CN114663253A - High-voltage user power utilization inspection plan auxiliary decision-making method and related device - Google Patents
High-voltage user power utilization inspection plan auxiliary decision-making method and related device Download PDFInfo
- Publication number
- CN114663253A CN114663253A CN202210279802.5A CN202210279802A CN114663253A CN 114663253 A CN114663253 A CN 114663253A CN 202210279802 A CN202210279802 A CN 202210279802A CN 114663253 A CN114663253 A CN 114663253A
- Authority
- CN
- China
- Prior art keywords
- electricity
- data
- voltage
- user
- layer
- 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 91
- 238000007689 inspection Methods 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 claims abstract description 82
- 230000008569 process Effects 0.000 claims abstract description 37
- 230000005611 electricity Effects 0.000 claims description 321
- 239000011159 matrix material Substances 0.000 claims description 67
- 238000004364 calculation method Methods 0.000 claims description 64
- 230000002159 abnormal effect Effects 0.000 claims description 36
- 238000012423 maintenance Methods 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 2
- 230000005856 abnormality Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 101100261006 Salmonella typhi topB gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007781 pre-processing 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
- 101150032437 top-3 gene Proteins 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- 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
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an auxiliary decision-making method and a related device for a power utilization inspection plan of a high-voltage user. According to the invention, the power utilization abnormity of the high-voltage user is detected by programming the first power utilization data, so that the influence of human factors on the detection process is avoided, and the accuracy and the detection efficiency of power utilization detection are improved.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to an auxiliary decision-making method for a power utilization inspection plan of a high-voltage user and a related device.
Background
With the rapid development of the economy of various industries, the demand of production and life for high voltage electricity keeps growing rapidly, and the number of high voltage users increases year by year. Meanwhile, when the high-voltage user uses high-voltage electricity, the high-voltage electricity distribution system has the characteristics of high incoming line voltage level, more high-voltage and low-voltage equipment of a power distribution room, large electricity consumption and the like, and the high-voltage electricity distribution system has higher requirements on the safety and reliability of electricity utilization inside the high-voltage user, so that the high-voltage electricity distribution system plays an important role in carrying out periodic or special electricity utilization safety check on the high-voltage user to guarantee safe electricity utilization of the user and safe and reliable operation of a power grid.
The current process of safety check of electricity consumption for high-voltage users generally shows as follows: the business personnel evaluate according to the information that information-based systems such as marketing system, power consumption information acquisition system collected, confirm the inspection object, the inspection object of selecting carries out the power consumption safety inspection, but at this in-process, receive factors such as business personnel's own experience, service level, the accuracy when often making screening process inefficiency and aassessment different high-voltage user's power consumption potential safety hazard and safe power consumption condition is lower, lead to having the high-voltage user of potential safety hazard or violation power consumption action not in time to be brought into the inspection plan, cause the risk to the safety and stability operation of electric wire netting, also influence high-voltage user's self economic benefits.
Disclosure of Invention
The invention provides an auxiliary decision-making method and a related device for a power utilization inspection plan of a high-voltage user, which are used for solving the problems of low accuracy and low efficiency caused by the fact that the high-voltage user with power utilization risks is screened manually when the power utilization condition of the high-voltage user is inspected in a current power system.
According to an aspect of the invention, an auxiliary decision-making method for a high-voltage user electricity utilization inspection plan is provided, which comprises the following steps:
acquiring first electricity data of a high-voltage user, wherein the first electricity data is a set of real-time numerical values of various electricity utilization parameters generated in an electricity utilization process of the high-voltage user monitored by an electric power system;
carrying out power utilization abnormity detection on the first power utilization data to obtain a detection result;
if the detection result is abnormal electricity utilization, the first electricity utilization data is indicated
Classifying the high-voltage users as abnormal electricity utilization high-voltage users;
if the detection result is that the power consumption is normal, second electricity data are obtained for the high-voltage users, and the second electricity data comprise bottom layer operation data of the power system with a fixed number of items;
performing hierarchical analysis calculation on the second electrical data to obtain the electricity utilization specification score of the high-voltage user;
classifying the high-voltage users according to the electricity utilization specification scores;
and carrying out electricity utilization inspection on the high-voltage users according to the classification.
According to another aspect of the present invention, there is provided a high voltage user electricity utilization inspection plan assistant decision device, including:
the first electricity data acquisition module is used for acquiring first electricity data of a high-voltage user, wherein the first electricity data is a set of real-time numerical values of various electricity utilization parameters generated in the electricity utilization process of the high-voltage user monitored by an electric power system;
the power utilization abnormity detection module is used for carrying out power utilization abnormity detection on the first power utilization data to obtain a detection result;
the high-voltage user first classification module is used for classifying the high-voltage users pointed by the first electricity utilization data as abnormal electricity utilization high-voltage users if the detection result is that electricity utilization is abnormal;
the second electrical data acquisition module is used for acquiring second electrical data for the high-voltage user if the detection result shows that the power consumption is normal, wherein the second electrical data comprises bottom layer operation data of the power system with a fixed number of items;
the hierarchical analysis module is used for performing hierarchical analysis calculation on the second electrical data to obtain the electricity utilization specification score of the high-voltage user;
the high-voltage user second classification module is used for classifying the high-voltage users according to the electricity utilization specification scores;
and the electricity utilization checking module is used for checking the electricity utilization of the high-voltage users according to the classification.
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 content of the first and second substances,
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 the high voltage user electricity inspection plan assistant decision method according to any embodiment 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 the high voltage user electricity inspection plan assistant decision method according to any one of the embodiments of the present invention when executed.
The technical scheme of the embodiment of the invention includes that the first electricity data of a high-voltage user are obtained, electricity utilization abnormity detection is carried out on the first electricity data, a detection result about the electricity utilization safety condition of the high-voltage user is obtained, then the second electricity data are obtained for the high-voltage user when the electricity utilization is normal, the electricity utilization safety condition of the high-voltage user is further evaluated by combining a hierarchical analysis method, the electricity utilization specification score of the high-voltage user is obtained, the high-voltage user is classified again through the electricity utilization specification score, then the electricity utilization inspection is carried out on the high-voltage user according to the classification result, compared with the current manual screening method for determining the high-voltage user receiving the electricity utilization inspection, the first electricity data generated by the high-voltage user in the electricity utilization process is fully utilized, the electricity utilization abnormity detection in the first electricity data is programmatically determined for the electricity utilization condition of the high-voltage user, the influence of human factors on the detection process is avoided, the accuracy of power utilization condition detection is improved, the automatic detection process also improves the detection efficiency, and the high-voltage users are classified according to different power utilization conditions of the high-voltage users to receive power utilization inspection, so that the inspection arrangement of the high-voltage users for receiving the power utilization inspection is more reasonable.
