CN117452062A - Method for monitoring line loss rate of transformer area in consideration of operation load - Google Patents
Method for monitoring line loss rate of transformer area in consideration of operation load Download PDFInfo
- Publication number
- CN117452062A CN117452062A CN202311342368.1A CN202311342368A CN117452062A CN 117452062 A CN117452062 A CN 117452062A CN 202311342368 A CN202311342368 A CN 202311342368A CN 117452062 A CN117452062 A CN 117452062A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- loss rate
- line loss
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/06—Arrangements for measuring electric power or power factor by measuring current and voltage
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Power Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to the technical field of monitoring of the line loss rate of a transformer area, and discloses a monitoring method of the line loss rate of the transformer area considering the operation load, which comprises the following steps: data acquisition and preprocessing, feature extraction, monitoring model establishment, model training and optimization, deployment and real-time monitoring. According to the method for monitoring the line loss rate of the transformer area considering the operation load, the sensor group arranged on the power supply equipment of the transformer area can comprehensively collect relevant operation data of the transformer area, the collection of multi-source data can comprehensively analyze and evaluate a plurality of influence factors of the line loss rate, the collected data are preprocessed, the quality and accuracy of the data are improved, the load characteristics, the temperature characteristics, the power factor characteristics, the relevance characteristics, the waveform characteristics, the time characteristics and the trend characteristics of the transformer area are extracted from the preprocessed data in the characteristic extraction stage, the influence of the multi-dimensional factors on the line loss rate is fully considered, and more accurate and reliable monitoring of the line loss rate of the transformer area is realized.
Description
Technical Field
The invention relates to the technical field of monitoring of line loss rate of a transformer area, in particular to a monitoring method of line loss rate of a transformer area considering operation load.
Background
The line loss of a bay refers to the loss of electric energy in the bay in the electric power system, specifically, the line loss of the bay refers to the loss caused by factors such as resistance, inductance and capacitance in equipment such as a power transmission line, a transformer, a cable, a distribution line and the like of the bay in the electric energy transmitted from a power supply station to a user terminal, and the line loss rate of the bay refers to the ratio of the line loss occurring on a line between the power supply station and an electric energy terminal to the electric energy input by the power supply station.
The high station area line loss rate can cause the reduction of power supply quality, such as unstable voltage, waste of electric energy, reduction of user service capacity and the like, and the monitoring station area line loss rate can timely find and solve the problem of power supply quality reduction, so that the reliability and stability of power supply are improved, the energy utilization efficiency is improved, the energy resources are saved, and the power supply device contributes to sustainable development.
The prior art monitors the line loss rate of the transformer area, because the method mainly depends on the reading of an electric energy meter and a small amount of load data, the dimension of comprehensive multi-source data is lacking, the influence of other factors on the line loss rate cannot be comprehensively considered, for example, factors such as temperature, humidity and weather can also influence the line loss condition of a line, the prior art usually ignores the factors, the data processing and algorithm accuracy is limited, meaningful characteristics cannot be accurately extracted, an accurate line loss rate prediction model is not established, the accuracy and the reliability of the monitoring method are influenced, and the conditions of false alarm and missing alarm are easily generated, so that the method for monitoring the line loss rate of the transformer area, which considers the operation load, is proposed.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a method for monitoring the line loss rate of a platform area by considering the operation load, which has the advantages of multiple data sources and high data processing and algorithm precision, and solves the problems that the prior art monitors the line loss rate of the platform area, the prior art mainly depends on the reading of an electric energy meter and a small amount of load data, lacks the dimension of comprehensive multi-source data, cannot comprehensively consider the influence of other factors on the line loss rate, such as temperature, humidity, weather and the like, also influence the line loss condition of a line, the prior art often ignores the factors, the precision of data processing and algorithm is limited, meaningful characteristics cannot be accurately extracted, an accurate line loss rate prediction model is built, the accuracy and the reliability of the monitoring method are influenced, and false alarm and missing alarm conditions are easy to generate.
