CN113222245A - Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium - Google Patents
Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium Download PDFInfo
- Publication number
- CN113222245A CN113222245A CN202110508269.0A CN202110508269A CN113222245A CN 113222245 A CN113222245 A CN 113222245A CN 202110508269 A CN202110508269 A CN 202110508269A CN 113222245 A CN113222245 A CN 113222245A
- Authority
- CN
- China
- Prior art keywords
- month
- predicted
- monthly
- electricity
- resident
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 5
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000000126 substance 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a checking method and system for monthly electric quantity and electricity charge abnormity of a resident user and a storage medium, wherein the checking method comprises the following steps: acquiring the average human body comfort level of a month of a resident user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, monthly power consumption information of all months before the month to be predicted and resident user type information; inputting the average human comfort level of a month, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the power consumption information of all months before the month to be predicted and the resident type information of a resident user into a pre-trained XGboost model to predict the monthly power consumption of the month to be predicted to obtain a prediction result; and adjusting the electricity charge abnormity checking rule according to the prediction result. The method and the device realize the prediction of the monthly electricity consumption of the resident users, and adjust the electricity quantity and electricity charge check rule according to the prediction result, thereby being beneficial to the effective screening of the abnormal data of the electricity quantity.
Description
Technical Field
The invention relates to the technical field of abnormal checking of electric quantity and electric charge, in particular to a monthly electric quantity and electric charge abnormal checking method and system for a residential user and a storage medium.
Background
The current marketing system electricity quantity and electricity charge abnormity check rule is subjective planning mainly by experience, and lacks objective rule identification supported by operation data, so two predicaments often appear as follows:
1) the rule threshold is set to be too rigid, so that a plurality of false exceptions exist, and the efficiency is low.
In the existing enabling rules, the rule of "having adjustable variable" reaches 20, the adjustable variable can be divided into two categories of "reference electric quantity" and "fluctuation rate", the "reference electric quantity" and "fluctuation rate" can be manually adjusted in the system, and the rationality and applicability thereof will directly affect the abnormal data quantity generated by the system and the work efficiency of electric charge accounting. According to historical data statistics, abnormal data screened by the rule with the adjustable variable accounts for more than 80% of total quantity abnormality, so that if the threshold value of the adjustable variable can be reasonably and classified set, the abnormal rate of the electricity charge can be reduced, and the accounting efficiency can be effectively improved.
2) The existing rules have limited coverage for abnormal power utilization by users.
The existing rule is obtained based on experience, the threshold value is often set once, the electricity consumption of a user is changed along with the change of economic and environmental conditions, but the rule cannot be adjusted in time. The threshold setting of one cutting often fails to effectively identify the true abnormality from the group regularity of the abnormal events. The most important is that the rule-based abnormality identification range mainly depends on the range defined by the rule, the abnormal condition of the undiscovered rule cannot be identified through the rule, the rule coverage is limited, and the user electricity utilization abnormality cannot be comprehensively identified.
Disclosure of Invention
The invention aims to provide a method, a system, a device and a storage medium for checking monthly electric quantity and electricity charge abnormity of a resident user, so as to predict the monthly electric quantity and electricity charge of the resident user, adjust an electric quantity and electricity charge checking rule according to a prediction result and contribute to effective screening of electric quantity abnormal data.
In order to achieve the above object, a first aspect of the present invention provides a checking method for monthly electricity and electricity charges anomaly of a residential user, comprising the following steps:
acquiring the average human body comfort level of a month of a resident user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, monthly power consumption information of all months before the month to be predicted and resident user type information;
inputting the average human comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the power consumption information of all the months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly power consumption of the month to be predicted to obtain a prediction result;
and adjusting the electricity charge abnormity checking rule according to the prediction result.
Optionally, the information of the electricity consumption of all months before the month to be predicted comprises:
the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted.
Optionally, the human comfort degree calculation formula is as follows:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
and calculating the average human body comfort level of the resident users in the month according to the human body comfort levels of the resident users in all the months before the month to be predicted.
Optionally, the XGBoost model is trained as follows:
determining the latest complete month as the month to be predicted;
acquiring a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the method; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value.