Further, when detecting that the power consumption safety condition of the high-voltage user is abnormal in this embodiment, directly classify the high-voltage user as an abnormal power consumption high-voltage user, the high-voltage user who has the potential safety hazard of power consumption is ensured to be screened out in time, and when the detection result of the high-voltage user is normal power consumption in this embodiment, still further evaluate the power consumption safety condition of the high-voltage user according to the second power consumption data, the potential detection error caused by simply relying on the power consumption detection power consumption abnormal detection step is avoided, thereby further promoting the safety and reliability of the high-voltage user and the power grid operation, and reducing the safety threat and economic loss caused by the detection error and the like. 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 an auxiliary decision method for a high-voltage user electricity utilization inspection plan according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an auxiliary decision-making device for a high-voltage user electricity utilization inspection plan according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device implementing an auxiliary decision-making method for a high-voltage user power utilization check plan according to a third embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be 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. Moreover, 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 auxiliary decision-making method for a power utilization inspection plan of a high-voltage user according to an embodiment of the present invention, which is applicable to evaluating and classifying power utilization conditions of the high-voltage user, and performing power utilization inspection on the high-voltage user according to a classification result. As shown in fig. 1, the method includes:
s110, first electricity data of the high-voltage users are obtained, and the first electricity data are a set of real-time numerical values of various electricity utilization parameters generated in the process that the power system monitors the electricity utilization of the high-voltage users.
In this embodiment, the high voltage generally refers to 35KV (kilovolt) and above, the high voltage user may be a user between an ultra-high voltage user and a low voltage user in the power system, the high voltage user may use the voltage at the ultra-high voltage user for self power supply through transformation in the working process, and may also reduce the voltage through transformation again, thereby supplying power to the low voltage user composed of factory or civil power supply lines, so the high voltage user plays a role in the power system after starting, and is in a more important position, and by detecting the power consumption condition of the high voltage user, it may help to guarantee the overall power consumption safety and power consumption efficiency of the power system. In this embodiment, when the power system detects a high-voltage user, first power data may be obtained, where the first power data is a set of multiple monitored power consumption parameters in a power consumption process of the high-voltage user, and for example, the first power data may include total active power, a/B/C phase voltage, a/B/C phase current, a/B/C phase active power, an a/B/C phase power factor, and the like. It can be known that each electricity utilization parameter correspondingly has own real-time numerical value when monitoring, so the electricity utilization safety condition of the high-voltage user can be judged according to the real-time numerical values of the electricity utilization parameters.
In this embodiment, in addition to a plurality of types, for example, a sensor failure of collected data or a data loss of collected data may occur in the data collection process, so as to ensure accuracy of analyzing the power consumption safety condition of the high-voltage user, after the first power consumption data is acquired, real-time values of various power consumption parameters in the first power consumption data may be preprocessed, for example:
and detecting whether the first electronic data has data loss, wherein the data loss mainly comprises recorded data and a field in the recorded data, and both the recorded data and the field in the recorded data cause inaccuracy of the analysis result. When detecting whether the first electricity data has data loss, the evaluation can be performed through the recorded value and the unique value in the data statistics, for example, the data of the electricity utilization parameters in the first electricity data collected in the same past time period is 30, and if the data of the electricity utilization parameters in the first electricity data suddenly drops to 5 in a certain day, the data loss is indicated.
If the data loss occurs, average value filling is performed on the first electric data, and after the data loss occurs, the embodiment may use an average value filling method to remedy the data loss, and the implementation does not limit the use of other preprocessing methods for data loss, such as a deletion method, an interpolation method, and the like.
In this embodiment, when the first electricity data is preprocessed, it is possible to detect whether an abnormal value occurs in the first electricity data, and when a deviation between a real-time value of the electricity consumption parameter in the acquired first electricity data and an average value exceeds 3 times of a standard deviation, it may be regarded that the abnormal value occurs.
And S120, carrying out power utilization abnormity detection on the first power utilization data to obtain a detection result.
In this embodiment, after the first electricity data is acquired, the electricity utilization abnormality of the first electricity data may be detected, and the condition of electricity utilization safety of the high-voltage user is judged according to a detection result.
In the embodiment, the electricity utilization abnormity detection is carried out on the first electricity data, firstly, the characteristic electricity utilization data is extracted from the first electricity data, this is because the power consumption parameters of high-voltage users are usually monitored at regular time intervals, for example, the real-time values of the electricity utilization parameters are recorded every 15 minutes, however, as a result of this implementation, each electricity utilization parameter will have 96 real-time values in one day, if the electricity utilization abnormality detection is performed on each collected real-time value of the electricity utilization parameter, the calculation amount is too large, the calculation frequency is too many, the waste of calculation resources and storage resources is caused, therefore, in the embodiment, more representative electricity utilization periods such as peak electricity utilization period, ordinary electricity utilization period and valley electricity utilization period can be selected, and taking the recorded real-time numerical value of the electricity utilization parameter as first electricity utilization data to detect electricity utilization abnormity.
The specific process of selecting the three time periods in this embodiment may be represented as follows:
the time for inquiring and collecting the first electricity data is used as the collecting time, the collecting time is divided into a peak electricity utilization time interval, a low-valley electricity utilization time interval and a normal electricity utilization time interval, the collecting time of each electricity utilization parameter in the first electricity data can be recorded, the electricity utilization time of a high-voltage user can be obviously carried out in a production mode according to life habits of people, and therefore the representative electricity utilization parameters in the three time intervals can be obtained by inquiring the collecting time of each electricity utilization parameter in the first electricity data.
In the embodiment, after the power consumption parameters of representative high-voltage users are obtained, the statistical characteristics corresponding to the power consumption parameters can be obtained through statistical calculation, and the accuracy of subsequent analysis is further improved. In this embodiment, the statistical characteristic of the electricity consumption parameter may be calculated by 1) calculating a first average load characteristic, a first difference characteristic, and a first extreme value characteristic for first electricity consumption data collected during a peak electricity consumption period, where the calculation formula for calculating the first average load characteristic is as follows: a is1＝Pav/PmaxWherein a is1Representing a first average load characteristic, PavRepresenting the average value, P, of the real-time values of a certain electricity consumption parameter during peak electricity periodsmaxIt represents the maximum value of the real-time value of the electricity utilization parameter during peak electricity utilization period. The calculation formula for calculating the first difference characteristic in this embodiment may be: a is2＝(Pmax-Pmin)/PmaxWherein a is2Representing a first difference characteristic, PminAnd the minimum value of the real-time numerical value of the electricity utilization parameter in the peak electricity utilization period is shown. The calculation formula for calculating the first extremum characteristic in this embodiment may be: a is a3＝∑i＝top3Pi/3 wherein a3Representing a first extreme characteristic, i represents the number of terms of the real-time numerical value of the electricity utilization parameter, top3 represents the maximum three real-time numerical values acquired during the peak electricity utilization period of the electricity utilization parameter, PiRepresenting one of three real-time values.
