CN112256735B - Power consumption monitoring method and device, computer equipment and storage medium - Google Patents
Power consumption monitoring method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112256735B CN112256735B CN202011143546.4A CN202011143546A CN112256735B CN 112256735 B CN112256735 B CN 112256735B CN 202011143546 A CN202011143546 A CN 202011143546A CN 112256735 B CN112256735 B CN 112256735B
- Authority
- CN
- China
- Prior art keywords
- probability
- data
- determining
- electricity
- operation data
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 230000005611 electricity Effects 0.000 claims abstract description 111
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 38
- 238000011156 evaluation Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000007637 random forest analysis Methods 0.000 claims description 10
- 238000012806 monitoring device Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000001788 irregular Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000035772 mutation Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to the technical field of power grids, in particular to a power consumption monitoring method, a device, computer equipment and a storage medium, wherein power consumption monitoring data are obtained, and the power consumption monitoring data comprise business data and operation data; screening the service data according to a preset rule, and determining a first probability according to the screened service data; preprocessing the operation data, processing the preprocessed operation data by using a preset identification model, and outputting a second probability; and determining the power consumption unnormal probability according to the first probability and the second probability. According to the electricity consumption monitoring method provided by the embodiment of the invention, the electricity consumption monitoring data are divided, different processing modes are adopted for different data to determine the first probability and the second probability, the first probability and the second probability finally determine the non-standard electricity consumption probability, whether a user does not use electricity normally can be judged more accurately, and the degree of automation is high.
Description
Technical Field
The present invention relates to the field of power grid technologies, and in particular, to a power consumption monitoring method, a device, a computer device, and a storage medium.
Background
Electric energy is an indispensable energy source in the production and life of people, and the electric quantity required by the production and life of people is increased along with the continuous development of social economy of China.
In this case, whether careful or unintentional, the power consumption phenomena are not normalized. The irregular electricity consumption generally comprises under-voltage electricity consumption, undercurrent electricity consumption, phase-shifting electricity consumption, meter-free electricity consumption and the like. Some modes use electricity, and the actual electricity consumption is not matched with the electricity meter indication, so that the normal charging cannot be performed, and the normal order of the electricity market is destroyed.
The prior art can only realize the non-standard electricity consumption through the modes of on-site inspection, improvement of the monitoring capability of the intelligent ammeter, wireless communication monitoring and the like, however, the modes are easy to cause misjudgment and missed judgment, and the method has the defects of large workload and high monitoring cost and needs improvement.
Disclosure of Invention
Based on this, it is necessary to provide an electricity usage monitoring method, apparatus, computer device, and storage medium in order to address the above-described problems.
The embodiment of the invention is realized in such a way that the electricity consumption monitoring method comprises the following steps:
acquiring electricity consumption monitoring data, wherein the electricity consumption monitoring data comprises service data and operation data;
screening the service data according to a preset rule, and determining a first probability according to the screened service data;
preprocessing the operation data, processing the preprocessed operation data by using a preset identification model, and outputting a second probability;
and determining the power consumption unnormal probability according to the first probability and the second probability.
In one embodiment, the embodiment of the invention further provides an electricity consumption monitoring device, which comprises:
the power consumption monitoring system comprises an acquisition module, a power consumption monitoring module and a power consumption monitoring module, wherein the acquisition module is used for acquiring power consumption monitoring data, and the power consumption monitoring data comprises service data and operation data;
the first probability determining module is used for screening the service data according to a preset rule and determining a first probability according to the screened service data;
the second probability determining module is used for preprocessing the operation data, processing the preprocessed operation data by using a preset recognition model and outputting a second probability;
and the unnormal electricity utilization probability determining module is used for determining unnormal electricity utilization probability according to the first probability and the second probability.
In one embodiment, the present invention further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the computer program when executed by the processor causes the processor to execute the steps of the electricity usage monitoring method described above.
In one embodiment, the present invention further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, where the computer program when executed by a processor causes the processor to perform the steps of the electricity usage monitoring method described above.
According to the electricity consumption monitoring method provided by the embodiment of the invention, the electricity consumption monitoring data are divided, different processing modes are adopted for different data to determine the first probability and the second probability, the first probability and the second probability finally determine the non-standard electricity consumption probability, whether a user does not use electricity normally can be judged more accurately, and the degree of automation is high. The method can be adapted to the existing electricity utilization system, and is used for analyzing and processing on the basis of the existing electricity utilization monitoring data so as to determine whether a user does not use electricity normally, the modification of the existing system is small, the embedding performance is strong, the algorithm is easy to realize, and the cost is low.