Optionally, the error comprises one or more of a mean absolute error, a mean square error, a root mean square error, a mean absolute percentage error.
The second aspect of the present invention provides a checking system for monthly electricity and electricity charges abnormity of a residential user, comprising:
the information acquisition unit is used for acquiring the average human body comfort level of the month of the resident user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, monthly electricity consumption information of all months before the month to be predicted and the type information of the resident user;
the electricity consumption prediction unit is used for inputting the average human comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the electricity consumption information of all the months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly electricity consumption of the month to be predicted so as to obtain a prediction result; and
and the checking rule adjusting unit is used for adjusting the electricity charge abnormity checking rule according to the prediction result.
Optionally, the information of the electricity consumption of all months before the month to be predicted comprises:
the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted.
Optionally, the human comfort degree calculation formula is as follows:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
and calculating the average human body comfort level of the resident users in the month according to the human body comfort levels of the resident users in all the months before the month to be predicted.
Optionally, the XGBoost model is trained as follows:
determining the latest complete month as the month to be predicted;
acquiring a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the system; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value; the error comprises one or more of average absolute error, mean square error, root mean square error and average absolute percentage error.
A third aspect of the present invention proposes a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the monthly electricity quantity and electricity charge abnormality checking method for the residential user according to the first aspect.
The checking method, the system and the storage medium for monthly electricity and electricity charge abnormity of the residential user at least have the following beneficial effects: the method comprises the steps of predicting future monthly power consumption of a resident user based on a pre-trained XGboost model, adjusting a power consumption and power charge check rule according to a prediction result, gradually reducing power charge error rate according to effective screening of abnormal power fluctuation, accurately positioning abnormal data, reducing workload of customer service staff, reducing labor cost and improving work efficiency.
Other features and advantages of the above-described method and system for checking monthly electricity and electricity charges abnormality of the residential subscriber, and the storage medium will be described in the following specification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a checking method for abnormal monthly electricity consumption of a residential user according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an abnormal checking system for monthly electricity consumption of residential users according to an embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In addition, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for checking abnormal monthly electricity and electricity charges of a residential user, where the method includes the following steps:
step S1, acquiring average human body comfort level of a month of a resident user, holiday days of the month to be predicted, working day days of the month to be predicted, holiday days of the month to be predicted, monthly electricity consumption information of all months before the month to be predicted is ended, and resident user type information;
specifically, the information on the amount of electricity used for all months before the month to be predicted by the expiration includes: the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted;
specifically, the human comfort degree calculation formula is as follows:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
it can be understood that the average human body comfort level of the resident users in the month is calculated according to the human body comfort levels of the resident users in all the months before the month to be predicted;
the resident user type information specifically represents the types of monthly electric quantity fluctuation conditions of the resident users, wherein some users have large fluctuation and some users have small fluctuation, and the user types are divided according to the historical fluctuation conditions of the users. The monthly electricity consumption difference of the residential users can be determined according to the monthly electricity consumption information of all months before the month to be predicted, for example, the monthly electricity consumption fluctuation difference of the residential users is determined according to the difference value between the monthly maximum electricity consumption and the monthly minimum electricity consumption of all months before the month to be predicted, for example, the residential users are of three types, namely, the users with large fluctuation, the users with general fluctuation and the users with small fluctuation, and the monthly electricity consumption fluctuation difference is only exemplified and does not form the limitation of the invention;
step S2, inputting the average human body comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the power consumption information of all the months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly power consumption of the month to be predicted to obtain a prediction result;
specifically, XGboost, as a newly proposed Boosting-based ensemble learning algorithm, achieves good results in many fields; in the embodiment, influences of weather factors such as wind speed, humidity and temperature on electricity consumption are considered, a human body comfort index is combined, a short-term electricity quantity prediction model based on XGboost is established by combining historical electricity quantity, the XGboost model has the characteristics of high parallel operation speed, high precision, strong flexibility and good robustness, the prediction result of the XGboost model can be well fitted with actual electricity quantity data, and the average percentage error is below 2%; compared with linear regression, arima time sequence and random forest methods, the XGboost electric quantity prediction model has the advantages of short training time and the like, has better generalization performance, is not easy to over-fit, has excellent accuracy, and improves the prediction accuracy of monthly electric quantity of residential users to the maximum extent;
step S3, adjusting an electricity charge abnormity checking rule according to the prediction result;
specifically, according to the prediction result, the monthly electricity consumption change condition of future residential users can be estimated in advance, the electricity charge abnormity checking rule is updated and adjusted accordingly, and the corresponding reasonable threshold value is set.