2) And calculating a second average load characteristic, a second difference characteristic and a second extreme characteristic for the first electricity data acquired in the valley electricity utilization period, wherein the calculation principle of each characteristic in the valley electricity utilization period is the same as that in the peak electricity utilization period.
3) The third load characteristic, the third difference characteristic and the third pole characteristic are calculated for the first electricity data collected in the ordinary electricity consumption time period, and the calculation principle of each yarn characteristic in the ordinary electricity consumption time period in the embodiment is the same as that in the peak electricity consumption time period.
The characteristic electricity utilization data is obtained by screening the first average load characteristic, the first difference characteristic and the first extreme characteristic, the second average load characteristic, the second difference characteristic and the second extreme characteristic, the third load characteristic, the third difference characteristic and the third extreme characteristic through a characteristic recursion elimination method, in the embodiment, three electricity utilization characteristics of the electricity utilization parameters, namely the average load characteristic, the difference characteristic and the extreme characteristic, are respectively obtained, and excessive calculation data is also caused by combining the number of terms of the electricity utilization parameters obtained before, for example, when the electricity utilization parameters of the selected high-voltage users are 13 terms, each electricity utilization parameter corresponds to 9 characteristic values, the data for analyzing the electricity utilization safety condition of the high-voltage users reach 117, and when the dimensionality of the data is excessive in a subsequent electricity utilization abnormity detection model, the classification and identification of the model are not easy to realize in the training process of the abnormal electricity utilization detection model, therefore, the data dimension can be reduced by the characteristic recursion elimination method provided in the embodiment.
The characteristic recursion elimination method reduces the data dimension by eliminating the redundancy among the characteristics and selecting the optimal characteristics, and the specific process can be represented as follows: (1) inputting the screened k features as an initial feature subset into a random forest classifier, calculating to obtain the importance of each feature, and obtaining the classification accuracy of the initial feature subset by using a cross validation method, where k is the number of the features, and in this embodiment, k may be the above 117 features, that is, different feature values of the above-mentioned power consumption parameter at different time periods.
(2) And removing a feature with the lowest feature importance from the current feature subset to obtain a new feature subset, inputting the new feature subset into the random forest classifier again, calculating the importance of each feature in the new feature subset, and obtaining the classification accuracy of the new feature subset by using a cross-validation method.
(3) And repeating the step 2 in a recursive manner until the feature subset is empty, finally obtaining k feature subsets with different feature quantities, and selecting the feature subset with the highest classification precision as the optimal feature combination, namely the final feature electricity utilization data in the embodiment.
After the characteristic electricity utilization data are obtained, the characteristic electricity utilization data can be input into a pre-trained electricity utilization abnormity detection model so as to output a detection result.
In this embodiment, the power consumption abnormality detection model may be pre-trained, for example, the characteristic power consumption data is divided into a training set and a testing set, and the training and testing evaluation are performed on a plurality of models respectively, where the types of the models used for training may be a random forest model, an XGBoost model, a LightGBM model, an SVM model, and the like, and when the optimal power consumption abnormality detection model is selected in this embodiment, two parameters, i.e., classification accuracy and recall rate, may be used as evaluation indexes for comprehensive optimization.
When the characteristic electricity utilization data are input into the electricity utilization abnormality detection model, the electricity utilization abnormality detection model can output detection results according to the classification during training, and the detection results comprise electricity utilization abnormality and electricity utilization normality.
And S130, if the detection result is that the electricity utilization is abnormal, classifying the high-voltage users pointed by the first electricity utilization data as abnormal electricity utilization high-voltage users.
In this embodiment, when the detection result of the power consumption abnormality detection model is a power consumption abnormality, in order to avoid damage such as power grid outage caused by considering the important status of the high-voltage users in the power grid operation, the high-voltage users to which the first power consumption data obtained from the detection result points can be classified as abnormal power consumption high-voltage users, so as to prompt the abnormal power consumption high-voltage users to perform power consumption inspection in time, and prevent damage and loss.
And S140, if the power consumption is normal, acquiring second electrical data for the high-voltage user, wherein the second electrical data comprises bottom operating data of the fixed-item power system.
In this embodiment, when the detection result output by the power consumption abnormality detection model is that power consumption is normal, a certain error may exist in the detection process and the severity of an effect caused if the error occurs is considered, in this embodiment, second electrical data may be obtained for a high-voltage user when the detection result is that power consumption is normal, and the second electrical data may be bottom layer operation data of each facility of an electrical power system that supplies power to the high-voltage user and bottom layer operation data that the electrical power system evaluates the high-voltage user based on past power consumption behavior. For example, the operation data of each facility of the power system can be divided into the bottom operation data of the power equipment operation and maintenance layer, the bottom operation data of the operation environment layer, and the bottom operation data evaluated by the high-voltage user can be divided into the user payment layer and the user credit layer, wherein the bottom operation data of the power equipment operation and maintenance layer can include: operation data of pole towers, drop-out fuses, on-pole isolating switches, high-voltage cabinets, transformers and the like, and the bottom layer operation data of the operation environment layer can comprise: the user payment layer can comprise monthly average payment rate, monthly average payment timeliness rate, accumulated arrearage total amount and the like, and the user credit layer can comprise bottom layer operation data such as illegal electricity utilization records and safety accident records. In this embodiment, each bottom layer operation data may be assigned a score of 100, and the score may be added or subtracted according to the actual operation condition, so that the power utilization safety condition of the high-voltage user and the operation condition of the power system are reflected by the score of the bottom layer operation data.
And S150, performing hierarchical analysis calculation on the second electrical data to obtain the electricity utilization specification score of the high-voltage user.
In this embodiment, after the second electrical data is acquired, the electrical safety condition of the high-voltage user included in the second electrical data may be analyzed in an analytic hierarchy process, the electrical specification score of the high-voltage user is obtained through analysis, and then the high-voltage user may be classified according to the electrical specification score of the high-voltage user, and an electrical inspection and the like are arranged, so that the operation safety of the power system is ensured.