Drawings
FIG. 1 is an application environment diagram of a power usage monitoring method provided in one embodiment;
FIG. 2 is a flow chart of a power usage monitoring method in one embodiment;
FIG. 3 is a flowchart showing the steps of determining a first probability according to the service data after screening in FIG. 2;
FIG. 4 is a flowchart showing the steps of preprocessing the operation data in FIG. 2;
FIG. 5 is a flowchart showing the steps of processing the operation data after preprocessing and outputting a second probability by using the preset recognition model in FIG. 2;
FIG. 6 is a detailed flow chart of the steps of FIG. 2 for determining a probability of power utilization for an irregular use based on the first probability and the second probability;
FIG. 7 is a block diagram of an electrical monitoring device in one embodiment;
FIG. 8 is a block diagram of the internal architecture of a computer device in one embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.
Fig. 1 is a diagram of an application environment of an electricity consumption monitoring method provided in one embodiment, as shown in fig. 1, in the application environment, including a power supply grid 110 and a power supply monitoring system 120.
In the embodiment of the present invention, the power supply grid 110 may be a small-sized grid covering a certain city or region, or may be a large-sized or medium-sized grid covering a plurality of cities or regions, which is not particularly limited in terms of the scale of the power supply grid and whether the power supply grid operates independently or is operated in a grid-connected manner. In the embodiment of the present invention, it should be understood that the power supply grid 110 needs to be able to provide the power consumption monitoring data required by the power consumption monitoring method provided by the present invention, and a specific manner of providing the data may be online collection by the power supply monitoring system 120, recording by using intelligence, and collecting by manual collection or wireless uploading, or a combination of the two manners, which is not limited in the embodiment of the present invention.
In the embodiment of the present invention, the power supply monitoring system 120 is mainly responsible for operation control and online monitoring of the power supply grid, and the power consumption monitoring method provided in the embodiment of the present invention operates in the system, and may be used as a module in the system to perform online monitoring on the power consumption behavior of the user, and of course, may also operate in an independent system to perform offline analysis processing on the provided data, which is an optional specific implementation manner, and the embodiment of the present invention is not limited in this way specifically.
The electricity consumption monitoring method provided by the embodiment of the invention can be adapted to the existing electricity consumption system, and is used for analyzing and processing on the basis of the existing electricity consumption monitoring data so as to determine whether a user does not use electricity normally, so that the existing system is small in transformation, strong in embedding property, easy to realize an algorithm and low in cost.
As shown in fig. 2, in one embodiment, an electricity consumption monitoring method is provided, and this embodiment is mainly exemplified by the method applied to the electricity supply monitoring system 120 in fig. 1. Specifically, the method comprises the steps S202 to S208:
step S202, electricity consumption monitoring data are acquired, wherein the electricity consumption monitoring data comprise business data and operation data.
In an embodiment of the invention, the electrical monitoring data includes, but is not limited to, index data, meter data, event data, archive data and historical electricity consumption data in an electricity acquisition system and a marketing business system. For meter acquisition data, in order to ensure the integrity of the data, all data recorded from the installation to the operation of the electric energy meter can be extracted, and specifically, the meter can comprise a meter reading day freezing electric energy indication value, a day measuring point power factor, a day measuring point voltage, a day measuring point current and the like; the events in the event data can comprise an electric energy meter voltage loss event, an electric energy meter current loss event, an electric energy meter cover opening event, an electric energy meter overvoltage event, an electric energy meter current overflow event and the like; the archive data is mainly an electric energy meter archive, an electric energy meter user archive, a metering point archive and the like. In addition, several non-canonical electricity case data may be included, which is an alternative embodiment, and embodiments of the invention are not specifically limited in this regard.
And S204, screening the service data according to a preset rule, and determining a first probability according to the screened service data.
In the embodiment of the invention, the screening is mainly performed through two dimensions of the platform area and the user, and the preset rule can be specifically any one or more of the following forms:
(1) The line loss rate of the line where the user is positioned is more than 10 percent or the line loss rate is close to a circle fluctuation coefficient of more than 3 or the daily average value of three-phase unbalance is more than 15 percent;
(2) The user change relation of the line where the user is located is correct;
(3) The acquisition coverage rate of the line where the user is located is 100%;
(4) The acquisition success rate of the line where the user is located is 100%.
The electricity usage monitoring data of the user satisfying one or more of the above-indicated conditions may be used as business data for determining the first probability. The screening is mainly used for eliminating users with low power consumption possibility to save computing resources.