For example, the XGBoost model is trained as follows:
step1, determining the latest complete month as the month to be predicted;
step2, obtaining a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
step3, inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the method; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value.
Illustratively, the error includes one or more of a mean absolute error MAE, a mean square error MSE, a root mean square error RMSE, a mean absolute percentage error MAPE;
specifically, the average absolute error MAE is calculated as follows:
wherein the content of the first and second substances,
is the predicted value of the ith sample, yiThe real value of the ith sample is n, and the number of the samples of the residential users is n;
the range of MAE is [0, + ∞), when the predicted value is completely consistent with the true value, the predicted value is equal to 0, namely a perfect model; the larger the error, the larger the value.
Specifically, the mean square error MSE calculation formula is as follows:
the MSE is in the range of [0, + ∞), and is equal to 0 when the predicted value is completely consistent with the true value, namely a perfect model; the larger the error, the larger the value.
Specifically, the root mean square error RMSE calculation formula is as follows:
that is, the MSE is added with a root sign, so that the order of magnitude is more intuitive, for example, when the RMSE is 10, the regression effect can be considered to be 10 different from the true value on average.
RMSE ranges from [0, + ∞) and equals 0 when the predicted value matches the true value completely, i.e. a perfect model; the larger the error, the larger the value.
Specifically, the calculation formula of the mean absolute percentage error MAPE is as follows:
MAPE ranges from [0, + ∞), with 0% MAPE indicating a perfect model and MAPE greater than 100% indicating a poor model.
According to the description of the embodiment, the method predicts the future monthly power consumption of the residential user based on the pre-trained XGboost model, adjusts the power consumption and power consumption check rule according to the prediction result, gradually reduces the power consumption error rate according to the effective screening of the abnormal power fluctuation, accurately positions abnormal data, reduces the workload of customer service staff, reduces the labor cost and improves the working efficiency.
Referring to fig. 2, another embodiment of the present invention provides a checking system for monthly electricity and electricity charges anomaly of a residential user, including:
the information acquisition unit 1 is used for acquiring average human body comfort level of a month of a resident user, holiday days of the month to be predicted, working day days of the month to be predicted, holiday days of the month to be predicted, monthly electricity consumption information of all months before the month to be predicted is ended, and resident user type information;
the power consumption prediction unit 2 is used for inputting the average human comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the power consumption information of all months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly power consumption of the month to be predicted so as to obtain a prediction result; and
and the checking rule adjusting unit 3 is used for adjusting the electricity charge abnormity checking rule according to the prediction result.
Illustratively, the electricity usage information of all months before the month to be predicted by the expiration includes:
the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted.
Illustratively, the human comfort calculation formula is as follows:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
and calculating the average human body comfort level of the resident users in the month according to the human body comfort levels of the resident users in all the months before the month to be predicted.
Illustratively, the XGBoost model is trained as follows:
determining the latest complete month as the month to be predicted;
acquiring a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the system; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value; the error comprises one or more of average absolute error, mean square error, root mean square error and average absolute percentage error.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
It should be noted that the system described in the foregoing embodiment corresponds to the method described in the foregoing embodiment, and therefore, a part of the system described in the foregoing embodiment that is not described in detail can be obtained by referring to the content of the method described in the foregoing embodiment, that is, the specific step content described in the method of the foregoing embodiment can be understood as the function that can be realized by the system of the present embodiment, and is not described herein again.
Moreover, the checking system for monthly electricity and electricity charges abnormity of the residential users in the above embodiments may be stored in a computer readable storage medium if the checking system is implemented in the form of a software functional unit and sold or used as an independent product.
Another embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the monthly electricity quantity and electricity charge abnormity checking method for the residential users according to the above embodiments.