Analytic Hierarchy Process (AHP) is a simple method for making decisions on more complex and fuzzy problems, and is particularly suitable for the problems that are difficult to be completely quantitatively analyzed. When the analytic modeling is carried out by using the analytic hierarchy process, the analytic modeling can be carried out according to the following four steps in general: (i) establishing a hierarchical structure model; (ii) constructing all judgment matrixes in each layer; (iii) sorting the hierarchical lists and checking consistency; (iv) and (5) carrying out overall hierarchical ordering and consistency check. In this embodiment, when applying the analytic hierarchy process, the process may be performed according to the above steps, and specifically includes establishing a hierarchical structure model of the power consumption specification score-user payment layer, the user credit layer, the power equipment operation and maintenance layer, and the operating environment layer-bottom operating data, and then constructing determination matrices of each level, that is, a determination matrix of the bottom operating data on the user payment layer, a determination matrix of the bottom operating data on the user credit layer, a determination matrix of the bottom operating data on the power equipment operation and maintenance layer, and a determination matrix of the bottom operating data on the operating environment layer, and a determination matrix of the power consumption specification score of the user payment layer, the user credit layer, the power equipment operation and maintenance layer, and the operating environment layer, respectively, and a more specific process includes:
1501. and classifying the bottom layer operation data in the second electric data into first operation data of a user payment layer, second operation data of a user credit layer, third operation data of an electric power equipment operation and maintenance layer and fourth operation data of an operation environment layer, wherein the bottom layer operation data can be selected for establishing a user payment layer, the user credit layer, the electric power equipment operation and maintenance layer and an operation environment layer judgment matrix.
1502. In the embodiment, each item of bottom layer operation data classified in the user payment layer, namely the first operation data, has an influence on numerical calculation of the user payment layer, and each item of bottom layer operation data has different influence weights on the user payment layer, and the first influence weight is a set of influence weights of the bottom layer operation data of the user payment layer.
The calculating of the first influence weight in this embodiment may specifically be represented as:
comparing the importance of every two first operation data to establish a first judgment matrix, wherein the comparison of the importance in this embodiment can be accomplished by using a 1-9 scale method, for example, comparing the importance of the first operation data i with the importance of the first operation data j, and comparing aijAs a result of the comparison of the importance, wherein i, j represents the sequence number of the first operation data, when the importance of the first operation data i is the same as that of the first operation data j, a is the sameijIs 1, when the importance comparison is completed, the first operation data can be compared two by two to obtain a value aijAnd filling the position of the ith row and the jth column of the first judgment matrix, and completing the establishment of the whole first judgment matrix according to the principle.
After the first judgment matrix piece is established, consistency check can be performed on the first judgment matrix, because when the first judgment matrix is the consistency matrix, the normalized eigenvector of the first judgment matrix can be used as the weight vector, and then influence weights of various first operation data on the user payment layer can be obtained by inquiring the normalized eigenvector of the first judgment matrix, so that the first influence weight is obtained.
If the consistency check is passed, calculating a first maximum eigenvector for the first judgment matrix, and after the consistency check is passed, selecting the maximum eigenvector of the first judgment matrix to query the influence weight of the first operation data, wherein the maximum eigenvector can be expressed as an eigenvector matrix, and the numerical value of each row in the eigenvector matrix can express the influence weight of each item of the first operation data on the user payment layer.
And inquiring the first maximum characteristic vector, acquiring a first influence weight of the first operation data on the user payment layer, namely searching the numerical value of each row in the characteristic vector matrix.
1503. And calculating a second influence weight of the second operation data on the credit layer of the user.
The specific process of calculating the second influence weight of the second operation data on the user credit layer in this embodiment is as follows, and the calculation principle and the calculation method involved in the calculation are the same as those in the calculation of the first influence weight, and specifically include:
comparing the importance of every two second operation data to establish a second judgment matrix;
carrying out consistency check on the second judgment matrix;
if the consistency check is passed, calculating a second maximum eigenvector for the second judgment matrix;
inquiring the second maximum characteristic vector, and acquiring second influence weight of the second operation data on the user payment layer;
1504. and calculating a third influence weight of the third operation data on the operation and maintenance layer of the power equipment.
The specific process of calculating the third influence weight of the third operating data on the user credit layer in this embodiment is as follows, where the calculation principle and the calculation method involved in the calculation are the same as those in the calculation of the first influence weight, and specifically include:
comparing the importance of every two third operation data to establish a third judgment matrix;
carrying out consistency check on the third judgment matrix;
if the consistency check is passed, calculating a third maximum eigenvector for the third judgment matrix;
inquiring a third maximum characteristic vector, and acquiring a third influence weight of third operation data on a user payment layer;
1505. and calculating a fourth influence weight of the fourth operation data on the operation environment layer.
The specific process of calculating the fourth influence weight of the fourth operation data on the user credit layer in this embodiment is as follows, and the calculation principle and the calculation method involved in the calculation are the same as those in the calculation of the first influence weight, and specifically include:
comparing the importance of every two fourth operation data to establish a fourth judgment matrix;
carrying out consistency check on the fourth judgment matrix;
if the consistency check is passed, calculating a fourth maximum eigenvector for the fourth judgment matrix;
and inquiring the fourth maximum feature vector, and acquiring fourth influence weight of the fourth operation data on the user payment layer.
1506. And calculating fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on the acquisition of the power utilization specification scores of the high-voltage users.
In this embodiment, after the influence weights of each bottom layer operation data on the user payment layer, the user credit layer, the power equipment operation and maintenance layer, and the operation environment layer are obtained through calculation, a fifth influence weight of the user payment layer, the user credit layer, the power equipment operation and maintenance layer, and the operation environment layer on the user specification score may be further calculated, the calculation principle and the calculation method are the same as those in the case of calculating the first influence weight, and the specific process may be expressed as follows:
comparing the importance of each item of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer to establish a fifth judgment matrix;
carrying out consistency check on the fifth judgment matrix;
if the consistency check is passed, calculating a fifth maximum eigenvector for the fifth judgment matrix;
and inquiring the fifth maximum characteristic vector, and acquiring fifth influence weights of a user payment layer, a user credit layer, an electric power equipment operation and maintenance layer and an operation environment layer on the electricity utilization standard score.
1507. And querying real-time scores of the first operation data, the second operation data, the third operation data and the fourth operation data.