Step S206, preprocessing the operation data, processing the preprocessed operation data by using a preset recognition model, and outputting a second probability.
In the embodiment of the invention, the data processed by the identification module is required to be preprocessed, the preprocessed data can be adapted to the requirements of the model, and partial users with low power consumption unnormal can be removed. It should be understood that in the embodiment of the present invention, there may be a certain repetition of the data for model identification and the service data described in the previous step, that is, for some electricity usage monitoring data, it is used as both the service data and the process data for identifying the model, but preferably, the service data and the data for model identification are not repeated, so that the repeated processing of the data may be reduced to provide the operation speed and efficiency.
And step S208, determining the power consumption unnormal probability according to the first probability and the second probability.
In the embodiment of the invention, the electricity consumption monitoring data are divided and processed by adopting different methods to obtain the first probability and the second probability, and the probability of irregular electricity consumption is finally determined according to the first probability and the second probability, so that the analysis processing of the electricity consumption monitoring data of the user from the multi-dimensional multi-rule is realized, the judgment accuracy can be effectively improved, and the occurrence of misjudgment and missed judgment is reduced.
According to the electricity consumption monitoring method provided by the embodiment of the invention, the electricity consumption monitoring data are divided, different processing modes are adopted for different data to determine the first probability and the second probability, the first probability and the second probability finally determine the non-standard electricity consumption probability, whether a user does not use electricity normally can be judged more accurately, and the degree of automation is high. The method can be adapted to the existing electricity utilization system, and is used for analyzing and processing on the basis of the existing electricity utilization monitoring data so as to determine whether a user does not use electricity normally, the modification of the existing system is small, the embedding performance is strong, the algorithm is easy to realize, and the cost is low.
In one embodiment, as shown in fig. 3, the step of determining the first probability according to the service data after screening in step S204 may specifically include steps S302 to S306:
step S302, determining an evaluation index.
In the embodiment of the invention, the evaluation index is preferably historical electric quantity mutation, electric quantity and line loss rate correlation, uncovering and electric quantity mutation, undervoltage and electric quantity mutation, lost flow and electric quantity mutation, electric quantity and line loss rate fluctuation, same-industry same-capacity same-season deviation, meter acquisition power and calculation power deviation.
Step S304, determining the weight of each evaluation index by using a analytic hierarchy process.
In the embodiment of the invention, the analytic hierarchy process refers to a system method which takes a complex multi-objective decision problem as a system, decomposes an objective into a plurality of objectives or criteria, further decomposes the objective into a plurality of layers of multi-indexes (or criteria and constraints), calculates single-order (weights) and total order of the layers by a qualitative index fuzzy quantization method, and takes the single-order (weights) and total order as objective (multi-index) multi-scheme optimization decision, and is called as the analytic hierarchy process. The analytic hierarchy process is to decompose the decision problem into different hierarchical structures according to the sequence of the total target, the sub-targets of each layer and the evaluation criteria until a specific spare power switching scheme, then to calculate the priority weight of each element of each layer to a certain element of the previous layer by solving the matrix feature vector, and finally to merge the final weight of each alternative scheme to the total target in a hierarchical manner by a weighted sum method, wherein the final weight with the largest weight is the optimal scheme. The term "priority" is used herein to refer to a relative measure of how well each alternative is under a particular evaluation criteria or sub-objective, and how important each sub-objective is to the upper level of objective. The analytic hierarchy process is more suitable for a target system with hierarchical staggered evaluation indexes, and the target value is difficult to quantitatively describe. The use method is to construct a judgment matrix, calculate the maximum characteristic value and the corresponding characteristic vector W, normalize the maximum characteristic value and the corresponding characteristic vector W, and then obtain the relative importance weight of a certain level index to a certain related index of the previous level. The analytic hierarchy process is characterized in that on the basis of deep analysis of the nature, influence factors, internal relations and the like of complex decision problems, the thinking process of decision is mathematically realized by using less quantitative information, so that a simple decision method is provided for complex decision problems with multiple targets, multiple criteria or no structural characteristics, and the analytic hierarchy process is particularly suitable for occasions where decision results are difficult to directly and accurately measure.
In the embodiment of the invention, the construction steps of the analytic hierarchy process mainly comprise:
(1) Establishing a hierarchical model;
(2) Constructing a pair comparison matrix;
(3) Calculating the weight vector of the hierarchical single sequence and the maximum eigenvector of the consistency check pairing comparison matrix A;
(4) And calculating the total ranking weight of the hierarchy and checking consistency.
