need to be corrected, and finally all the judged abnormal data of the electric power equipment are output.
Meanwhile, the invention provides a power equipment data quality evaluation method based on combined empowerment to evaluate the data quality of the power equipmentijThe value of the static data quality index i of the power equipment corresponding to the power equipment j is as follows:
wherein: m represents the number of static data quality indexes of the power equipment; n represents the number of electrical devices; and performing weighting on static data quality indexes of different power equipment by using a combined weighting method, wherein the calculation formula of the combined weighting method is as follows:
wherein: w is aiThe weight is the static data quality index i of the power equipment; q. q.sijThe method comprises the steps of obtaining a correlation coefficient between a static data quality index i of the power equipment and a static data quality index j of the power equipment; sigmaiThe standard deviation is the standard deviation of the static data quality index i of the power equipment; e.g. of the typeiThe entropy of the static data quality index i of the power equipment is obtained; for xijCarrying out standardization processing to obtain a dimensionless matrix V of the power equipment data quality evaluation matrix X, and weighting the indexes wjIs the same as vijMultiplying to obtain a weighting matrix R, wherein:
rij=wj×vij
by calculating the weighted Euclidean distance s from different power equipment to the positive and negative ideal solutionsi +And siCompared with the prior art, the calculated Euclidean distance is weighted, and the weighted Euclidean distance is adopted to judge the sequencing of the evaluation objects, so that the probability that the evaluation results are the same can be remarkably reduced, and the calculation formula is as follows:
wherein: smaxMax (which is a benefit index)rij);sminMin (r) as a cost-type indicatorij) (ii) a And in addition, the invention calculates the grey correlation degree of different power equipment i to the positive and negative ideal solutionsAnd
wherein:gray correlation coefficient from different power equipment i to positive and negative ideal solutions; γ is a resolution coefficient, which is set to 0.3; compared with the prior art, the method introduces the grey correlation degree and the weighted distance to form a new comprehensive characteristic quantity, wherein the grey correlation degree is the basic basis of a grey correlation analysis method and can describe the density of the relation between the factors in the multi-factor sample, if the sample data shows that the change situations of the two factors are almost different, the correlation value between the two factors is large, otherwise, the correlation value is small, and the obtained characteristic vector of the power equipment iAndcomprises the following steps:
therefore, the invention calculates the evaluation result of the data quality of each power device by using the following formula:
wherein: etaiThe larger the value of the evaluation index is, the closer the data quality of the power equipment is to the positive ideal solution, the better the data quality result of the power equipment is, and otherwise, the worse the data quality of the power equipment is.
Drawings
Fig. 1 is a schematic flowchart of a method for evaluating static data quality of an electrical device according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for evaluating static data quality of an electrical device according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The method comprises the steps of detecting abnormal data of the electrical equipment by using an electrical equipment abnormal data detection algorithm based on a machine learning hybrid model, evaluating the data quality of the electrical equipment by using an electrical equipment data quality evaluation method based on combined weighting, and evaluating the grade of the electrical equipment by using a random forest algorithm combined with an optimization algorithm. Fig. 1 is a schematic diagram illustrating a method for evaluating static data quality of a power device according to an embodiment of the present invention.
In this embodiment, the method for evaluating the quality of static data of the power equipment includes:
and S1, acquiring static data of the power equipment, and calculating to obtain a quality index of the static data of the power equipment.