In this embodiment, each piece of bottom layer operation data has a real-time value, for example, the second operation data of the user credit layer may include bottom layer operation data recorded illegally with electricity, so that when there is no illegal electricity record for the high-voltage user, the real-time value of the bottom layer operation data may be 100 minutes, but if there is an illegal electricity record for the high-voltage user, the real-time value of the bottom layer operation data may be assigned to be 0. In this embodiment, for calculating the user specification power consumption score, after the first influence weight, the second influence weight, the third influence weight, and the fourth influence weight are obtained through calculation, the real-time scores of the first operation data, the second operation data, the third operation data, and the fourth operation data need to be obtained.
1508. In this embodiment, the real-time scores of the user payment layers, that is, the first electronic electricity standard scores, and the second electronic electricity standard scores, the third electronic electricity standard scores, and the fourth electronic electricity standard scores, can be obtained by performing weighting calculation in a one-to-one correspondence manner according to the real-time scores of each bottom layer operation data in the first operation data and the influence weights of each bottom layer operation data in the first influence weights obtained by calculation, and the second electronic electricity standard scores, the third electronic electricity standard scores, and the fourth electronic electricity standard scores can be obtained by the same method, which includes the following specific processes:
performing weighted calculation on the real-time scores of the first operation data by combining with the first influence weights to obtain first electronic electricity standard scores;
performing weighted calculation on the real-time scores of the second operation data in combination with the second influence weights to obtain second electronic electricity utilization specification scores;
performing weighted calculation on the real-time fraction of the third operation data in combination with the third influence weight to obtain a third electronic electricity utilization specification fraction;
and performing weighted calculation on the real-time fraction of the fourth operation data by combining the fourth influence weight to obtain a fourth electronic electricity standard fraction.
1509. And combining the first electronic electricity specification score, the second electronic electricity specification score, the third electronic electricity specification score, the fourth electronic electricity specification score and the fifth influence weight to weight and calculate the electricity specification score of the high-voltage user.
In this embodiment, the power consumption specification score of the high-voltage user is determined by the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer, so that after the first electronic power consumption specification score, the second electronic power consumption specification score, the third electronic power consumption specification score and the fourth electronic power consumption specification score are obtained through calculation, the power consumption specification score of the high-voltage user can be obtained through weighted calculation according to influence weights of different layers in the fifth influence weights on the power consumption specification score.
And S160, classifying the high-voltage users according to the power utilization specification scores.
In this embodiment, after the power consumption specification score of the high-voltage user is obtained through calculation, the high-voltage user may be classified according to the power consumption specification score, specifically, a classification interval may be first defined according to the power consumption specification score, for example, if the power consumption specification score is in a preset first interval, the high-voltage user to which the power consumption specification score points is classified as an abnormal power consumption high-voltage user, where the preset first interval may be that the power consumption specification score is less than 70.
And if the electricity utilization specification score is in a preset second interval, classifying the high-voltage users pointed by the electricity utilization specification score into suspected abnormal electricity utilization high-voltage users, wherein the electricity utilization specification score in the second interval can be more than or equal to 70 and less than 90.
If the electricity specification score is in a preset third interval, classifying the high-voltage users pointed by the electricity specification score as normal electricity high-voltage users, wherein the third interval can be more than 90 minutes, and it is noted that the electricity specification score is fully divided into 100 minutes.
And S170, carrying out electricity utilization inspection on the high-voltage users according to the classification.
In this embodiment, after the classification of the high-voltage users is finished, the power consumption safety conditions of different high-voltage users are correspondingly known, so that the power consumption inspection of the high-voltage users can be arranged according to the classification conditions of the high-voltage users, for example, the power consumption inspection arrangement with the highest priority is set for the high-voltage users classified as abnormal power consumption high-voltage users, that is, the high-voltage users are arranged in the last power consumption inspection to inspect the power consumption safety. In this embodiment, a higher voltage user classified as a suspected abnormal power consumption higher voltage user may be set with a lower priority for power consumption inspection arrangement, so as to prompt the higher voltage user to perform regular power consumption safety inspection. Can also set up the electricity inspection priority of lower one-level with categorised high-voltage consumer for normal power consumption high-voltage consumer in this embodiment, it is good to indicate this high-voltage consumer electricity safety condition promptly, need not carry out electricity safety inspection temporarily, from this embodiment through the automatic arrangement to high-voltage consumer electricity safety inspection plan of having accomplished to high-voltage consumer's categorised, compare in the manual work and formulate electricity inspection plan, this embodiment is more high-efficient, accurate completion the appointed of electricity inspection plan, and this embodiment is from user's layer of paying fees, user credit layer, a plurality of angles such as power equipment fortune dimension layer and operational environment layer are considered comprehensively, can reflect high-voltage consumer's electricity safety condition more comprehensively, thereby scientific completion high-voltage consumer's classification.
The technical scheme of the embodiment of the invention includes that the first electricity data of a high-voltage user are obtained, electricity utilization abnormity detection is carried out on the first electricity data, the detection result about the electricity utilization safety condition of the high-voltage user is obtained, then the second electricity data are obtained for the high-voltage user when the detection result is that the electricity utilization is normal, the electricity utilization safety condition of the high-voltage user is further evaluated by combining a hierarchical analysis method, the electricity utilization specification score of the high-voltage user is obtained, the high-voltage user is classified again through the electricity utilization specification score, then the electricity utilization inspection is carried out on the high-voltage user according to the classification result, compared with the method for determining the high-voltage user receiving the electricity utilization inspection by manually screening at present, the first electricity data generated by the high-voltage user in the electricity utilization process is fully utilized, the electricity utilization abnormity detection in the first electricity data is programmed to determine the electricity utilization condition of the high-voltage user, the influence of human factors on the detection process is avoided, the accuracy of power utilization condition detection is improved, the automatic detection process also improves the detection efficiency, and the high-voltage users are classified according to different power utilization conditions of the high-voltage users to receive power utilization inspection, so that the inspection arrangement of the high-voltage users for receiving the power utilization inspection is more reasonable.
Further, when detecting that the power consumption safety condition of the high-voltage user is abnormal in this embodiment, directly classify the high-voltage user as an abnormal power consumption high-voltage user, the high-voltage user who has the potential safety hazard of power consumption is ensured to be screened out in time, and when the detection result of the high-voltage user is normal power consumption in this embodiment, still further evaluate the power consumption safety condition of the high-voltage user according to the second power consumption data, the potential detection error caused by simply relying on the power consumption detection power consumption abnormal detection step is avoided, thereby further promoting the safety and reliability of the high-voltage user and the power grid operation, and reducing the safety threat and economic loss caused by the detection error and the like.