Among the difficulties of the analytic hierarchy process are:
(1) The establishment of the comparison matrix is realized by 1-9 level scale according to the numerical ratio of each index to each other, and the establishment of the judgment matrix is reasonable as follows:
B1:B1＝1:1；B1:B2＝1:5；B1:B3＝1:3
B2:B1＝5:1；B2:B2＝1:1；B2:B3＝3:1
B3:B1＝3:1；B3:B2＝1:3；B3:B3＝1:1
to facilitate mathematical processing, we typically write the results in a matrix form, referred to as a pair-wise comparison matrix.
(2) Whether the weight is reasonable or not is based on whether the consistency test of each layer is qualified or not, and CR is generally considered to be less than 0.1.
In the embodiment of the present invention, the algorithm specifically adopted for each index is shown in table 1:
table 1: specific algorithm corresponding to each indication and weight thereof
Step S306, determining the first probability according to the screened service data, the evaluation index and the corresponding weight.
In the embodiment of the present invention, the first probability is equal to the sum of the products of the above indexes and the corresponding weights, namely: first probability = comparison of corresponding weight + correlation of electric quantity and line loss rate + corresponding weight + disconnection and electric quantity mutation + corresponding weight + electric quantity and line loss rate fluctuation + corresponding weight + same-industry same-capacity same-season deviation + corresponding weight + meter acquisition power and calculation power deviation.
In one embodiment, as shown in fig. 4, the step of preprocessing the operation data in step S206 may specifically include steps S402 to S406:
step S402, cleaning the operation data to remove abnormal values.
In the embodiment of the invention, abnormal values in the data, such as data of flying and rewinding of the ammeter indication in the electric quantity data, data of abnormal file cases in the archive data, data of abnormal mark in event data and the like, are removed; deleting repeated data in the data, such as data repeatedly reported by the same event in the event data, user data which is not collected in more than 7 days in the recent period, and the like; and supplementing missing data, such as electric energy indication data, without collecting data.
Step S404, normalizing the operation data after cleaning.
In the embodiment of the invention, normalization is adopted for data normalization processing of numerical data in the data, such as power consumption data, user voltage and current data.
Step S406, converting the normalized operation data.
In the embodiment of the invention, normalization is adopted for data normalization processing of numerical data in the data, such as power consumption data, user voltage and current data.
In the embodiment of the invention, the data can be subjected to characteristic processing by combining data distribution and business flow. If the standard deviation of the user electric quantity data is calculated, the user electric wave mobility is measured; the power consumption abnormal coefficient is used for measuring fluctuation degree of the power consumption of the user near the mean value; the number of times the user has an abnormal event, etc. This is an alternative embodiment, and the embodiment of the present invention is not limited thereto.
In one embodiment, as shown in fig. 5, the step of processing the preprocessed operation data and outputting the second probability in step S206 by using a preset recognition model may specifically include steps S502 to S508:
step S502, the operation data are processed by using a random forest algorithm model to output a first result.
In the embodiment of the invention, a CART (classification and regression tree, classification and RegressionTrees, CART) decision tree is used as a weak learner by the random forest, and the establishment of the decision tree is improved. For a common decision tree, an algorithm selects an optimal feature from all sample features on nodes to make a division basis of a decision tree subtree, but a random forest makes a left subtree and a right subtree division of the decision tree by randomly selecting a part of sample features on the nodes and then selecting an optimal feature from the randomly selected part of sample features. The generalization ability of the model is further improved due to uncertainty in feature selection.
In the embodiment of the invention, the algorithm calculation flow is as follows:
the model input is a sample set D = { (x) 1 ，y 1 )，(x 2 ，y 2 )，...(x m ，y m ) Weak classifier iteration number T. The model output is the final strong classifier f (x).
(1) Weak classifier iteration (t=1, 2.., T):
1) Randomly sampling the training set for the t th time, and collecting m times to obtain a sampling set D containing m samples t ；
2) Using sample set D t When training the t decision tree model G (x) and training the nodes of the decision tree model, firstly selecting a part of sample characteristics from all sample characteristics on the nodes, and then selecting an optimal characteristic from the randomly selected part of sample characteristics to make left and right subtree division of the decision tree;
(2) For classification algorithm prediction, the class with the most votes cast by the T weak learners is taken as the final class. And for the regression algorithm, taking the value obtained by carrying out arithmetic average on the regression results obtained by the T weak learners as a final model output.
And step S504, processing the operation data by using the XGBoost algorithm model to output a second result.