Specifically, the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A checking method for monthly electric quantity and electricity charge abnormity of a resident user is characterized by comprising the following steps:
acquiring the average human body comfort level of a month of a resident user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, monthly power consumption information of all months before the month to be predicted and resident user type information;
inputting the average human comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the power consumption information of all the months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly power consumption of the month to be predicted to obtain a prediction result;
and adjusting the electricity charge abnormity checking rule according to the prediction result.
2. The method for checking abnormality in monthly electricity and electricity charges of residential users according to claim 1, wherein said information on electricity usage amounts of all months before the month to be predicted by expiration includes:
the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted.
3. The method for checking abnormal monthly electricity and electricity charges of residential users according to claim 1, wherein the human body comfort degree calculation formula is as follows:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
and calculating the average human body comfort level of the resident users in the month according to the human body comfort levels of the resident users in all the months before the month to be predicted.
4. The method for checking abnormal monthly electricity quantity and electricity charge of the residential users as claimed in claim 1, wherein the XGboost model is trained as follows:
determining the latest complete month as the month to be predicted;
acquiring a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the method; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value.
5. The method for checking abnormal monthly electricity and power charges of residential users according to claim 4, wherein said error comprises one or more of mean absolute error, mean square error, root mean square error, and mean absolute percentage error.
6. The utility model provides a resident user monthly electric quantity charges of electricity abnormal check system which characterized in that includes:
the information acquisition unit is used for acquiring the average human body comfort level of the month of the resident user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, monthly electricity consumption information of all months before the month to be predicted and the type information of the resident user;
the electricity consumption prediction unit is used for inputting the average human comfort level of the month of the residential user, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the electricity consumption information of all the months before the month to be predicted and the residential type information into a pre-trained XGboost model to predict the monthly electricity consumption of the month to be predicted so as to obtain a prediction result; and
and the checking rule adjusting unit is used for adjusting the electricity charge abnormity checking rule according to the prediction result.
7. The system for checking monthly electricity and electricity charges abnormality of residential users according to claim 6, wherein said electricity usage information of all months before the month to be predicted by expiration includes:
the monthly maximum power, the monthly minimum power, the monthly average power, the monthly median power, the monthly power variance, the monthly power before 13 months of the month to be predicted, the monthly power before 12 months of the month to be predicted, and the monthly power before 11 months of the month to be predicted.
8. The system for checking abnormal monthly electricity and electricity charges of residential users according to claim 6, wherein said human comfort degree calculation formula is:
ssd＝(1.818t+18.18)(0.88+0.002f)+(t-32)/(45-t)-3.2v+18.2
wherein ssd is a human body comfort index in a certain month, t is a month average air temperature, f is a month average relative humidity, and v is a month average wind speed;
and calculating the average human body comfort level of the resident users in the month according to the human body comfort levels of the resident users in all the months before the month to be predicted.
9. The system for checking abnormal monthly electricity and electricity charges of residential users as claimed in claim 1, wherein said XGBoost model is trained as follows:
determining the latest complete month as the month to be predicted;
acquiring a plurality of resident user sample data, wherein each resident user sample data comprises: the average human comfort level of the month of the resident users, the holiday days of the month to be predicted, the working day days of the month to be predicted, the holiday days of the month to be predicted, the monthly electricity consumption information of all the months before the month to be predicted and the type information of the resident users;
inputting the sample data of the plurality of residential users into an original XGboost model for training to obtain the XGboost model of the system; in the training process, the loss function of the XGboost model is that the error between the monthly power consumption information of the plurality of residential users in the latest complete month and the monthly power consumption information of the plurality of residential users output by the XGboost model in the training process is smaller than a preset value; the error comprises one or more of average absolute error, mean square error, root mean square error and average absolute percentage error.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps of the monthly electricity quantity and electricity charge abnormality checking method for the residential user according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110508269.0A CN113222245A (en) | 2021-05-11 | 2021-05-11 | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110508269.0A CN113222245A (en) | 2021-05-11 | 2021-05-11 | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113222245A true CN113222245A (en) | 2021-08-06 |
Family
ID=77094518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110508269.0A Pending CN113222245A (en) | 2021-05-11 | 2021-05-11 | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222245A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627682A (en) * | 2021-08-25 | 2021-11-09 | 深圳供电局有限公司 | Method and system for predicting daily electric quantity fluctuation of non-residential users |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
| CN109299156A (en) * | 2018-08-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Electronic device, the electric power data predicting abnormality method based on XGBoost and storage medium |
| CN109858674A (en) * | 2018-12-27 | 2019-06-07 | 国网浙江省电力有限公司 | Monthly load forecasting method based on XGBoost algorithm |
| CN110991555A (en) * | 2019-12-16 | 2020-04-10 | 国网上海市电力公司 | Method for monitoring abnormal electricity consumption of user in typical industry |
| CN111160401A (en) * | 2019-12-09 | 2020-05-15 | 国网辽宁省电力有限公司电力科学研究院 | Abnormal electricity utilization judging method based on mean shift and XGboost |
| CN111178957A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for early warning sudden increase of electric quantity of electricity consumption customer |
| CN112686449A (en) * | 2020-12-31 | 2021-04-20 | 国网河南省电力公司经济技术研究院 | Residential electricity consumption prediction method based on human body weather comfort index |
-
2021
- 2021-05-11 CN CN202110508269.0A patent/CN113222245A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
| CN109299156A (en) * | 2018-08-21 | 2019-02-01 | 平安科技（深圳）有限公司 | Electronic device, the electric power data predicting abnormality method based on XGBoost and storage medium |
| CN109858674A (en) * | 2018-12-27 | 2019-06-07 | 国网浙江省电力有限公司 | Monthly load forecasting method based on XGBoost algorithm |
| CN111160401A (en) * | 2019-12-09 | 2020-05-15 | 国网辽宁省电力有限公司电力科学研究院 | Abnormal electricity utilization judging method based on mean shift and XGboost |
| CN110991555A (en) * | 2019-12-16 | 2020-04-10 | 国网上海市电力公司 | Method for monitoring abnormal electricity consumption of user in typical industry |
| CN111178957A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for early warning sudden increase of electric quantity of electricity consumption customer |
| CN112686449A (en) * | 2020-12-31 | 2021-04-20 | 国网河南省电力公司经济技术研究院 | Residential electricity consumption prediction method based on human body weather comfort index |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627682A (en) * | 2021-08-25 | 2021-11-09 | 深圳供电局有限公司 | Method and system for predicting daily electric quantity fluctuation of non-residential users |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991875B (en) | Platform user quality evaluation system | |
| CN113743673B (en) | Power load prediction method during typhoon | |
| CN110198302B (en) | Privacy protection method and system for data release of intelligent electric meter | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN103810538A (en) | Electricity sale quantity distribution method and device | |
| Yi et al. | Balancing cost and dissatisfaction in online EV charging under real-time pricing | |
| CN107957988A (en) | For determining the method, apparatus and electronic equipment of data exception reason | |
| CN104866922A (en) | User off-network prediction method and apparatus | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN110135652B (en) | Long-term flood season runoff prediction method | |
| CN115905904A (en) | Line loss abnormity evaluation method and device for power distribution network feeder line | |
| CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
| CN113222245A (en) | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium | |
| CN114357737A (en) | Agent optimization calibration method for time-varying parameters of large-scale hydrological model | |
| CN114186733A (en) | Short-term load prediction method and device | |
| CN111800807A (en) | Method and device for alarming number of base station users | |
| CN112465266A (en) | Bus load prediction accuracy analysis method and device and computer equipment | |
| CN116706884A (en) | Photovoltaic power generation amount prediction method, device, terminal and storage medium | |
| CN114549095B (en) | Sliding window type electricity selling amount prediction method based on time sequence | |
| CN110880987A (en) | Packet domain network capacity prediction method and system based on time characteristics | |
| CN116050636A (en) | Output prediction method, device, equipment and medium of photovoltaic power station | |
| CN115864461A (en) | Control method of electric power energy storage system | |
| CN113468811B (en) | Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit | |
| CN115169089A (en) | Wind power probability prediction method and device based on kernel density estimation and copula | |
| CN114781720A (en) | Regional carbon emission prediction method and device and terminal equipment |
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 |