Example two
Fig. 2 is a schematic structural diagram of an auxiliary decision-making device for a high-voltage user power utilization check plan according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes:
the first electricity data acquiring module 210 is configured to acquire first electricity data of a high-voltage user, where the first electricity data is a set of real-time numerical values of various electricity consumption parameters generated by an electric power system monitoring an electricity consumption process of the high-voltage user.
And the power utilization abnormity detection module 220 is used for performing power utilization abnormity detection on the first power utilization data to obtain a detection result.
The high-voltage user first classification module 230 is configured to classify the high-voltage user to which the first electricity consumption data points as an abnormal electricity consumption high-voltage user if the detection result is that electricity consumption is abnormal.
And a second electrical data acquisition module 240, configured to acquire second electrical data for the high-voltage user if the power consumption is normal according to the detection result, where the second electrical data includes a fixed number of pieces of bottom-layer operation data of the power system.
And the hierarchical analysis module 250 is configured to perform hierarchical analysis calculation on the second electrical data to obtain the power utilization specification score of the high-voltage user.
And the high-voltage user second classification module 260 is used for classifying the high-voltage users according to the electricity specification scores.
And the electricity utilization checking module 270 is used for checking the electricity utilization of the high-voltage users according to the classification.
Optionally, the device for assisting in decision-making of the power utilization check plan of the high-voltage user further includes:
the data missing detection module is used for detecting whether the first electric data is missing or not, and if so, the average value filling module is called;
a mean-filling module to perform mean-filling on the first electrical data;
the abnormal value detection module is used for detecting whether the abnormal value occurs in the first electric data or not, and if the abnormal value occurs, the moving average processing module is called;
and the moving average processing module is used for executing moving average processing on the first electric data.
Optionally, the power consumption abnormality detecting module 220 includes:
the characteristic electricity utilization data extraction module is used for extracting characteristic electricity utilization data from the first electricity utilization data;
and the characteristic electricity utilization data input module is used for inputting the characteristic electricity utilization data into a pre-trained electricity utilization abnormity detection model so as to output a detection result.
Optionally, the feature electricity consumption data extraction module includes:
a collection time query module for querying the time of collecting the first electricity data as collection
The collection time is divided into a peak power utilization time period, a low-ebb power utilization time period and a normal power utilization time period;
the first characteristic calculation module is used for calculating a first average load characteristic, a first difference characteristic and a first extreme value characteristic of the first electricity consumption data collected in the peak electricity consumption period;
the second characteristic calculation module is used for calculating a second average load characteristic, a second difference characteristic and a second extreme characteristic of the first electricity data collected in the valley electricity utilization period;
the third characteristic calculation module is used for calculating a third load characteristic, a third difference characteristic and a third pole characteristic of the first electricity data acquired in the ordinary electricity time period;
and the characteristic electricity data screening module is used for screening the first average load characteristic, the first difference characteristic and the first extreme value characteristic, the second average load characteristic, the second difference characteristic and the second extreme value characteristic, the third load characteristic, the third difference characteristic and the third extreme value characteristic by a characteristic recursive elimination method to obtain characteristic electricity data.
Optionally, the hierarchical analysis module 250 includes:
the bottom layer operation data classification module is used for classifying the bottom layer operation data in the second electric data into first operation data of a user payment layer, second operation data of a user credit layer, third operation data of an electric power equipment operation and maintenance layer and fourth operation data of an operation environment layer,
the first influence weight calculation module is used for calculating first influence weight of the first operation data on the user payment layer;
the second influence weight calculation module is used for calculating second influence weight of the second operation data on the user credit layer;
the third influence weight calculation module is used for calculating a third influence weight of the third operation data on the operation and maintenance layer of the power equipment;
a fourth influence weight calculation module, configured to calculate a fourth influence weight of the fourth operation data on the operation environment layer;
the fifth influence weight calculation module is used for calculating fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on the acquisition of the power utilization specification scores of the high-voltage users;
a real-time score query module for querying real-time scores of the first operational data, the second operational data, the third operational data and the fourth operational data;
an electronic electricity specification score calculation module that calculates a first electronic electricity specification score, a second electronic electricity specification score, a third electronic electricity specification score, and a fourth electronic electricity specification score in combination with the first impact weight, the second impact weight, the third impact weight, the fourth impact weight, and the real-time score;
and the electricity specification score calculating module is used for weighting and calculating the electricity specification score of the high-voltage user by combining the first electronic electricity specification score, the second electronic electricity specification score, the third electronic electricity specification score, the fourth electronic electricity specification score and the fifth influence weight.
Optionally, the first influence weight calculating module includes:
the first judgment matrix establishing module is used for comparing the importance of every two items of the first operation data to establish a first judgment matrix;
the consistency first checking module is used for checking the consistency of the first judgment matrix;
a first maximum feature vector calculation module, configured to calculate a first maximum feature vector for the first determination matrix if the consistency check is passed;
the first influence weight query module is used for querying the first maximum characteristic vector and acquiring a first influence weight of the first operation data on the user payment layer;
the second influence weight calculation module comprises:
the second judgment matrix establishing module is used for performing importance comparison between every two second operation data to establish a second judgment matrix;
the consistency second checking module is used for checking the consistency of the second judgment matrix;
a second maximum eigenvector calculation module, configured to calculate a second maximum eigenvector for the second decision matrix if the consistency check is passed;
the second influence weight query module is used for querying the second maximum characteristic vector and acquiring a second influence weight of the second operation data on the user credit layer;
the third influence weight calculation module includes:
the third judgment matrix establishing module is used for comparing the importance of every two third running data to establish a third judgment matrix;
the consistency third checking module is used for checking the consistency of the third judgment matrix;
a third maximum feature vector calculation module, configured to calculate a third maximum feature vector for the third determination matrix if the consistency check is passed;
a third influence weight query module, configured to query the third maximum eigenvector, and obtain a third influence weight of the third operation data on the operation and maintenance layer of the electrical equipment;
the fourth influence weight calculation module includes:
the fourth judgment matrix establishing module is used for comparing the importance of every two fourth operation data to establish a fourth judgment matrix;
the consistency fourth checking module is used for checking the consistency of the fourth judgment matrix;
a fourth maximum eigenvector calculation module, configured to calculate a fourth maximum eigenvector for the fourth determination matrix if the consistency check is passed;
a fourth influence weight query module, configured to query the fourth maximum feature vector and obtain a fourth influence weight of the fourth operation data on the operation environment layer;
optionally, the fifth influence weight calculating module includes:
the fifth judgment matrix establishing module is used for comparing the importance of each two items of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer to establish a fifth judgment matrix;
the consistency fifth checking module is used for checking the consistency of the fifth judgment matrix;
a fifth maximum eigenvector calculation module, configured to calculate a fifth maximum eigenvector for the fifth determination matrix if the consistency check is passed;
and the fifth influence weight query module is used for querying the fifth maximum feature vector and acquiring fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on the power utilization specification scores.
Optionally, the high voltage user second classification module 260 includes:
the first interval classification module is used for classifying the electricity utilization of the high-voltage users pointed by the electricity utilization specification score into abnormal electricity utilization high-voltage users if the electricity utilization specification score is in a preset first interval;
the second interval classification module is used for classifying the high-voltage users pointed by the electricity specification scores as suspected abnormal electricity utilization high-voltage users if the electricity specification scores are in a preset second interval;
and the third interval classification module is used for classifying the high-voltage users pointed by the electricity specification scores as abnormal electricity utilization high-voltage users if the electricity specification scores are in a preset third interval.
The high-voltage user power utilization inspection plan assistant decision-making device provided by the embodiment of the invention can execute the high-voltage user power utilization inspection plan assistant decision-making method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
FIG. 3 illustrates a schematic 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. 3, 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 RAM13, various programs and data required for operation of the electronic device 10 may also be stored. The processor 11, the ROM12, and the RAM13 are connected to each other by a bus 14. An input/output (I/O) interface 15 is also connected to 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.
In some embodiments, the high voltage user electricity usage inspection plan aid decision method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the 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 ROM12 and/or the communication unit 19. When the computer program is loaded into RAM13 and executed by processor 11, one or more steps of the high voltage user electricity inspection plan aid decision method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured by any other suitable means (e.g., by way of firmware) to perform the high voltage user electricity inspection plan aid decision method.
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 the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the 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 portable 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 may 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 may be used, with steps reordered, added, or deleted. 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 in accordance with 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 (12)
1. An auxiliary decision-making method for a power utilization check plan of a high-voltage user is characterized by comprising the following steps:
acquiring first electricity data of a high-voltage user, wherein the first electricity data is a set of real-time numerical values of various electricity utilization parameters generated in an electricity utilization process of the high-voltage user monitored by an electric power system;
carrying out power utilization abnormity detection on the first power utilization data to obtain a detection result;
if the detection result is abnormal electricity utilization, classifying the high-voltage users pointed by the first electricity utilization data as abnormal electricity utilization high-voltage users;
if the detection result is that the power consumption is normal, second electricity data are obtained for the high-voltage users, and the second electricity data comprise bottom layer operation data of the power system with a fixed number of items;
performing hierarchical analysis calculation on the second electrical data to obtain the electricity specification score of the high-voltage user;
classifying the high-voltage users according to the electricity utilization specification scores;
and carrying out electricity utilization inspection on the high-voltage users according to the classification.
2. The method of claim 1, further comprising, after said obtaining first electricity data for a high voltage user:
detecting whether the first electricity consumption data is missing;
if so, performing mean value padding on the first electrical data;
detecting whether an abnormal value occurs in the first electricity data;
if so, performing a moving average process on the first electrical data.
3. The method according to claim 1, wherein the performing of the power consumption anomaly detection on the first power consumption data to obtain a detection result comprises:
extracting characteristic electricity utilization data from the first electricity utilization data;
and inputting the characteristic electricity utilization data into a pre-trained electricity utilization abnormity detection model to output a detection result.
4. The method of claim 3, wherein said extracting characteristic electricity data from said first electricity data comprises:
inquiring the time for acquiring the first electricity utilization data as acquisition time, wherein the acquisition time is divided into a peak electricity utilization time period, a low-ebb electricity utilization time period and a normal electricity utilization time period;
calculating a first average load characteristic, a first difference characteristic and a first extreme value characteristic of the first electricity consumption data collected in the peak electricity consumption period;
calculating a second average load characteristic, a second difference characteristic and a second extreme characteristic of the first electricity data collected in the valley electricity utilization period;
calculating a third load characteristic, a third difference characteristic and a third pole characteristic of the first electricity data acquired in the ordinary electricity utilization time period;
and screening the first average load characteristic, the first difference characteristic and the first extreme value characteristic, the second average load characteristic, the second difference characteristic and the second extreme value characteristic, and the third load characteristic, the third difference characteristic and the third extreme value characteristic by a characteristic recursive elimination method to obtain characteristic electricity data.
5. The method according to any one of claims 1-4, wherein the performing a hierarchical analysis calculation on the second electrical data to obtain the electricity specification score of the high voltage user comprises:
classifying the bottom layer operation data in the second electrical data into first operation data of a user payment layer, second operation data of a user credit layer, third operation data of an electric power equipment operation and maintenance layer and fourth operation data of an operation environment layer,
calculating a first influence weight of the first operation data on the user payment layer;
calculating a second influence weight of the second operation data on the user credit layer;
calculating a third influence weight of the third operation data on the operation and maintenance layer of the power equipment;
calculating a fourth weight of influence of the fourth operational data on the operational environment layer;
calculating fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on the acquisition of the power utilization specification scores of the high-voltage users;
querying real-time scores of the first operational data, the second operational data, the third operational data, and the fourth operational data;
calculating a first, second, third and fourth electronic specification score in conjunction with the first, second, third, fourth impact weights and the real-time score;
and weighting and calculating the electricity specification score of the high-voltage user by combining the first electronic electricity specification score, the second electronic electricity specification score, the third electronic electricity specification score, the fourth electronic electricity specification score and the fifth influence weight.
6. The method of claim 5, wherein said calculating a first, second, third, and fourth sub-electricity specification score in combination with said first, second, third, fourth impact weights and said real-time score comprises:
performing weighted calculation on the real-time score of the first operation data by combining the first influence weight to obtain a first electronic electricity specification score;
performing weighted calculation on the real-time score of the second operation data in combination with the second influence weight to obtain a second electronic electricity standard score;
performing weighted calculation on the real-time score of the third operation data in combination with the third influence weight to obtain a third electronic electricity standard score;
and performing weighted calculation on the real-time score of the fourth operation data by combining the fourth influence weight to obtain a fourth electronic electricity specification score.