In the embodiment of the invention, the XGBoost algorithm is an algorithm with high calculation efficiency and robustness. XGBoost can support many other weak learners in addition to decision trees in the weak learner model selection of the algorithm. On the loss function of the algorithm, a regularization part is added besides the loss of the algorithm. In the optimization mode of the algorithm, the XGBoost loss function performs second-order Taylor expansion on the error part, so that the method is more accurate. Parallel selection is performed on the process established by each weak learner, and before parallel selection, the values of all the features are sorted and grouped. For the characteristics of the packet, a proper packet size is selected, and the CPU cache is used for reading acceleration. Each packet is saved to multiple hard disks to increase IO speed. For the characteristics of the missing values, the processing mode of the missing values is determined by enumerating whether all the missing values enter a left subtree or a right subtree at the current node. The algorithm itself adds L1 and L2 regularization terms, so that overfitting can be prevented, and generalization capability is stronger.
Step S506, processing the operation data by using the LightGBM algorithm model to output a third result.
In the embodiment of the invention, the LightGBM algorithm is a classical Boosting series algorithm. Compared with the XGBoost algorithm, the calculation logic of the XGBoost algorithm and the XGBoost algorithm are similar, and the main difference is that the LightGBM is better in optimizing communication processing. The LightGBM directly supports the category characteristics, and independent heat coding treatment is not needed to be carried out on the category characteristics, so that the algorithm efficiency is improved. The LightGBM simultaneously supports data parallelism and feature parallelism. The early stop strategies of the two are different when multiple evaluation indexes are used for simultaneous evaluation, XGBoost is used as a stop standard according to the last item in the evaluation index list, and the LightGBM is influenced by all the evaluation indexes.
Step S508, determining the second probability according to the first result, the second result, the third result and the respective corresponding preset weights.
In the embodiment of the invention, the constructed identification model selects historical data of the power consumption sample in the whole year as data input, wherein 2994 suspected samples are taken as the total, and sample data are obtained according to the following steps: and 3, dividing the data training set and the test set. Considering the problem of unbalance of positive and negative samples, the classifier threshold in the algorithm is changed to the actual ratio of negative samples to positive samples in the data. The accuracy of the training set in the model is improved through continuous training and parameter adjustment optimization of the algorithm model.
The machine learning electricity identification model is a two-class prediction task, and the model accuracy is evaluated mainly through the accuracy rate and the recall rate. In the power consumption prediction scenario, a high accuracy is required. The calculation formulas of the accuracy rate and the recall rate are as follows:
accuracy rate: p=tp/(tp+fp)
Recall rate: r=tp/(tp+fn)
Through model training and parameter tuning, the data of random forests and XGBoost, lightGBM on the test set are expressed as follows:
(1) Random forest model
(2) XGBoost model
(3) LightGBM model
The model accuracy versus recall ratio is shown below:
| model name | Accuracy rate of | Recall rate of recall |
| Random forest | 81.62 | 69.87％ |
| XGBoost | 84.94 | 72.01％ |
| LightGBM | 82.97 | 71.14％ |
In the embodiment of the present invention, the second probability=random forest model output×weight 1+xgboost model output×weight 2+lightgbm model output×weight 3.
In one embodiment, as shown in fig. 6, the step of determining the power consumption unnormalized probability according to the first probability and the second probability in step S208 may specifically include steps S602 to S604:
step S602, determining weights corresponding to the first probability and the second probability.
In the embodiment of the present invention, the weights corresponding to the first probability and the second probability may be empirical values, or may be determined by other algorithms, which is an optional specific implementation manner, and in the embodiment of the present invention, the weights corresponding to the two probabilities are all 0.5.
Step S604, determining the non-standard electricity probability according to the first probability, the second probability and the weights corresponding to the first probability and the second probability.
In the embodiment of the present invention, the power consumption probability=first probability 0.5+second probability 0.5 is not specified. The irregular electricity consumption probability can be further classified into extremely high (90% -100%), high (70% -90% including 90%), generally (50% -70% including 70%), low (0-50% including 50%) according to the magnitude of the irregular electricity consumption probability. As an alternative processing mode, risk early warning can be carried out on users with extremely high unnormalized electricity probability types and users with unnormalized electricity probability of more than 60% in 4 consecutive days every day.