(II) technical scheme
In order to achieve the purposes of multiple data sources and high data processing and algorithm precision, the invention provides the following technical scheme: a method for monitoring the line loss rate of a station area in consideration of operation load comprises the following steps:
1) Data acquisition and pretreatment: collecting relevant operation data of a platform area through an intelligent ammeter and a sensor group arranged on power supply equipment of the platform area, and preprocessing the collected data;
2) Feature extraction: extracting features of the area from the preprocessed data;
3) Establishing a monitoring model: establishing a model by using a supervised learning technology, and associating the extracted characteristics with the actual line loss rate of the station area;
4) Model training and optimizing: training the monitoring model by using historical data, optimizing model parameters, and improving prediction accuracy and stability;
5) Deployment and real-time monitoring: the trained model is deployed into an actual monitoring system, changes of the line loss rate of the station area are monitored in real time, and early warning or alarming is conducted in time.
Preferably, the sensor group installed on the power supply equipment of the transformer area comprises a current sensor, a voltage sensor, a power sensor, a temperature sensor, a humidity sensor and a leakage sensor, and the related data information of the transformer area comprises electric energy data, current data, voltage data, power data, temperature data and humidity data.
Preferably, preprocessing is performed on the acquired data, including data cleaning, denoising and outlier processing, so that the quality and accuracy of the data are improved.
Preferably, the zone characteristics include a zone load characteristic, a zone temperature characteristic, a correlation characteristic, a power factor characteristic, a waveform characteristic, a time characteristic, and a trend characteristic.
Preferably, a linear regression algorithm is used to build a monitoring model and predict the line loss rate by a linear relationship between the features and the line loss rate.
Preferably, the training procedure of the monitoring model is as follows:
(1) Data set partitioning: dividing the collected historical data into a training set and a verification set by adopting a cross verification method;
(2) Model training: training the selected model by using a training set through a random gradient descent algorithm, and adjusting parameters of the model according to a loss function in the training process so as to minimize training errors;
(3) Model evaluation: evaluating the trained model by using a verification set, calculating an evaluation index, and knowing the generalization capability and performance of the model;
(4) And (3) model tuning: and (5) optimizing the model according to the evaluation result.
Preferably, the evaluation index includes a mean square error, an average absolute error, an accuracy, a precision, and an F1-score.
Preferably, the tuning of the model includes parameter adjustment, model complexity control and feature selection, and the selection of the best model parameters through cross-validation.
Preferably, after the model is tuned, the final optimized model is tested by using a test set, and the prediction effect of the model on new data is evaluated.
Preferably, an early warning and alarming mechanism is set based on a prediction result of the model, and when the line loss rate is abnormal or exceeds a preset threshold value, early warning and alarming are carried out in a mode of message pushing, alarming sound and flashing and wireless communication equipment information pushing.
(III) beneficial effects
Compared with the prior art, the invention provides a method for monitoring the line loss rate of a station area by considering the operation load, which has the following beneficial effects:
1. according to the method for monitoring the line loss rate of the transformer area taking the operation load into consideration, through the sensor group consisting of the current sensor, the voltage sensor, the power sensor, the temperature sensor, the humidity sensor and the leakage sensor which is arranged on the power supply equipment of the transformer area, the related operation data of the transformer area including electric energy data, current data, voltage data, power data, temperature data and humidity data can be comprehensively collected, multiple influencing factors of the line loss rate can be comprehensively analyzed and evaluated through the collection of multi-source data, the collected data is preprocessed, including data cleaning, denoising and abnormal value processing, the quality and accuracy of the data are improved, and in the characteristic extraction stage, the influence of the transformer area load characteristic, the temperature characteristic, the power factor characteristic, the correlation characteristic, the waveform characteristic, the time characteristic and the trend characteristic on the line loss rate are fully considered, so that the more accurate and reliable monitoring of the line loss rate of the transformer area is realized.
2. According to the monitoring method for the line loss rate of the transformer area, a monitoring model is established by using a supervision learning technology, the extracted characteristics are associated with the actual line loss rate of the transformer area through a training model, in the model training and optimizing process, historical data are used for training the monitoring model, model parameters are optimized, prediction accuracy and stability are improved, the trained model is deployed into an actual monitoring system, real-time monitoring of the line loss rate of the transformer area is achieved, abnormal changes of the line loss rate can be found timely through analysis and prediction of the real-time data through the monitoring model, and timely early warning and alarm are conducted through an early warning and alarm mechanism, so that accuracy and reliability of the monitoring method are improved, and false alarm and missing alarm conditions are reduced.