7. The method of claim 5, wherein the calculating a first impact weight of the first operational data on the customer payment layer comprises:
comparing the importance of every two items of the first operation data to establish a first judgment matrix;
carrying out consistency check on the first judgment matrix;
if the consistency check is passed, calculating a first maximum feature vector for the first judgment matrix;
inquiring the first maximum characteristic vector to obtain a first influence weight of the first operation data on the user payment layer;
the calculating a second influence weight of the second operation data on the user credit layer comprises:
comparing the importance of every two items of the second operation data to establish a second judgment matrix;
carrying out consistency check on the second judgment matrix;
if the consistency check is passed, calculating a second maximum eigenvector for the second judgment matrix;
inquiring the second maximum feature vector to obtain a second influence weight of the second operation data on the user credit layer;
the calculating a third influence weight of the third operation data on the operation and maintenance layer of the power equipment comprises:
comparing the importance of every two third operation data to establish a third judgment matrix;
carrying out consistency check on the third judgment matrix;
if the consistency check is passed, calculating a third maximum eigenvector for the third judgment matrix;
inquiring the third maximum characteristic vector to obtain a third influence weight of the third operation data on the operation and maintenance layer of the power equipment;
the calculating a fourth weight of influence of the fourth operational data on the operational environment layer includes:
comparing the importance of every two items of the fourth operation data to establish a fourth judgment matrix;
carrying out consistency check on the fourth judgment matrix;
if the consistency check is passed, calculating a fourth maximum eigenvector for the fourth judgment matrix;
and inquiring the fourth maximum feature vector to obtain a fourth influence weight of the fourth operation data on the operation environment layer.
8. The method according to claim 5, wherein the calculating fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on obtaining the power utilization specification score of the high-voltage user comprises:
comparing the importance of each item of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer to establish a fifth judgment matrix;
carrying out consistency check on the fifth judgment matrix;
if the consistency check is passed, calculating a fifth maximum eigenvector for the fifth judgment matrix;
and inquiring the fifth maximum characteristic vector to obtain fifth influence weights of the user payment layer, the user credit layer, the power equipment operation and maintenance layer and the operation environment layer on the electricity consumption specification scores.
9. The method according to any one of claims 1-4, wherein said classifying said high voltage users according to said electricity usage specification score comprises:
if the electricity utilization specification score is in a preset first interval, classifying the electricity utilization of the high-voltage users pointed by the electricity utilization specification score as abnormal electricity utilization high-voltage users;
if the electricity specification score is in a preset second interval, classifying the high-voltage users pointed by the electricity specification score as suspected abnormal electricity utilization high-voltage users;
and if the electricity specification score is in a preset third interval, classifying the high-voltage users pointed by the electricity specification score as normal electricity utilization high-voltage users.
10. An auxiliary decision-making device for a high-voltage user electricity utilization check plan is characterized by comprising:
the first electricity consumption data acquisition module is used for acquiring first electricity consumption data of a high-voltage user, wherein the first electricity consumption data is a set of real-time numerical values of various electricity consumption parameters generated in the electricity consumption process of the high-voltage user monitored by an electric power system;
the electricity utilization abnormity detection module is used for carrying out electricity utilization abnormity detection on the first electricity data to obtain a detection result;
the high-voltage user first classification module is used for classifying the high-voltage users pointed by the first electricity utilization data as abnormal electricity utilization high-voltage users if the detection result is that electricity utilization is abnormal;
the second electrical data acquisition module is used for acquiring second electrical data for the high-voltage user if the detection result shows that the power consumption is normal, wherein the second electrical data comprises bottom layer operation data of the power system with a fixed number of items;
the hierarchical analysis module is used for performing hierarchical analysis calculation on the second electrical data to obtain the electricity utilization specification score of the high-voltage user;
the high-voltage user second classification module is used for classifying the high-voltage users according to the electricity utilization specification scores;
and the electricity utilization checking module is used for checking the electricity utilization of the high-voltage users according to the classification.
11. 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 content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the high voltage user electricity inspection plan aid decision method of any one of claims 1-9.
12. A computer readable storage medium storing computer instructions for causing a processor to implement the high voltage user electricity inspection plan assistant decision method of any one of claims 1-9 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279802.5A CN114663253A (en) | 2022-03-21 | 2022-03-21 | High-voltage user power utilization inspection plan auxiliary decision-making method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279802.5A CN114663253A (en) | 2022-03-21 | 2022-03-21 | High-voltage user power utilization inspection plan auxiliary decision-making method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114663253A true CN114663253A (en) | 2022-06-24 |
Family
ID=82031492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210279802.5A Pending CN114663253A (en) | 2022-03-21 | 2022-03-21 | High-voltage user power utilization inspection plan auxiliary decision-making method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663253A (en) |
-
2022
- 2022-03-21 CN CN202210279802.5A patent/CN114663253A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223196B (en) | Anti-electricity-stealing analysis method based on typical industry feature library and anti-electricity-stealing sample library | |
| CN109544399B (en) | Power transmission equipment state evaluation method and device based on multi-source heterogeneous data | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN113360358A (en) | Method and system for adaptively calculating IT intelligent operation and maintenance health index | |
| CN115049315A (en) | Power utilization safety risk assessment method, device, equipment and storage medium | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN109542742A (en) | Database server hardware health evaluating method based on expert model | |
| CN113591393A (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
| CN113627735A (en) | Early warning method and system for safety risk of engineering construction project | |
| CN115860383A (en) | Power distribution network scheduling method and device, electronic equipment and storage medium | |
| CN116523140A (en) | Method and device for detecting electricity theft, electronic equipment and storage medium | |
| CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
| CN113807751A (en) | Safety risk grade assessment method and system based on knowledge graph | |
| CN111967684B (en) | Metering asset active distribution method based on big data analysis | |
| CN116452054A (en) | Method and device for managing material spot check of electric power system | |
| CN114663253A (en) | High-voltage user power utilization inspection plan auxiliary decision-making method and related device | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| CN114254806A (en) | Power distribution network heavy overload early warning method and device, computer equipment and storage medium | |
| CN114708117A (en) | Electricity safety inspection rating method, device and equipment integrating priori knowledge | |
| CN117131947B (en) | Overhead transmission line fault prediction method, device, equipment and storage medium | |
| CN116627695B (en) | Alarm event root cause recommendation method, device, equipment and storage medium | |
| CN114693305A (en) | Transaction fraud detection method, device, equipment, medium and product | |
| CN117217599A (en) | Evaluation method and device of power distribution network equipment, electronic equipment and storage medium | |
| CN118134462A (en) | Operation and maintenance method and device of power transformation equipment, electronic equipment and storage medium | |
| CN117195055A (en) | Classification method, device, equipment and medium for executing protection action strategy |
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 |