According to the electricity consumption monitoring method provided by the embodiment of the invention, the electricity consumption monitoring data are divided, different processing modes are adopted for different data to determine the first probability and the second probability, the first probability and the second probability finally determine the non-standard electricity consumption probability, whether a user does not use electricity normally can be judged more accurately, and the degree of automation is high. The method can be adapted to the existing electricity utilization system, and is used for analyzing and processing on the basis of the existing electricity utilization monitoring data so as to determine whether a user does not use electricity normally, the modification of the existing system is small, the embedding performance is strong, the algorithm is easy to realize, and the cost is low.
As shown in fig. 7, in one embodiment, an electricity consumption monitoring device is provided, and the electricity consumption monitoring device may be integrated into the power supply monitoring system 120, and may specifically include:
the acquiring module 701 is configured to acquire electricity consumption monitoring data, where the electricity consumption monitoring data includes service data and operation data;
the first probability determining module 702 is configured to screen the service data according to a preset rule, and determine a first probability according to the screened service data;
a second probability determining module 703, configured to preprocess the operation data, process the preprocessed operation data with a preset recognition model, and output a second probability;
the unnormalized electricity probability determining module 704 is configured to determine an unnormalized electricity probability according to the first probability and the second probability.
In the embodiment of the present invention, the explanation of the specific steps of the execution of each module refers to the content of any one or more combinations of the foregoing embodiments of the present invention, and the embodiments of the present invention are not repeated herein.
According to the electricity consumption monitoring device provided by the embodiment of the invention, the electricity consumption monitoring data are divided, different processing modes are adopted for different data so as to determine the first probability and the second probability, and the first probability and the second probability finally determine the non-standard electricity consumption probability, so that whether a user does not use electricity in a standard manner can be judged more accurately, and the degree of automation is high. The method can be adapted to the existing electricity utilization system, and is used for analyzing and processing on the basis of the existing electricity utilization monitoring data so as to determine whether a user does not use electricity normally, the modification of the existing system is small, the embedding performance is strong, the algorithm is easy to realize, and the cost is low.
FIG. 8 illustrates an internal block diagram of a computer device in one embodiment. The computer device may be specifically the power supply monitoring system 120 of fig. 1. As shown in fig. 8, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, where the computer program when executed by the processor may cause the processor to implement the electricity consumption monitoring method provided by the embodiment of the present invention. The internal memory may also store a computer program, which when executed by the processor, causes the processor to execute the electricity consumption monitoring method provided by the embodiment of the invention. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the electricity usage monitoring apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 8. The memory of the computer device may store various program modules constituting the electricity usage monitoring apparatus, such as an acquisition module 701, a first probability determination module 702, a second probability determination module 703, and an unnormalized electricity usage probability determination module 704 shown in fig. 7. The computer program of each program module causes the processor to execute the steps in the electricity usage monitoring method of each embodiment of the present application described in the present specification.
For example, the computer apparatus shown in fig. 8 may perform step S202 through the acquisition module 701 in the electricity usage monitoring device shown in fig. 7; the computer device may perform step S204 through the first probability determination module 702; the computer device may perform step S206 by the second probability determination module 703; the computer device may perform step S208 by the unnormal electricity probability determination module 704.
In one embodiment, a computer device is presented, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring electricity consumption monitoring data, wherein the electricity consumption monitoring data comprises service data and operation data;
screening the service data according to a preset rule, and determining a first probability according to the screened service data;
preprocessing the operation data, processing the preprocessed operation data by using a preset identification model, and outputting a second probability;
and determining the power consumption unnormal probability according to the first probability and the second probability.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of: .
Acquiring electricity consumption monitoring data, wherein the electricity consumption monitoring data comprises service data and operation data;
screening the service data according to a preset rule, and determining a first probability according to the screened service data;
preprocessing the operation data, processing the preprocessed operation data by using a preset identification model, and outputting a second probability;
and determining the power consumption unnormal probability according to the first probability and the second probability.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. An electricity consumption monitoring method, characterized in that the electricity consumption monitoring method comprises:
acquiring electricity consumption monitoring data, wherein the electricity consumption monitoring data comprises service data and operation data;
screening the service data according to a preset rule, and determining a first probability according to the screened service data;
preprocessing the operation data, processing the preprocessed operation data by using a preset identification model, and outputting a second probability;
determining a power consumption unnormal probability according to the first probability and the second probability;
the determining the first probability according to the service data after screening comprises the following steps:
determining an evaluation index;
determining the weight of each evaluation index by using an analytic hierarchy process;
determining the first probability according to the screened service data, the evaluation index and the corresponding weight thereof;
the method for processing the preprocessed operation data by using the preset recognition model and outputting the second probability comprises the following steps:
processing the operation data by using a random forest algorithm model to output a first result;
processing the operation data by using an XGBoost algorithm model to output a second result;
processing the operation data by using a LightGBM algorithm model to output a third result;
and determining the second probability according to the first result, the second result, the third result and the corresponding preset weights.