Drawings
Fig. 1 is a schematic diagram of a process for monitoring a line loss rate of a cell according to the present invention;
fig. 2 is a schematic diagram of a training process of the monitoring model of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, a method for monitoring a line loss rate of a station area in consideration of an operation load includes the following steps:
1) Data acquisition and pretreatment: collecting relevant operation data of a platform area through an intelligent ammeter and a sensor group arranged on power supply equipment of the platform area, and preprocessing the collected data;
2) Feature extraction: extracting features of the area from the preprocessed data;
3) Establishing a monitoring model: establishing a model by using a supervised learning technology, and associating the extracted characteristics with the actual line loss rate of the station area;
4) Model training and optimizing: training the monitoring model by using historical data, optimizing model parameters, and improving prediction accuracy and stability;
5) Deployment and real-time monitoring: the trained model is deployed into an actual monitoring system, changes of the line loss rate of the station area are monitored in real time, and early warning or alarming is conducted in time.
Specifically, the sensor group installed on the power supply equipment of the platform area comprises a current sensor, a voltage sensor, a power sensor, a temperature sensor, a humidity sensor and a leakage sensor, and the related data information of the platform area comprises electric energy data, current data, voltage data, power data, temperature data and humidity data.
Further, the data collected by the sensor group can be used for predicting the line loss rate of the station area and helping to monitor the change of the line loss rate of the station area in real time, the current, voltage and power data can be used for calculating the line loss rate, the temperature and humidity data can provide environment information, the leakage sensor can detect the leakage condition, and the data can be used for extracting the characteristics of the station area and establishing a monitoring model so as to predict and monitor the line loss rate of the station area.
Specifically, preprocessing is performed on the collected data, including data cleaning, denoising and outlier processing, so that the quality and accuracy of the data are improved.
Further, in the process of monitoring the line loss rate of the area, some problems may exist in the acquired data, such as noise, abnormal values or incomplete data, which may negatively affect the subsequent analysis and model establishment, and the data may be corrected and filtered through preprocessing steps such as data cleaning, denoising, abnormal value processing and the like, so that errors or anomalies in the data are eliminated or reduced, and thus the quality and accuracy of the data may be improved, and the subsequent feature extraction and monitoring model establishment process is more reliable and effective.
Specifically, the zone characteristics include a zone load characteristic, a zone temperature characteristic, a correlation characteristic, a power factor characteristic, a waveform characteristic, a time characteristic, and a trend characteristic.
Furthermore, the temperature characteristics of the platform region can reflect the temperature conditions of the platform region, including the environment temperature, the equipment temperature and the like, the overheat or abnormal temperature condition of the equipment can be found in time, and corresponding measures are taken to avoid the increase of the line loss rate; the correlation characteristics can analyze the correlation between different variables, and can know the influence degree of each factor on the line loss rate, so that the operation strategy of the station area is optimized, and the line loss rate is reduced; the power factor characteristics can reflect the power factor condition of the station area, can find the abnormal or bad condition of the power factor, adjust the power factor of the power system in time, reduce the line loss rate; the waveform characteristics can analyze the waveform characteristics of the power signals, can find problems of distortion, harmonic waves and the like of the power signals, and timely take measures to improve the power quality and reduce the line loss rate; the time characteristics can reflect the change trend of the line loss rate of the station area along with time; the trend feature may analyze long-term trends in line loss rate.
Specifically, a linear regression algorithm is used to build a monitoring model, and the line loss rate is predicted through the linear relation between the characteristics and the line loss rate.
Furthermore, the linear regression algorithm is a simple and visual regression analysis method, is easy to understand and realize, can directly predict the line loss rate by using the characteristic value by establishing the linear relation between the characteristic and the line loss rate, does not need to introduce a complex model and algorithm, has high calculation efficiency, and can quickly establish a model for a large-scale data set, so that the linear regression has higher instantaneity and operability in practical application.
Specifically, the training process of the monitoring model is as follows:
(1) Data set partitioning: dividing the collected historical data into a training set and a verification set by adopting a cross verification method;
(2) Model training: training the selected model by using a training set through a random gradient descent algorithm, and adjusting parameters of the model according to a loss function in the training process so as to minimize training errors;
(3) Model evaluation: evaluating the trained model by using a verification set, calculating an evaluation index, and knowing the generalization capability and performance of the model;
(4) And (3) model tuning: and (5) optimizing the model according to the evaluation result.
Further, the selected linear regression model is trained by using a training set through a random gradient descent algorithm, in the training process, the model can minimize training errors by adjusting parameters of the model, so that the linear relation between the characteristics and the line loss rate is better fitted, the trained model is evaluated by using a verification set, evaluation indexes are calculated to know the performance and generalization capability of the model, and the evaluation result can help to judge the prediction accuracy of the model and guide further model tuning.
Specifically, the evaluation index includes a mean square error, an average absolute error, an accuracy, a precision, and an F1-score.
Further, the mean square error and the mean absolute error are used for measuring the difference between the model prediction result and the true value, the accuracy is an evaluation index for classifying problems, the accuracy represents the proportion of the number of correctly predicted samples of the model to the total number of samples, the accuracy represents the proportion of the model to the true positive class in the samples predicted to the positive class, and the accuracy and the recall are comprehensively considered by the F1-score and are used for evaluating the comprehensive performance of the classifying problems.
Specifically, the tuning of the model includes parameter adjustment, model complexity control and feature selection, and optimal model parameters are selected through cross-validation.
Furthermore, the learning capacity and complexity of the model can be changed by adjusting the parameters of the model, and the fitting capacity of the model can be improved by adjusting the parameters, so that the model is better adapted to actual data, and the problems of over-fitting or under-fitting are avoided; the model complexity refers to the number and complexity of parameters or features contained in the model, and proper control of the model complexity can avoid the model from being too simple or too complex, so that the generalization capability of the model is improved, and the overfitting to noise and irrelevant information is reduced; by selecting proper characteristics, the complexity of the model can be reduced, the performance of the model can be improved, redundant and irrelevant characteristics can be filtered by the characteristic selection, and the characteristics which are most significant and relevant for line loss rate prediction are extracted, so that the prediction accuracy and interpretation capability of the model are improved; the cross verification is a method for evaluating the performance of the model by dividing a data set, training and verifying for multiple times, and the performance of the model under different parameter configurations can be comprehensively considered by selecting the optimal model parameters through the cross verification, and the model parameters with optimal performance are selected, so that the prediction accuracy and generalization capability of the model are improved.
Specifically, after the model is optimized, a test set is used for testing the finally optimized model, and the prediction effect of the model on new data is estimated.
Furthermore, the test set contains data which are not found before the model, so that the generalization capability of the model to new data can be evaluated, and the prediction accuracy and stability of the model in practical application can be determined through the evaluation of the test set; if the model does not perform well on the test set, the generalization capability of the model is required to be improved, the defects of the model can be known according to the evaluation result of the test set, and the model is adjusted and improved in a targeted manner; by comparing the final optimized model with other models or reference models, the relative performance of the models can be evaluated, which helps us to understand the dominance and competitiveness of the final model and make decisions to select the appropriate model.
Specifically, based on the prediction result of the model, an early warning and alarming mechanism is set, and when the line loss rate is abnormal or exceeds a preset threshold value, early warning and alarming are carried out in a message pushing mode, an alarming sound mode, a flashing mode and a wireless communication device information pushing mode.
Furthermore, by setting an early warning and alarming mechanism based on a prediction result of the model, the line loss rate can be monitored in time and an abnormal situation can be found, so that a power system manager can be helped to respond to the problem quickly, corresponding measures are taken to avoid potential loss or faults, early warning and alarming are carried out in a mode of message pushing, alarming sound and flashing and wireless communication equipment information pushing, the fact that relevant personnel can receive alarm information in time can be ensured, the response speed can be improved, the manager can take actions quickly, and the problem of abnormal line loss rate can be solved in time.
In summary, according to the method for monitoring the line loss rate of the transformer area taking the operation load into consideration, through the sensor group consisting of the current sensor, the voltage sensor, the power sensor, the temperature sensor, the humidity sensor and the leakage sensor which is arranged on the power supply equipment of the transformer area, the related operation data of the transformer area including the electric energy data, the current data, the voltage data, the power data, the temperature data and the humidity data can be comprehensively collected, a plurality of influencing factors of the line loss rate can be comprehensively analyzed and evaluated through the collection of the multi-source data, the collected data is preprocessed, including data cleaning, denoising and outlier processing, the quality and the accuracy of the data are improved, and in the characteristic extraction stage, the influence of the transformer area load characteristic, the temperature characteristic, the power factor characteristic, the correlation characteristic, the waveform characteristic, the time characteristic and the trend characteristic on the line loss rate are fully considered, so that the more accurate and reliable line loss rate monitoring of the transformer area is realized.
In addition, the monitoring method for the line loss rate of the transformer area taking the operation load into consideration uses a supervision learning technology to establish a monitoring model, the extracted characteristics are associated with the actual line loss rate of the transformer area through a training model, in the model training and optimizing process, historical data are used for training the monitoring model, model parameters are optimized, prediction accuracy and stability are improved, the trained model is deployed into an actual monitoring system to realize real-time monitoring of the line loss rate of the transformer area, the abnormal change of the line loss rate can be found in time through analysis and prediction of the real-time data by the monitoring model, and timely early warning and alarm are carried out through an early warning and alarm mechanism, so that the problems that the accuracy and reliability of the monitoring method are improved, the situation that the line loss rate of the transformer area is monitored in the prior art is reduced, the influence of other factors on the line loss rate cannot be comprehensively considered due to the fact that the dimension of electric energy meter reading and a small amount of load data is lacked, the prior art often has neglected, the influence on the line loss conditions of the line is caused by factors such as temperature, humidity and weather factors, the like, the accuracy and the accuracy of the prediction accuracy of the data cannot be easily achieved, and the accuracy of the prediction accuracy and the accuracy of the prediction method is improved, and the accuracy of the extracted data is not easy, and the accuracy and the reliability of the prediction is not established.
The related modules involved in the system are all hardware system modules or functional modules in the prior art combining computer software programs or protocols with hardware, and the computer software programs or protocols involved in the functional modules are all known technologies for those skilled in the art and are not improvements of the system; the system is improved in interaction relation or connection relation among the modules, namely, the overall structure of the system is improved, so that the corresponding technical problems to be solved by the system are solved.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The method for monitoring the line loss rate of the transformer area in consideration of the operation load is characterized by comprising the following steps of:
1) Data acquisition and pretreatment: collecting relevant operation data of a platform area through an intelligent ammeter and a sensor group arranged on power supply equipment of the platform area, and preprocessing the collected data;
2) Feature extraction: extracting features of the area from the preprocessed data;
3) Establishing a monitoring model: establishing a model by using a supervised learning technology, and associating the extracted characteristics with the actual line loss rate of the station area;
4) Model training and optimizing: training the monitoring model by using historical data, optimizing model parameters, and improving prediction accuracy and stability;
5) Deployment and real-time monitoring: the trained model is deployed into an actual monitoring system, changes of the line loss rate of the station area are monitored in real time, and early warning or alarming is conducted in time.
2. The method according to claim 1, wherein in the step 1), the sensor group installed on the power supply equipment of the transformer area includes a current sensor, a voltage sensor, a power sensor, a temperature sensor, a humidity sensor and a leakage sensor, and the data information related to the transformer area includes electric energy data, current data, voltage data, power data, temperature data and humidity data.
3. The method for monitoring the line loss rate of the station area considering the operation load according to claim 1, wherein in the step 1), the collected data is preprocessed, including data cleaning, denoising and outlier processing, so as to improve the quality and accuracy of the data.
4. The method for monitoring the line loss rate of a platform according to claim 1, wherein in the step 2), the platform characteristics include platform load characteristics, platform temperature characteristics, correlation characteristics, power factor characteristics, waveform characteristics, time characteristics and trend characteristics.
5. The method for monitoring the line loss rate of a platform area according to claim 1, wherein in the step 3), a linear regression algorithm is used to build a monitoring model, and the line loss rate is predicted by a linear relation between the characteristics and the line loss rate.
6. The method for monitoring the line loss rate of a station area considering the operation load according to claim 1, wherein in the step 4), the training process of the monitoring model is as follows:
(1) Data set partitioning: dividing the collected historical data into a training set and a verification set by adopting a cross verification method;
(2) Model training: training the selected model by using a training set through a random gradient descent algorithm, and adjusting parameters of the model according to a loss function in the training process so as to minimize training errors;
(3) Model evaluation: evaluating the trained model by using a verification set, calculating an evaluation index, and knowing the generalization capability and performance of the model;
(4) And (3) model tuning: and (5) optimizing the model according to the evaluation result.
7. The method of claim 6, wherein in the step (3), the evaluation index includes mean square error, average absolute error, accuracy, precision, and F1-score.
8. The method for monitoring line loss rate of a station area considering operation load according to claim 6, wherein in the step (4), the content of tuning the model includes parameter adjustment, model complexity control and feature selection, and the optimal model parameters are selected through cross-validation.
9. The method for monitoring the line loss rate of a platform area considering the operation load according to claim 6, wherein in the step (4), after the model is tuned, a test set is used to test the finally optimized model, and the prediction effect of the model on new data is evaluated.
10. The method for monitoring the line loss rate of the station area considering the operation load according to claim 1, wherein in the step 5), an early warning and alarming mechanism is set based on the prediction result of the model, and when the line loss rate is abnormal or exceeds a predetermined threshold, the early warning and alarming are performed by means of message pushing, alarming sound and flashing and wireless communication equipment information pushing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311342368.1A CN117452062A (en) | 2023-10-17 | 2023-10-17 | Method for monitoring line loss rate of transformer area in consideration of operation load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311342368.1A CN117452062A (en) | 2023-10-17 | 2023-10-17 | Method for monitoring line loss rate of transformer area in consideration of operation load |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117452062A true CN117452062A (en) | 2024-01-26 |
Family
ID=89584624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311342368.1A Pending CN117452062A (en) | 2023-10-17 | 2023-10-17 | Method for monitoring line loss rate of transformer area in consideration of operation load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117452062A (en) |
-
2023
- 2023-10-17 CN CN202311342368.1A patent/CN117452062A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN107844067B (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| CN116559598B (en) | Smart distribution network fault positioning method and system | |
| CN117060409B (en) | Automatic detection and analysis method and system for power line running state | |
| JP2017524325A (en) | System and method for classifying on-site sensor response data patterns representing grid anomaly severity | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN116800199A (en) | Distributed photovoltaic operation electric energy quality monitoring and analyzing method | |
| CN113987908A (en) | Natural gas pipe network leakage early warning method based on machine learning method | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN114781476A (en) | Fault analysis system and method for measuring equipment | |
| CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
| CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
| CN117639251A (en) | Intelligent online monitoring system for high-voltage switch cabinet | |
| CN112904148A (en) | Intelligent cable operation monitoring system, method and device | |
| CN117041312A (en) | Enterprise-level information technology monitoring system based on Internet of things | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN117452062A (en) | Method for monitoring line loss rate of transformer area in consideration of operation load | |
| CN113109666B (en) | Rail circuit fault diagnosis method based on deep convolutional neural network | |
| CN115936663A (en) | Maintenance method and device for power system | |
| CN114997375A (en) | Insulator surface metal pollution model building system in air type switch cabinet | |
| CN114414938B (en) | Dynamic response method and system for power distribution network faults | |
| CN111024141B (en) | Online detection system of environmental pollution detection equipment based on wireless communication | |
| CN117591507B (en) | Automatic construction method and system for data quality characteristics of measurement and control equipment | |
| CN115828165B (en) | New energy intelligent micro-grid data processing method and system |
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 |