Firstly, the method acquires static data of the electrical equipment, wherein in a specific embodiment of the method, the static data of the electrical equipment comprises a voltage value, frequency, harmonic waves and the like of the electrical equipment;
according to the obtained static data of the power equipment, the static data quality index of the power equipment is obtained through calculation, and the calculation formula of the data quality index of the power equipment is as follows:
1) voltage deviation:
wherein:
Δ U is a voltage deviation of the power equipment;
Ureis a voltage measurement of the electrical device;
u is the nominal voltage of the power equipment;
2) voltage fluctuation:
d=(Umax-Umin)/U×100%
wherein:
Umax,Uminthe voltage difference value of two adjacent extreme values on a voltage square mean root value curve of the power equipment is obtained;
d is a voltage fluctuation value;
u is the nominal voltage of the power equipment;
3) frequency deviation:
the frequency is the number of times that the sine quantity alternates in unit time, wherein the alternating time is called a period;
Δf=fre-f
wherein:
freas a power plantA measure of frequency;
f is the nominal value of the frequency of the power equipment;
4) voltage harmonics:
wherein:
UHthe harmonic content of the power equipment;
THDUthe total distortion rate of harmonic voltage of the power equipment;
Uhthe voltage effective value of the h-th harmonic component is obtained;
U1is the voltage effective value of the 1 st harmonic component.
And S2, constructing a plurality of power equipment abnormal data detection submodels, and detecting the power equipment abnormal data of the static data quality index of the power equipment by using the power equipment abnormal data detection submodels to obtain a submodel detection judgment result.
Furthermore, a plurality of electrical equipment abnormal data detection submodels are constructed, wherein the electrical equipment abnormal data detection submodels comprise an LOF model, an SVM model and an LSTM model;
detecting abnormal data of the power equipment on the static data quality index of the power equipment by using the abnormal data detection submodel of the power equipment to obtain a submodel detection judgment result;
the power equipment abnormal data detection process of the LOF model comprises the following steps:
the LOF model inputs the electricity data characteristics of the current month containing short time span power equipment, the specific characteristic dimensions comprise the maximum value and the minimum value of daily electricity consumption in the current month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the current month, 25 percent quantiles, 50 percent quantiles and 75 percent quantiles of daily electricity consumption sequencing in the current month, the maximum value and the minimum value of the change percentage of the daily electricity consumption in the current month, the image characteristics (including the maximum value point number, the minimum value point number, the longest continuous repetitive sequence length, the longest continuous ascending sequence length and the longest continuous descending sequence length) of the daily electricity consumption in the current month, the statistical value of the indexes in each week in the current month, and the output is the judgment result of whether the data of each power equipment is abnormal or not;
the detection process of the abnormal data of the power equipment of the SVM model comprises the following steps:
the input of the SVM model is the electricity data characteristics of all normal power equipment in the same period of the last year, the specific characteristic dimensions comprise the maximum value and the minimum value of daily electricity consumption in the month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the month, 25 percent quantiles, 50 percent quantiles and 75 percent quantiles of daily electricity consumption sequencing in the month, the maximum value and the minimum value of the change percentage of the daily electricity consumption in the month, the image characteristics (comprising the maximum value point number, the minimum value point number, the maximum continuous repetitive sequence length, the maximum continuous ascending sequence length and the maximum continuous descending sequence length) of the daily electricity consumption in the month and the statistical value of the indexes every week in the month, the output is a model file for recording the learning condition of the model for the characteristic data, and in the detection stage, the input of the SVM model is a short-time span data index of the power equipment comprising the same characteristic dimensions in the month, outputting a result of judging whether the data of each power device is abnormal or not;
the detection process of the abnormal data of the electric power equipment of the LSTM model comprises the following steps:
the training input of the LSTM model comprises the average value, the average absolute deviation, the standard deviation, the skewness, the standard deviation-free kurtosis, the unbiased error and the maximum power consumption of all normal power equipment in the kth-1 month and the average value of the monthly power consumption of all normal power equipment in the kth month, and the output is a model file for recording the learning condition of the model to the characteristic data; in the detection stage, the input of the LSTM model is monthly power consumption data of all normal electric power equipment with the same characteristic dimension in the previous month, the output is prediction of a monthly power consumption average value of all normal electric power equipment in the current month, and after the monthly power consumption average value of the normal electric power equipment in the current month is obtained through prediction, a formula for judging whether the short-time span electric power equipment data is abnormal or not is as follows:
wherein:
the data label of the normal power equipment is 0, and the data label of the abnormal power equipment is 1;
ρ is an anomaly coefficient, which is set to 0.4;
Etthe actual total power consumption of the power equipment in the current month;
Eeand predicting the total amount of the power consumption of the power equipment in the current month.
And S3, correcting the error judgment result according to the detection judgment results of the plurality of submodels to obtain the detection result of the abnormal data of the power equipment.
Furthermore, according to the detection and judgment results of a plurality of submodels, the detection and judgment results are respectively stored as a model file of a record model for learning characteristic data, when prediction is carried out, the judgment result of LOF is measured, models of SVM and LSTM are called to give judgment, finally the type judgment result of SVM is taken as a reference to carry out correction, if the density of abnormal data of the electric power equipment judged by SVM in LOF is normal, and the difference between the total monthly power consumption and the predicted electric power consumption of the electric power equipment by LSTM is in a reasonable range, the abnormal data of the electric power equipment is corrected to be normal equipment, if the SVM judges to be normal electric power equipment data, correction is not needed, and all the judged abnormal data of the electric power equipment are finally output.
And S4, evaluating the data quality of the power equipment by using the power equipment data quality evaluation method based on the combined empowerment to obtain the evaluation result of the data quality of the power equipment.
Further, the invention utilizes a power equipment data quality assessment method based on combined weighting to assess the data quality of the power equipment, and the power equipment data quality assessment method based on combined weighting comprises the following steps:
1) constructing a power equipment data quality evaluation matrix X, wherein XijAs a power plantj corresponds to the value of the static data quality index i of the power equipment:
wherein:
m represents the number of static data quality indexes of the power equipment;
n represents the number of electrical devices;
2) weighting static data quality indexes of different power equipment by using a combined weighting method, wherein the calculation formula of the combined weighting method is as follows:
wherein:
withe weight is the static data quality index i of the power equipment;
qijthe method comprises the steps of obtaining a correlation coefficient between a static data quality index i of the power equipment and a static data quality index j of the power equipment;
σithe standard deviation is the standard deviation of the static data quality index i of the power equipment;
eithe entropy of the static data quality index i of the power equipment is obtained;
3) for xijIn a specific embodiment of the present invention, different standardization formulas are adopted for different types of data quality evaluation indexes of the power equipment:
the standardized formula of the benefit type index is as follows:
the standardized formula of the cost index is as follows:
wherein:
max(xj),min(xj) The maximum value and the minimum value of the jth power equipment data quality index are obtained;
vijrepresents a normalized value;
weighting the index wjIs the same as vijMultiplying to obtain a weighting matrix R, wherein:
rij=wj×vij
4) calculating weighted Euclidean distance s from different power equipment to positive and negative ideal solutionsi +And si:
Wherein:
smaxmax (r) as a benefit indexij);
sminMin (r) as a cost-type indicatorij);
5) Calculating grey correlation degrees of different power equipment i to positive and negative ideal solutionsAnd
wherein:
gray correlation coefficient from different power equipment i to positive and negative ideal solutions;
γ is a resolution coefficient, which is set to 0.3;
6) will weight Euclidean distance siDegree of association with Gray EiCombining to obtain the characteristic vector of the power equipment iAnd
7) calculating the evaluation result of the data quality of each power device:
wherein:
ηifor the power equipment data quality evaluation index, in an embodiment of the invention, the larger the value is, the more the power equipment data quality is representedAnd if the result is close to the positive ideal solution, the data quality result of the power equipment is better, otherwise, the data quality of the power equipment is poorer.
And S5, evaluating the grade of the power equipment by utilizing a random forest algorithm combined with an optimization algorithm according to the evaluation result of the data quality of the power equipment.
Further, according to the evaluation result of the data quality of the power equipment, the evaluation of the grade of the power equipment is carried out by utilizing a random forest algorithm combined with an optimization algorithm, the grade of the power equipment is divided into four grades of 1, 2, 3 and 4, wherein the grade 1 is the rest grade of the optimal grade, the grade 1 represents that the power equipment meets the high-level power quality requirement of a special industry, the grade 2 represents that the power quality of the power equipment meets the national standard, the grade 3 represents that each evaluation index of the power quality of the power equipment meets the power quality limit requirement specified by the national standard, and the grade 4 represents that the power quality of the power equipment does not meet the national standard;
the random forest algorithm flow of the combined optimization algorithm is as follows:
determining the number nt of decision trees and the subset size mt of attribute features in a random forest comprehensive evaluation model according to data in a training power equipment data set U, wherein mt is less than or equal to m, and m is the number of power equipment data quality evaluation indexes;
adopting a CART algorithm to establish nt decision trees, and selecting a characteristic variable with the minimum Gini index as an optimal splitting node;
calculating the average out-of-bag error of the model, if the iteration number of the model is smaller than the preset maximum iteration number, updating the values of nt and mt by using a particle swarm algorithm, repeating the steps until the maximum iteration number is reached, and outputting a final random forest model;
and inputting the data quality evaluation result of the power equipment into a random forest model to perform grade evaluation decision, and determining the final power equipment grade according to the results of all decision trees.
The following describes embodiments of the present invention through an algorithmic experiment and tests of the inventive treatment method. The hardware test environment of the algorithm of the invention is as follows: the operating system is Ubuntu16.04, the computer processor is Inteli5-8500CPU @3GHZ multiplied by 6, the size of the memory bank is 16G, the Tensorflow-gpu 1.18 version and the keras 2.24 version; the comparison processing method is a power equipment static data quality evaluation method based on random forests and a power equipment static data quality evaluation method based on SVM.
In the algorithm experiment, the data set is collected static data of 100G power equipment. In the experiment, the acquired data is input into the method and the comparison method, and the accuracy of the static data quality evaluation of the power equipment is used as an index for evaluating the performance of the algorithm.
According to experimental results, the static data quality assessment accuracy of the power equipment based on the static data quality assessment method of the power equipment of the random forest is 84.31%, the static data quality assessment accuracy of the power equipment based on the static data quality assessment method of the power equipment of the SVM is 81.75%, the static data quality assessment accuracy of the power equipment based on the static data quality assessment method of the SVM is 86.32%, and compared with a comparison method, the static data quality assessment method of the power equipment provided by the invention has higher static data quality assessment accuracy of the power equipment.
The invention further provides a system for evaluating the static data quality of the power equipment. Fig. 2 is a schematic diagram of an internal structure of a static data quality evaluation system of an electrical device according to an embodiment of the present invention.
In the present embodiment, the power equipment static data quality evaluation system 1 at least includes a power equipment data acquisition device 11, a data processor 12, a data quality evaluation device 13, a communication bus 14, and a network interface 15.
The power equipment data acquiring device 11 may be a PC (Personal Computer), a terminal equipment such as a smart phone, a tablet Computer, and a mobile Computer, or may be a server.
The data processor 12 includes at least one type of readable storage medium including flash memory, hard disks, multi-media cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, and the like. The data processor 12 may in some embodiments be an internal storage unit of the power device static data quality assessment system 1, for example a hard disk of the power device static data quality assessment system 1. The data processor 12 may also be an external storage device of the static data quality evaluation system 1 of the power equipment in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the static data quality evaluation system 1 of the power equipment. Further, the data processor 12 may also include both an internal storage unit and an external storage device of the power device static data quality evaluation system 1. The data processor 12 can be used not only to store application software installed in the power equipment static data quality evaluation system 1 and various types of data, but also to temporarily store data that has been output or is to be output.
The data quality evaluation device 13 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip in some embodiments, and is used for running program codes stored in the data processor 12 or Processing data, such as power equipment data quality evaluation program instructions.
The communication bus 14 is used to enable connection communication between these components.
The network interface 15 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the system 1 and other electronic devices.
Optionally, the system 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (organic light-Emitting Diode) touch device, or the like. The display may also be referred to as a display screen or a display unit, where appropriate, for displaying information processed in the power equipment static data quality assessment system 1 and for displaying a visual user interface.
Fig. 2 only shows the power equipment static data quality assessment system 1 with the components 11-15, and it will be understood by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the power equipment static data quality assessment system 1, and may include fewer or more components than shown, or combine certain components, or a different arrangement of components.
In the embodiment of the system 1 shown in fig. 2, the data processor 12 stores therein power equipment data quality evaluation program instructions; the steps of the data quality evaluation device 13 executing the power equipment data quality evaluation program instructions stored in the data processor 12 are the same as the implementation method of the power equipment static data quality evaluation method, and are not described here.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium having stored thereon power device data quality assessment program instructions, which are executable by one or more processors to implement the following operations:
acquiring static data of the power equipment, and calculating to obtain a quality index of the static data of the power equipment;
constructing a plurality of power equipment abnormal data detection submodels, and detecting the power equipment abnormal data of the static data quality indexes of the power equipment by using the power equipment abnormal data detection submodels to obtain a submodel detection judgment result;
correcting the wrong discrimination result according to the detection discrimination results of the plurality of submodels to obtain the detection result of the abnormal data of the power equipment;
evaluating the data quality of the power equipment by using a power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment;
and according to the evaluation result of the data quality of the power equipment, evaluating the grade of the power equipment by utilizing a random forest algorithm combined with an optimization algorithm.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. The term "comprising" is used to specify the presence of stated features, integers, steps, operations, elements, components, groups, integers, operations, elements, components, groups, elements, groups, integers, operations, elements.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. 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 (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A method for evaluating static data quality of power equipment is characterized by comprising the following steps:
acquiring static data of the power equipment, and calculating to obtain a quality index of the static data of the power equipment;
constructing a plurality of power equipment abnormal data detection submodels, and detecting the power equipment abnormal data of the static data quality indexes of the power equipment by using the power equipment abnormal data detection submodels to obtain a submodel detection judgment result;
correcting the wrong discrimination result according to the detection discrimination results of the plurality of submodels to obtain the detection result of the abnormal data of the power equipment;
evaluating the data quality of the power equipment by using a power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment;
and according to the evaluation result of the data quality of the power equipment, evaluating the grade of the power equipment by utilizing a random forest algorithm combined with an optimization algorithm.
2. The method for evaluating the quality of the static data of the electric power equipment according to claim 1, wherein the step of calculating the static data quality index of the electric power equipment comprises the following steps:
1) voltage deviation:
wherein:
Δ U is a voltage deviation of the power equipment;
Ureis a voltage measurement of the electrical device;
u is the nominal voltage of the power equipment;
2) voltage fluctuation:
d=(Umax-Umin)/U×100%
wherein:
Umax,Uminthe voltage difference value of two adjacent extreme values on a voltage square mean root value curve of the power equipment is obtained;
d is a voltage fluctuation value;
u is the nominal voltage of the power equipment;
3) frequency deviation:
the frequency is the number of times that the sine quantity alternates in unit time, wherein the alternating time is called a period;
Δf=fre-f
wherein:
freis a measurement of the frequency of the power equipment;
f is the nominal value of the frequency of the power equipment;
4) voltage harmonics:
wherein:
UHthe harmonic content of the power equipment;
THDUthe total distortion rate of harmonic voltage of the power equipment;
Uhthe voltage effective value of the h-th harmonic component is obtained;
U1is the voltage effective value of the 1 st harmonic component.
3. The method for evaluating the quality of the static data of the electric power equipment according to claim 2, wherein the detecting the abnormal data of the electric power equipment on the static data quality index of the electric power equipment by using the abnormal data detecting submodel of the electric power equipment comprises the following steps:
the power equipment abnormal data detection process of the LOF model comprises the following steps:
the LOF model inputs the data characteristics of the electricity consumption of the power equipment in the current month with short time span, and the specific characteristic dimensions comprise the maximum value and the minimum value of the daily electricity consumption in the current month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the current month, 25% quantiles, 50% quantiles and 75% quantiles of the daily electricity consumption in the current month, the maximum value and the minimum value of the change percentage of the daily electricity consumption in the current month, the image characteristics of the daily electricity consumption in the current month, and the statistical value of the index in each week in the current month, and the output of the statistical value is the judgment result of whether the data of each power equipment is abnormal or not;
the detection process of the abnormal data of the power equipment of the SVM model comprises the following steps:
the input of the SVM model is the electricity data characteristics of all normal electric power equipment in the same period of the last year, the specific characteristic dimensions comprise the maximum value and the minimum value of daily electricity consumption in the month, the average absolute deviation, the standard deviation, the skewness and the kurtosis of the daily electricity consumption in the month, 25% quantiles, 50% quantiles and 75% quantiles of daily electricity consumption sequencing in the month, the maximum value and the minimum value of daily electricity consumption change percentage in the month, the image characteristics of the daily electricity consumption in the month and the statistical value of the indexes in the month, the model file for recording the learning condition of the model for the characteristic data is output, and in the detection stage, the input of the SVM model is a short-time-span electric power equipment data index containing the same characteristic dimension in the month and the judgment result of the data abnormality of each electric power equipment is output;
the detection process of the abnormal data of the electric power equipment of the LSTM model comprises the following steps:
the training input of the LSTM model comprises the average value, the average absolute deviation, the standard deviation, the skewness, the standard deviation-free kurtosis, the unbiased error and the maximum power consumption of all normal power equipment in the kth-1 month and the average value of the monthly power consumption of all normal power equipment in the kth month, and the output is a model file for recording the learning condition of the model to the characteristic data; in the detection stage, the input of the LSTM model is monthly power consumption data of all normal electric power equipment with the same characteristic dimension in the previous month, the output is prediction of a monthly power consumption average value of all normal electric power equipment in the current month, and after the monthly power consumption average value of the normal electric power equipment in the current month is obtained through prediction, a formula for judging whether the short-time span electric power equipment data is abnormal or not is as follows:
wherein:
the data label of the normal power equipment is 0, and the data label of the abnormal power equipment is 1;
ρ is an anomaly coefficient, which is set to 0.4;
Etthe actual total power consumption of the power equipment in the current month;
Eeand predicting the total amount of the power consumption of the power equipment in the current month.
4. The method for evaluating the quality of the static data of the electric power equipment as claimed in claim 3, wherein the correcting the wrong discrimination result according to the detection discrimination results of the plurality of submodels comprises:
according to the detection and discrimination results of the sub-models, storing the detection and discrimination results as model files for recording the learning of the model on the characteristic data;
when prediction is carried out, the discrimination result of the grating LOF is measured, and the model of the SVM and the LSTM is called to give out the discrimination;
and finally, correcting by taking the classification judgment result of the SVM as a reference, if the density of the abnormal data of the electric power equipment judged by the SVM is normal in the LOF and the difference between the total monthly power consumption and the power consumption of the electric power equipment predicted by the LSTM is within a reasonable range, correcting the abnormal data of the electric power equipment into normal equipment, and if the SVM judges that the abnormal data of the electric power equipment is normal, not correcting the abnormal data of the electric power equipment, and finally outputting all the judged abnormal data of the electric power equipment.
5. The method for evaluating the quality of the static data of the electric power equipment according to claim 4, wherein the evaluation of the data quality of the electric power equipment by using the method for evaluating the data quality of the electric power equipment based on the combined empowerment comprises the following steps:
1) constructing a power equipment data quality evaluation matrix X, wherein XijThe value of the static data quality index i of the power equipment corresponding to the power equipment j is as follows:
wherein:
m represents the number of static data quality indexes of the power equipment;
n represents the number of electrical devices;
2) weighting static data quality indexes of different power equipment by using a combined weighting method, wherein the calculation formula of the combined weighting method is as follows:
wherein:
withe weight is the static data quality index i of the power equipment;
qijthe method comprises the steps of obtaining a correlation coefficient between a static data quality index i of the power equipment and a static data quality index j of the power equipment;
σithe standard deviation is the standard deviation of the static data quality index i of the power equipment;
eithe entropy of the static data quality index i of the power equipment is obtained;
3) for xijCarrying out standardization processing to obtain a dimensionless matrix V, V of the power equipment data quality evaluation matrix XijDenotes xijA normalized value of (d);
weighting the index wjIs the same as vijMultiplying to obtain a weighting matrix R, wherein:
rij=wj×vij
4) calculating weighted Euclidean distances from different power equipment to positive and negative ideal solutionsAnd
wherein:
smaxmax (r) as a benefit indexij);
sminMin (r) as a cost-type indicatorij);
5) Calculating grey correlation degrees of different power equipment i to positive and negative ideal solutionsAnd
wherein:
gray correlation coefficient from different power equipment i to positive and negative ideal solutions;
γ is a resolution coefficient, which is set to 0.3;
6) will weight Euclidean distance siDegree of association with Gray EiCombining to obtain the characteristic vector of the power equipment iAnd
7) calculating the evaluation result of the data quality of each power device:
wherein:
ηiand the data quality evaluation index of the power equipment is obtained.
6. The method for evaluating the quality of the static data of the power equipment as claimed in claim 5, wherein the evaluation of the grade of the power equipment by using the random forest algorithm combined with the optimization algorithm comprises the following steps:
determining the number nt of decision trees and the subset size mt of attribute features in a random forest comprehensive evaluation model according to data in a training power equipment data set U, wherein mt is less than or equal to m, and m is the number of power equipment data quality evaluation indexes;
adopting a CART algorithm to establish nt decision trees, and selecting a characteristic variable with the minimum Gini index as an optimal splitting node;
calculating the average out-of-bag error of the model, if the iteration number of the model is smaller than the preset maximum iteration number, updating the values of nt and mt by using a particle swarm algorithm, repeating the steps until the maximum iteration number is reached, and outputting a final random forest model;
and inputting the data quality evaluation result of the power equipment into a random forest model to perform grade evaluation decision, and determining the final power equipment grade according to the results of all decision trees.
7. An electrical device static data quality assessment system, the system comprising:
the power equipment data acquisition device is used for acquiring the static data of the power equipment and calculating to obtain the quality index of the static data of the power equipment;
the data processor is used for constructing a plurality of power equipment abnormal data detection submodels, carrying out power equipment abnormal data detection on static data quality indexes of the power equipment by using the power equipment abnormal data detection submodels to obtain submodel detection judgment results, and correcting wrong judgment results according to the detection judgment results of the plurality of submodels to obtain detection results of power equipment abnormal data;
and the data quality evaluation device is used for evaluating the data quality of the power equipment by using the power equipment data quality evaluation method based on combined empowerment to obtain an evaluation result of the data quality of the power equipment, so that the evaluation of the grade of the power equipment is carried out by using a random forest algorithm combined with an optimization algorithm.
8. A computer-readable storage medium having stored thereon power device data quality assessment program instructions executable by one or more processors to implement the steps of a method for implementing a power device static data quality assessment as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110240160.3A CN112949721A (en) | 2021-03-04 | 2021-03-04 | Power equipment static data quality assessment method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110240160.3A CN112949721A (en) | 2021-03-04 | 2021-03-04 | Power equipment static data quality assessment method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112949721A true CN112949721A (en) | 2021-06-11 |
Family
ID=76247616
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110240160.3A Withdrawn CN112949721A (en) | 2021-03-04 | 2021-03-04 | Power equipment static data quality assessment method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112949721A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113496440A (en) * | 2021-06-28 | 2021-10-12 | 国网上海市电力公司 | User abnormal electricity utilization detection method and system |
CN115048434A (en) * | 2022-08-15 | 2022-09-13 | 南京灿能电力自动化股份有限公司 | Electric energy quality data processing method |
CN116754901A (en) * | 2023-08-21 | 2023-09-15 | 安徽博诺思信息科技有限公司 | Power distribution network fault analysis management platform based on quick positioning |
WO2024098990A1 (en) * | 2022-11-11 | 2024-05-16 | 浙江万胜智能科技股份有限公司 | Special transformer acquisition terminal-based electric energy quality monitoring method and system |
-
2021
- 2021-03-04 CN CN202110240160.3A patent/CN112949721A/en not_active Withdrawn
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113496440A (en) * | 2021-06-28 | 2021-10-12 | 国网上海市电力公司 | User abnormal electricity utilization detection method and system |
CN113496440B (en) * | 2021-06-28 | 2023-12-12 | 国网上海市电力公司 | User abnormal electricity consumption detection method and system |
CN115048434A (en) * | 2022-08-15 | 2022-09-13 | 南京灿能电力自动化股份有限公司 | Electric energy quality data processing method |
WO2024098990A1 (en) * | 2022-11-11 | 2024-05-16 | 浙江万胜智能科技股份有限公司 | Special transformer acquisition terminal-based electric energy quality monitoring method and system |
CN116754901A (en) * | 2023-08-21 | 2023-09-15 | 安徽博诺思信息科技有限公司 | Power distribution network fault analysis management platform based on quick positioning |
CN116754901B (en) * | 2023-08-21 | 2023-11-03 | 安徽博诺思信息科技有限公司 | Power distribution network fault analysis management platform based on quick positioning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112949721A (en) | Power equipment static data quality assessment method and system | |
CN113792825B (en) | Fault classification model training method and device for electricity information acquisition equipment | |
CN107506868B (en) | Method and device for predicting short-time power load | |
Glänzel | The application of characteristic scores and scales to the evaluation and ranking of scientific journals | |
CN111343147B (en) | Network attack detection device and method based on deep learning | |
CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
CN115081025A (en) | Sensitive data management method and device based on digital middlebox and electronic equipment | |
CN111582315B (en) | Sample data processing method and device and electronic equipment | |
CN116167010A (en) | Rapid identification method for abnormal events of power system with intelligent transfer learning capability | |
CN106708729A (en) | Code defect predicting method and device | |
CN114139931A (en) | Enterprise data evaluation method and device, computer equipment and storage medium | |
CN117155771B (en) | Equipment cluster fault tracing method and device based on industrial Internet of things | |
CN114066261A (en) | Tampering detection method and device for electric meter, computer equipment and storage medium | |
CN111460293B (en) | Information pushing method and device and computer readable storage medium | |
CN111080489A (en) | Load trend prediction method, system and equipment | |
Anis et al. | An expository note on unit-Gompertz distribution with applications | |
CN115035966B (en) | Superconductor screening method, device and equipment based on active learning and symbolic regression | |
CN111950623A (en) | Data stability monitoring method and device, computer equipment and medium | |
CN111178556A (en) | Electric quantity abnormality detection method and device, computer equipment and readable storage medium | |
CN115423159A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
CN114660468A (en) | Retired battery state of charge prediction method and device and electronic equipment | |
CN112395179B (en) | Model training method, disk prediction method, device and electronic equipment | |
CN115083442B (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
CN110610213A (en) | Mail classification method, device, equipment and computer readable storage medium | |
CN110580494A (en) | Data analysis method based on quantile logistic regression |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210611 |