2. The electricity usage monitoring method of claim 1, wherein the electricity usage monitoring data includes index data, meter data, event data, archive data, and historical electricity usage data in an electricity usage collection system, a marketing business system.
3. The electricity usage monitoring method of claim 1, wherein the preprocessing of the operational data includes the steps of:
cleaning the operation data to remove abnormal values;
normalizing the cleaned operation data;
and converting the standardized operation data.
4. The electricity usage monitoring method of claim 1, wherein the identification model includes a random forest algorithm model, an XGBoost algorithm model, and a LightGBM algorithm model.
5. The electricity usage monitoring method of claim 1, wherein the determining the electricity usage unnormalized probability from the first probability and the second probability comprises the steps of:
determining the weight corresponding to the first probability and the second probability;
and determining the non-standard electricity utilization probability according to the first probability, the second probability and the weights corresponding to the first probability and the second probability.
6. An electricity usage monitoring device, characterized in that the electricity usage monitoring device comprises:
the power consumption monitoring system comprises an acquisition module, a power consumption monitoring module and a power consumption monitoring module, wherein the acquisition module is used for acquiring power consumption monitoring data, and the power consumption monitoring data comprises service data and operation data;
the first probability determining module is used for screening the service data according to a preset rule and determining a first probability according to the screened service data;
the second probability determining module is used for preprocessing the operation data, processing the preprocessed operation data by using a preset recognition model and outputting a second probability;
the non-standard electricity utilization probability determining module is used for determining the non-standard electricity utilization probability according to the first probability and the second probability;
the determining the first probability according to the service data after screening comprises the following steps:
determining an evaluation index;
determining the weight of each evaluation index by using an analytic hierarchy process;
determining the first probability according to the screened service data, the evaluation index and the corresponding weight thereof;
the method for processing the preprocessed operation data by using the preset recognition model and outputting the second probability comprises the following steps:
processing the operation data by using a random forest algorithm model to output a first result;
processing the operation data by using an XGBoost algorithm model to output a second result;
processing the operation data by using a LightGBM algorithm model to output a third result;
and determining the second probability according to the first result, the second result, the third result and the corresponding preset weights.
7. A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the electricity usage monitoring method of any of claims 1 to 5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of the electricity usage monitoring method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011143546.4A CN112256735B (en) | 2020-10-23 | 2020-10-23 | Power consumption monitoring method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011143546.4A CN112256735B (en) | 2020-10-23 | 2020-10-23 | Power consumption monitoring method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112256735A CN112256735A (en) | 2021-01-22 |
| CN112256735B true CN112256735B (en) | 2024-04-09 |
Family
ID=74264974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011143546.4A Active CN112256735B (en) | 2020-10-23 | 2020-10-23 | Power consumption monitoring method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112256735B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116990744B (en) * | 2023-09-25 | 2023-12-05 | 北京志翔科技股份有限公司 | Electric energy meter detection method, device, equipment and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465546A (en) * | 2009-01-08 | 2009-06-24 | 上海交通大学 | Electric energy quality synthesis evaluation system |
| CN104112181A (en) * | 2014-06-12 | 2014-10-22 | 西北工业大学 | Analytical hierarchy process-based information security Bayesian network evaluation method |
| CN105160864A (en) * | 2015-09-21 | 2015-12-16 | 国网上海市电力公司 | Operating data monitoring system and method for intelligent ammeters |
| CN107633050A (en) * | 2017-09-18 | 2018-01-26 | 安徽蓝杰鑫信息科技有限公司 | A kind of method that stealing probability is judged based on big data analysis electricity consumption behavior |
| CN109325542A (en) * | 2018-10-09 | 2019-02-12 | 烟台海颐软件股份有限公司 | A kind of electricity exception intelligent identification Method and system based on multistage machine learning |
| CN109558975A (en) * | 2018-11-21 | 2019-04-02 | 清华大学 | A kind of integrated approach of a variety of prediction results of electric load probability density |
| CN109740872A (en) * | 2018-12-18 | 2019-05-10 | 国网山西省电力公司长治供电公司 | The diagnostic method and system of a kind of area's operating status |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| CN110888101A (en) * | 2019-12-05 | 2020-03-17 | 新奥数能科技有限公司 | Electric energy meter abnormity diagnosis method and device |
| CN111008193A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Data cleaning and quality evaluation method and system |
| CN111738477A (en) * | 2019-08-01 | 2020-10-02 | 北方工业大学 | Deep feature combination-based power grid new energy consumption capability prediction method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3422518B1 (en) * | 2017-06-28 | 2020-06-17 | Siemens Aktiengesellschaft | A method for recognizing contingencies in a power supply network |
-
2020
- 2020-10-23 CN CN202011143546.4A patent/CN112256735B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465546A (en) * | 2009-01-08 | 2009-06-24 | 上海交通大学 | Electric energy quality synthesis evaluation system |
| CN104112181A (en) * | 2014-06-12 | 2014-10-22 | 西北工业大学 | Analytical hierarchy process-based information security Bayesian network evaluation method |
| CN105160864A (en) * | 2015-09-21 | 2015-12-16 | 国网上海市电力公司 | Operating data monitoring system and method for intelligent ammeters |
| CN107633050A (en) * | 2017-09-18 | 2018-01-26 | 安徽蓝杰鑫信息科技有限公司 | A kind of method that stealing probability is judged based on big data analysis electricity consumption behavior |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| CN109325542A (en) * | 2018-10-09 | 2019-02-12 | 烟台海颐软件股份有限公司 | A kind of electricity exception intelligent identification Method and system based on multistage machine learning |
| CN109558975A (en) * | 2018-11-21 | 2019-04-02 | 清华大学 | A kind of integrated approach of a variety of prediction results of electric load probability density |
| CN109740872A (en) * | 2018-12-18 | 2019-05-10 | 国网山西省电力公司长治供电公司 | The diagnostic method and system of a kind of area's operating status |
| CN111738477A (en) * | 2019-08-01 | 2020-10-02 | 北方工业大学 | Deep feature combination-based power grid new energy consumption capability prediction method |
| CN111008193A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Data cleaning and quality evaluation method and system |
| CN110888101A (en) * | 2019-12-05 | 2020-03-17 | 新奥数能科技有限公司 | Electric energy meter abnormity diagnosis method and device |
Non-Patent Citations (2)
| Title |
|---|
| Power system on-line risk assessment and decision support based on weighting fault possibility model;Jing Li 等;《Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE)》;20120514;1058-1061 * |
| 电力用户负荷模式提取技术及应用综述;张铁峰 等;《电网技术》;20160305;第40卷(第3期);804-811 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112256735A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| Wen et al. | A generalized remaining useful life prediction method for complex systems based on composite health indicator | |
| Cody et al. | Decision tree learning for fraud detection in consumer energy consumption | |
| CN106650797B (en) | Power distribution network electricity stealing suspicion user intelligent identification method based on integrated ELM | |
| CN107506868B (en) | Method and device for predicting short-time power load | |
| Najafi et al. | Building characterization through smart meter data analytics: Determination of the most influential temporal and importance-in-prediction based features | |
| Liu et al. | Quantitative evaluation of the building energy performance based on short-term energy predictions | |
| Massaferro et al. | Improving electricity non technical losses detection including neighborhood information | |
| CN112256735B (en) | Power consumption monitoring method and device, computer equipment and storage medium | |
| Sharma et al. | Forecasting and prediction of air pollutants concentrates using machine learning techniques: the case of India | |
| CN116401601B (en) | Power failure sensitive user handling method based on logistic regression model | |
| Tangrand | Some new contributions to neural networks and wavelets with applications | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| Velasco et al. | Rainfall forecasting using support vector regression machines | |
| CN115035966B (en) | Superconductor screening method, device and equipment based on active learning and symbolic regression | |
| CN116205355A (en) | Power load prediction method, device and storage medium | |
| CN113537607B (en) | Power failure prediction method | |
| EP4027277A1 (en) | Method, system and computer program product for drift detection in a data stream | |
| CN114784795A (en) | Wind power prediction method and device, electronic equipment and storage medium | |
| Sridevi et al. | Predictive Maintenance of Lead-Acid Batteries Using Machine Learning Algorithms | |
| Mascali et al. | A machine learning-based Anomaly Detection Framework for building electricity consumption data | |
| Raymand et al. | Machine learning-based estimation of buildings' characteristics employing electrical and chilled water consumption data: Pipeline optimization | |
| Oloyede et al. | Descriptive and diagnostic analysis of NASA and NiMet big weather data | |
| CN112116139A (en) | Power demand prediction method and system | |
| Nong | Construction and Simulation of Financial Risk Prediction Model Based on LSTM |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |