CN118473097B - Intelligent line loss detection and alarm method and device for power distribution network - Google Patents
Intelligent line loss detection and alarm method and device for power distribution network Download PDFInfo
- Publication number
- CN118473097B CN118473097B CN202410910456.5A CN202410910456A CN118473097B CN 118473097 B CN118473097 B CN 118473097B CN 202410910456 A CN202410910456 A CN 202410910456A CN 118473097 B CN118473097 B CN 118473097B
- Authority
- CN
- China
- Prior art keywords
- line loss
- line
- load
- loss
- rates
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 45
- 238000013461 design Methods 0.000 claims abstract description 40
- 230000005611 electricity Effects 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000007726 management method Methods 0.000 claims description 36
- 230000005856 abnormality Effects 0.000 claims description 35
- 230000004927 fusion Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000009467 reduction Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000009825 accumulation Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 230000002547 anomalous effect Effects 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000011835 investigation Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 16
- 238000012795 verification Methods 0.000 description 6
- 230000032683 aging Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000002864 sequence alignment Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an intelligent line loss detection alarm method and device for a power distribution network, and relates to the technical field of power distribution network line loss detection, wherein the method comprises the following steps: acquiring line design information, and carrying out line no-load loss identification according to the line design information to generate no-load line loss rate; receiving a preset plan and collecting electricity selling information; carrying out loss identification according to electricity selling information and a preset plan, and generating a real-time line loss rate; carrying out loss rate identification according to the real-time line loss rate and the no-load line loss rate, and collecting a state data set if the loss rate exceeds the standard; performing dynamic loss analysis based on the state data set to generate a dynamic line loss rate; and generating alarm information by combining the three loss rates to carry out abnormal alarm. The method solves the technical problem that the auxiliary performance of the subsequent line loss abnormal cause investigation is low due to the fact that the line loss analysis mode based on the threshold value direct judgment cannot be used for carrying out early warning pertinently due to various reasons of line loss, and achieves the effects of improving the line loss detection accuracy and enabling the operation management of the power distribution network to be more efficient and accurate.
Description
Technical Field
The application relates to the technical field of line loss detection of power distribution networks, in particular to an intelligent line loss detection alarming method and device of a power distribution network.
Background
With the rapid development of the power industry and the continuous expansion of the power grid scale, the line loss management of the power distribution network becomes a key link for guaranteeing the efficient operation of a power system and reducing the energy loss. However, with the complexity of the power grid structure and the diversification of load demands, the line loss detection and management of the power distribution network face an increasing challenge. Traditional line loss detection methods often rely on direct analysis and threshold judgment of line operation data, and the method is worry about dealing with complex and variable line loss problems. The reasons for line loss are various, and the method has technical factors such as equipment aging, improper line design and the like, and management factors such as improper operation and maintenance, unreasonable scheduling strategies and the like, and the specific reasons cannot be identified in a targeted manner by directly carrying out early warning according to the threshold value, so that the follow-up line loss abnormal reason is low in assistance.
Disclosure of Invention
The intelligent line loss detection alarm method and device for the power distribution network solve the technical problems that early warning cannot be performed pertinently due to various reasons for line loss in a line loss analysis mode based on threshold direct judgment and the follow-up line loss abnormal reason is low in assistance, and achieve the effects of improving the line loss detection accuracy and enabling operation management of the power distribution network to be more efficient and accurate.
The application provides an intelligent line loss detection and alarm method of a power distribution network, which comprises the following steps: acquiring a plurality of line design information of a plurality of distribution lines of a target distribution network, and carrying out line no-load loss identification according to the plurality of line design information to generate a plurality of no-load line loss rates; receiving a preset power distribution plan of the target power distribution network in a preset time zone, and collecting electricity selling information in the preset time zone; carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates; variable line loss rate identification is carried out according to the real-time line loss rates and the idle line loss rates, and if the variable line loss rate is larger than a preset variable line loss rate, a plurality of line load state data sets of the distribution lines are collected; performing dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates; and generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to perform line loss abnormality alarm.
The application also provides an intelligent line loss detection and alarm device of the power distribution network, which comprises the following components: the no-load loss identification module is used for acquiring a plurality of line design information of a plurality of distribution lines of the target distribution network, carrying out line no-load loss identification according to the plurality of line design information and generating a plurality of no-load line loss rates; the data analysis module is used for receiving a preset power distribution plan of the target power distribution network in a preset time zone and collecting electricity selling information in the preset time zone; the electric energy loss identification module is used for carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates; the variable line loss rate identification module is used for carrying out variable line loss rate identification according to the real-time line loss rates and the idle line loss rates, and collecting a plurality of line load state data sets of the distribution lines if the variable line loss rate is larger than a preset variable line loss rate; the dynamic loss analysis module is used for carrying out dynamic loss analysis based on the plurality of line load state data sets and generating a plurality of dynamic line loss rates; and the line loss abnormality alarming module is used for generating alarming information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to carry out line loss abnormality alarming.
The intelligent line loss detection alarm method and the intelligent line loss detection alarm device for the power distribution network acquire a plurality of line design information of a plurality of power distribution lines of a target power distribution network, and perform line no-load loss identification according to the plurality of line design information to generate a plurality of no-load line loss rates; receiving a preset power distribution plan of the target power distribution network in a preset time zone, and collecting electricity selling information in the preset time zone; carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates; variable line loss rate identification is carried out according to the real-time line loss rates and the idle line loss rates, and if the variable line loss rate is larger than a preset variable line loss rate, a plurality of line load state data sets of the distribution lines are collected; performing dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates; and generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to perform line loss abnormality alarm. The method solves the technical problem that the auxiliary performance of the subsequent line loss abnormal cause investigation is low due to the fact that the line loss analysis mode based on the threshold value direct judgment cannot be used for carrying out early warning pertinently due to various reasons of line loss, and achieves the effects of improving the line loss detection accuracy and enabling the operation management of the power distribution network to be more efficient and accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly describe the drawings of the embodiments of the present disclosure, in which flowcharts are used to illustrate operations performed by devices according to embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic flow chart of an intelligent line loss detection and alarm method for a power distribution network according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of an intelligent line loss detection alarm device for a power distribution network according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an empty load loss identification module 1, a data analysis module 2, an electric energy loss identification module 3, a variable line loss rate identification module 4, a dynamic loss analysis module 5 and a line loss abnormality alarm module 6.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides an intelligent line loss detection and alarm method of a power distribution network, as shown in fig. 1, comprising the following steps:
And acquiring a plurality of line design information of a plurality of distribution lines of the target distribution network, and carrying out line no-load loss identification according to the plurality of line design information to generate a plurality of no-load line loss rates.
In the embodiment of the application, in the line loss management of the power distribution network, the accurate identification and calculation of no-load loss, namely fixed loss or basic loss are important. By no-load loss is meant a fixed loss of energy generated by certain devices or components in the distribution network, irrespective of load variations. These losses include mainly transformer core losses, high voltage line corona losses, ammeter coil losses, etc. In order to accurately evaluate the no-load loss condition of a target power distribution network, a system terminal firstly acquires a plurality of line design information of a plurality of distribution lines. Such information includes critical parameters such as length of the line, material, wire cross section, type and capacity of transformer used, voltage class, etc. Based on the detailed line design information, the system terminal performs no-load loss accumulation calculation of the power grid element, and calculates no-load line loss rate of each line design information by combining rated distribution power. In this way, the system terminal may generate a plurality of idle line loss rates. The no-load line loss rate not only reflects the energy loss condition of the power distribution network in the no-load state, but also provides an important basis for the subsequent line loss abnormality cause investigation and energy saving and consumption reduction measures.
Further, the present application provides a method for identifying line no-load loss according to the multiple line design information, and generating multiple no-load line loss rates, including:
Extracting first circuit design information of a first distribution circuit according to the plurality of circuit design information, wherein the first circuit design information comprises the specification and the number of power grid elements in the first distribution circuit; carrying out no-load loss accumulation calculation on the power grid element according to the first circuit design information to generate a first no-load loss; and combining the rated distribution power of the first distribution line and the first no-load loss, calculating and obtaining a first no-load line loss rate, and adding the first no-load line loss rate into the multiple no-load line loss rates.
Preferably, the system terminal randomly extracts one line design information from the plurality of line design information as detailed design data of the first distribution line, i.e., the first line design information of the first distribution line. Such information includes the specifications and number of grid elements used in the line. Grid elements are the basic components that form the grid, such as voltage regulators, transformers, cables, voltage coils, capacitors, etc. The system terminal then performs a no-load loss calculation of the grid element based on the extracted first line design information. No-load losses refer to energy losses that occur when the grid elements are not loaded or are very low loaded. For a transformer, the system terminal directly uses the no-load loss data on the nameplate of the transformer, or searches the model and the capacity of the transformer to find the corresponding standard no-load loss data. For elements such as cables and capacitors, the no-load loss of which is related to the dielectric loss data per unit length and the actual length of the line, the system terminal obtains the total no-load loss by multiplying the dielectric loss per unit length by the actual length of the line. After the no-load loss calculation of each element is completed, the system terminal performs the operation of accumulating the total no-load loss. This represents the system termination adding the values of the no-load losses of all grid elements, resulting in a total no-load loss of the entire first distribution line, i.e. the first no-load loss. And then, calculating a first no-load line loss rate by combining the rated distribution power of the first distribution line and the calculated first no-load loss. The no-load line loss rate is the proportion of no-load loss to rated distribution power, and reflects the energy loss condition of the power grid in an no-load state. The system terminal then adds the calculated no-load line loss rate to a set of no-load line loss rates to evaluate and compare the performance of the overall grid system.
And receiving a preset power distribution plan of the target power distribution network in a preset time zone, and collecting electricity selling information in the preset time zone.
In one embodiment, to accurately evaluate the real-time line loss rate, the system terminal receives a preset power distribution plan for the target power distribution network in a preset time zone. This plan includes information such as the expected load of the grid during the period, the expected power distribution strategy, and possibly the power dispatch plan. The preset time zone is set based on the actual operation requirement of the power grid, the load change characteristics and the convenience in management. And then the system terminal collects the actual electricity selling information in the preset time zone. The electricity selling information mainly reflects the actual electricity selling condition of the power grid in the period, and the electricity selling information comprises key data such as electricity selling quantity, electricity selling time, electricity price and the like. These data are critical to understanding the actual operating conditions and load changes of the grid.
And carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates.
In one embodiment, to accurately calculate the real-time line loss rate of the power grid, we need to calculate the actual power loss. The process is based on collected electricity selling information and preset power distribution planning, and the electric energy loss of a plurality of lines in the power distribution network is identified through a real-time loss identification model. Specifically, the system terminal collects multiple groups of historical line loss detection records from the historical line loss database, the historical line loss detection records comprise historical electricity selling information, historical power distribution planning and corresponding historical line loss rates, and the multiple groups of historical line loss detection records are divided into a training set and a verification set. Then, designing a long-term and short-term memory network model structure, including determining the number of hidden layers, the number of hidden units, the input layer dimension, the output layer dimension, etc. These are determined based on actual problems and data characteristics. After the model structure is determined, the system terminal initializes model parameters such as weights and bias terms. And then, the system terminal trains the constructed model structure by using the training set, and updates the model parameters through a back propagation algorithm. And when each training period is finished, the system terminal uses the verification set to evaluate the performance of the model, judges whether the model meets the preset expectations or not, and records the performance index. If the model parameters are not satisfied, the system terminal adjusts the model parameters, such as learning rate, hidden layer number and the like, according to the performance index of the verification set, performs super-parameter tuning and optimizing until the preset expectations are satisfied, outputs the trained long-short term memory network model, and generates a real-time loss identification model. After the real-time loss identification model is built, the system terminal inputs the acquired electricity selling information and the preset power distribution plan into the real-time loss identification model to identify the energy loss of a plurality of power distribution lines. After the real-time loss identification model receives electricity selling information and preset power distribution planning, the real-time line loss rate of each power distribution line is calculated according to the learned knowledge, and a plurality of real-time line loss rates are generated. The real-time line loss rates reflect the electric energy loss condition of the line in a time period and are important indexes for evaluating the operation efficiency of the line.
And carrying out variable line loss rate identification according to the real-time line loss rates and the empty line loss rates, and collecting a plurality of line load state data sets of the distribution lines if the variable line loss rate is larger than a preset variable line loss rate.
In one embodiment, variable line loss rate identification is an important step in line loss detection, involving accurate calculation and assessment of line loss of the grid under normal operating conditions, i.e. with actual load. The calculation process is to use the real-time line loss rate of a distribution line to subtract the corresponding no-load line loss rate, thereby calculating the variable line loss rate. This variable line loss rate reflects the line loss variation due to the load current variation. If the variable line loss rate is larger than the preset variable line loss rate threshold value, the variable line loss rate represents that certain abnormal conditions exist in the power grid, such as line aging, uneven load distribution, equipment faults and the like. This preset variable line loss rate is set based on historical operating experience and safety standards. In this case, in order to further diagnose the problem and take corresponding measures, the system terminal collects a plurality of line load state data sets of a plurality of distribution lines, each line load state data set corresponding to a distribution line one by one. These line load status data sets include real-time parameters such as current, voltage, power factor, etc. on the line, and information such as the spatial and temporal distribution of the load, etc. to be used for further analysis and processing.
And carrying out dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates.
In one embodiment, dynamic loss analysis is a critical analysis process in line loss detection to evaluate line loss due to variable factors in line operation, such as load changes, ambient temperature changes, etc. These variable factors may cause changes in parameters such as resistance and inductance in the line, which may affect the loss condition of the line. And when the dynamic loss analysis is carried out, the system terminal calls a dynamic loss identification model to carry out dynamic loss calculation on each line based on the obtained multiple line load state data sets. Dynamic loss refers to line loss that may vary due to variable factors in line operation, in addition to the no-load line loss itself. Dynamic losses vary in real time and are related to various factors such as the load state of the line, the ambient temperature, etc. And the system terminal obtains a plurality of dynamic line loss rates through dynamic loss analysis. These dynamic line loss rates reflect the loss of the line under different load conditions. Theoretically, the sum of the empty line loss and the dynamic line loss of each line is equal to the real-time line loss. Therefore, dynamic loss analysis is an important tool in the aspects of power grid line loss detection, fault diagnosis and the like. The loss condition of the circuit can be more accurately known by monitoring and analyzing the dynamic loss of the circuit in real time, and potential problems can be timely found.
Further, the present application provides for performing dynamic loss analysis based on the plurality of line load status data sets, generating a plurality of dynamic line loss rates, including:
Screening and dimension-reducing the plurality of line load state data sets according to a preset load factor set to generate a plurality of dimension-reducing load data; analyzing the plurality of dimension reduction load data through a dynamic loss identification model, and outputting the plurality of dynamic line loss rates; the dynamic loss identification model comprises a plurality of single-factor identification channels and a factor weighting fusion channel, and the construction method of the dynamic loss identification model comprises the following steps of.
Preferably, in the process of performing dynamic loss analysis to generate a plurality of dynamic line loss rates, the system terminal first performs screening and dimension reduction on a plurality of line load state data sets. The purpose of this step is to pick out key data with high relevance to the dynamic line loss rate from a large amount of complex data, so as to evaluate the loss condition of the line more accurately. The screening and dimension reduction process is performed based on a preset load factor set. The preset load factor set is obtained by carrying out association identification on a plurality of initial load factor record sequences and line loss rate record sequences and judging the identification result, and is used for guiding the direction and range of data screening. By applying the load factors, the system terminal can identify and retain the load state data with obvious influence on the dynamic loss, and exclude the data with low association degree with the dynamic loss. After screening for dimension reduction, the system terminal generates a plurality of dimension reduction load data. The dimension reduction load data contains key information closely related to dynamic loss, and the data volume is more simplified compared with the original data set, so that the subsequent analysis and processing are facilitated. And then, the system terminal analyzes the plurality of dimension reduction load data by utilizing a pre-constructed dynamic loss identification model. The model comprises a plurality of single-factor identification channels and a factor weighted fusion channel, and can identify and fuse dynamic loss characteristics in load data. By inputting the dimension reduction load data, the model can output a plurality of corresponding dynamic line loss rates. The loss condition of the line can be known more accurately by monitoring and analyzing the dynamic line loss rate in real time, and early warning is carried out.
Collecting line loss detection logs according to the preset load factor set, wherein the line loss detection logs comprise a plurality of groups of line loss detection records, and any group of line loss detection records comprise a plurality of preset load factor record data and a plurality of line loss rate record data; training the plurality of single factor identification channels by using the plurality of groups of line loss detection records, and recording a plurality of convergence accuracy rates.
Preferably, the dynamic loss recognition model has important significance in the line loss detection and is used for accurately evaluating the loss condition of the line under different load states. This model consists of multiple single factor identification channels and a factor weighted fusion channel to ensure comprehensive analysis of line loss from multiple angles. In the model construction process, a system terminal firstly collects a line loss detection log from a historical line loss database according to a preset load factor set. The logs contain a plurality of groups of line loss detection records, and each group of records details a plurality of load factor data such as load size, current, voltage and the like at the time and corresponding line loss rate data. And then, respectively training each single factor identification channel in the dynamic loss identification model by using the obtained multiple groups of line loss detection records. Each single factor identification channel focuses on extracting information about the line loss rate from a particular load factor data. Specifically, the system terminal divides the acquired multiple groups of line loss detection records into a training set and a verification set, so that the data set is divided into representative and non-overlapping data sets. Then, for each single factor identified channel to be constructed, single load factor data corresponding to the channel is extracted as a feature from each set of line loss detection records in the training set. Then, a neural network structure is built for each single factor identification channel based on a multi-layer perceptron (MLP), a plurality of initial single factor identification channels are formed, and parameters such as weights, offsets and the like of the single factor identification channels are initialized by using random numbers. The system terminal then trains each initial single factor identification channel using the characteristic data and the corresponding line loss rate data. And the parameters of the initial single factor identification channel are iteratively updated through a back propagation algorithm and a gradient descent optimizer, so that the prediction loss of the initial single factor identification channel on the training set is gradually reduced. After each training period is finished, the system terminal uses a plurality of groups of line loss detection records in the verification set to evaluate the performance of the corresponding initial single factor identification channel. And calculates the loss function value and accuracy on the validation set. As training proceeds, the performance of the initial single-factor recognition channel on the validation set will gradually increase and tend to stabilize. At this time, the system terminal may determine the initial single-factor identification channel according to a set early-stop policy, where the early-stop policy is set based on the accuracy requirement, for example, on the verification set, five consecutive periods, and the performance of the initial single-factor identification channel is not improved. When the initial single factor identification channel meets the early-stop condition, the system terminal judges that the initial single factor identification channel is converged, and records the accuracy of each single factor identification channel in convergence, wherein the accuracy reflects the prediction capability of the channel on a specific load factor. And finally, outputting the converged multiple initial single-factor identification channels by the system terminal to generate multiple single-factor identification channels. Through this training process, each channel learns how to predict the corresponding line loss rate from its corresponding load factor data.
And training and constructing the factor weighted fusion channel by using the plurality of convergence accuracy rates, and connecting the plurality of single factor recognition channels with the factor weighted fusion channel to obtain the dynamic loss recognition model.
Preferably, training and construction of the factor weighted fusion channel is an important step in constructing the dynamic loss identification model. The purpose of this step is to effectively fuse the outputs of multiple single factor identification channels to obtain a more comprehensive and accurate prediction of dynamic loss. The system terminal firstly carries out partition in the factor weighted fusion channel, namely, the line loss rate storage address output by each single factor identification channel is divided. And then, the system terminal distributes weights for the storage addresses corresponding to each single-factor identification channel according to the obtained multiple convergence accuracy rates, and the storage addresses corresponding to the single-factor identification channels with higher convergence accuracy rates can obtain larger weights. And then, the system terminal sequentially inputs each group of line loss detection records into a plurality of trained single factor identification channels, and calculates the line loss rate of a plurality of preset load factors of each group of line loss detection records. And then, the system terminal inputs the outputs of the plurality of single factor identification channels into a factor weighting fusion channel for weighted summation, compares the weighted summation result with the sum of a plurality of line loss rate record data of each group of line loss detection records, and calculates the mean square error. Further, the system terminal iteratively updates the weights in the factor weighted fusion channel through a back propagation algorithm and a gradient descent optimizer, so that the error between the predicted line loss rate and the actual value is gradually reduced. After training, the system terminal connects the output ends of the single factor recognition channels with the input ends of the factor weighting fusion channels to form a complete dynamic loss recognition model. The output of each single factor identification channel is weighted according to the weight of the single factor identification channel in the factor weighting fusion channel, and then the final dynamic loss predicted value is obtained through fusion. Through the steps, a dynamic loss identification model which can comprehensively consider the influence of a plurality of load factors and has higher prediction accuracy can be constructed. This model can provide powerful support for line loss detection.
Further, the present application provides a method for screening and dimension-reducing the plurality of line load state data sets according to a preset load factor set, and generating a plurality of dimension-reduced load data, including:
Constructing an initial load factor set; and taking the initial load factor set as a variable, performing line loss detection record mining, and generating a plurality of initial load factor record sequences and line loss rate record sequences.
Alternatively, one key step in constructing the dynamic loss identification model is to determine and process the load factor set. The system terminal first builds an initial set of load factors. This set contains various factors that affect the grid line loss, such as load size, load type, voltage level, equipment aging, etc. These factors are critical for understanding and analyzing energy losses in the power grid. Then, the system terminal uses the initial load factor set as a variable to perform mining of the line loss detection record. The purpose of this step is to extract line loss information related to the load factor from a large amount of historical data. Through a data mining technique, a plurality of initial load factor record sequences and corresponding line loss rate record sequences can be generated. The sequence of load factor records describes specific values or states of the individual load factors at different times or under different conditions. The line loss rate recording sequence records the actual energy loss of the power grid under the conditions. There is a one-to-one correspondence between the two sequences, as changes in the load factor affect the energy loss of the grid. By generating these sequences, a more thorough analysis and understanding of the relationship between load factor and line loss can be made. The method is not only helpful for identifying key factors influencing line loss, but also can provide powerful data support for the subsequent construction of dynamic loss identification models.
Performing association identification on the plurality of initial load factor record sequences and the line loss rate record sequences to generate a plurality of association degrees; and extracting initial load factors with the association degree larger than or equal to a preset association degree according to the association degrees, and constructing the preset load factor set.
Optionally, after obtaining a plurality of initial load factor recording sequences and line loss rate recording sequences, the system terminal performs association identification on the sequences. The purpose of this step is to find out which load factors have a strong correlation with the line loss rate. Specifically, the system terminal randomly extracts an initial load factor record sequence from a plurality of initial load factor record sequences as a first initial load factor record sequence. And then, the system terminal performs time sequence alignment on the first initial load factor recording sequence and the line loss rate recording sequence, calculates the absolute difference value of the corresponding position, and extracts the maximum absolute difference value and the minimum absolute difference value. The system terminal then sets a resolution factor, which is used to adjust the sensitivity of the correlation factor to the absolute difference, typically set to 0.5 in practical applications. Then, the system terminal adds the product of the minimum absolute difference value and the resolution coefficient and the maximum absolute difference value, and calculates the absolute difference value of the corresponding position of the first initial load factor recording sequence and the line loss rate recording sequence. And adding the calculated absolute difference value to the product of the resolution coefficient and the maximum absolute difference value. Further, the system terminal calculates the ratio of the sum calculated for the first time and the sum calculated for the second time to obtain the association coefficient of the current position. This process is then repeated until the first initial load factor recording sequence and line loss rate recording sequence have all been calculated for the correlation coefficients. And then, the system terminal carries out average value calculation on all the calculated association coefficients to obtain a first association degree. Then, the above process is repeated, and the system terminal obtains a plurality of association degrees, each association degree corresponding to an initial load factor recording sequence. And finally, extracting an initial load factor with the association degree larger than or equal to the preset association degree by the system terminal according to the plurality of calculated association degrees. These load factors have a relatively close relationship with the line loss rate, so they have important reference values for predicting and analyzing the line loss rate. The system terminal then combines these extracted load factors to construct a set of preset load factors. The load factors in this set are factors that have a significant impact on the line loss rate, and they will serve as important input variables in the subsequent construction of dynamic loss identification models.
And generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to perform line loss abnormality alarm.
In one embodiment, after obtaining a plurality of dynamic line loss rates, a plurality of idle line loss rates, and a plurality of real-time line loss rates. The system terminal performs deviation identification of three line loss rates, and theoretically, the dynamic line loss rate plus the no-load line loss rate should be equal to or close to the real-time line loss rate. If the sum of the dynamic line loss rate and the idle line loss rate deviates too much from the real-time line loss rate, this represents that there is a managed line loss. The management line loss refers to electric energy loss caused by factors such as errors of metering equipment, errors of meter reading work, electricity stealing behavior, improper management and the like in the processes of power transmission, power transformation, power distribution and power supply. In order to timely discover and process the management line loss problems, the system terminal generates alarm information, carries out line loss abnormal alarm, and sends relevant information to operators in the form of alarm information so as to timely take measures, reduce management line loss and improve the operation efficiency of a power grid.
Further, the present application provides a method for generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates, for performing line loss anomaly alarm, including:
performing superposition calculation on the dynamic line loss rates and the idle line loss rates to generate a plurality of reference line loss rates; judging whether line loss rate deviation of the plurality of reference line loss rates and the plurality of real-time line loss rates meets a preset deviation threshold, if so, generating first alarm information to carry out line loss abnormal alarm.
Preferably, in order to determine whether the line loss is abnormal, the system terminal performs superposition calculation on a plurality of dynamic line loss rates and idle line loss rates, thereby generating a plurality of reference line loss rates. These reference line loss rates represent the expected line loss under theoretical conditions, i.e., without regulatory issues. The system terminal then compares these reference line loss rates to a plurality of real-time line loss rates measured in real-time to determine if there is a significant line loss rate deviation. If the deviation between the reference line loss rate and the real-time line loss rate does not exceed a preset deviation threshold, the system terminal generates first alarm information to carry out line loss abnormality alarm. Such alarm information indicates that no abnormality is found in the management at this time, that is, that the line loss is abnormal due to poor management. Therefore, the line loss abnormality is likely to be caused by a line operation abnormality, for example, an excessive operating voltage, an excessive current, or a physical cause such as an electric leakage. The alarm mechanism is beneficial to operation and maintenance personnel to rapidly locate and process abnormal line operation, eliminates potential safety hazards in time and ensures stable and efficient operation of the power grid.
Further, the present application provides a method for determining whether line loss rate deviations of the plurality of reference line loss rates and the plurality of real-time line loss rates meet a preset deviation threshold, including:
if the line loss rate deviation does not meet a preset deviation threshold value, positioning and managing an abnormal line; and positioning the management abnormal node of the management abnormal line, and generating second alarm information by the management abnormal node to perform distribution management abnormal alarm.
Alternatively, when the line loss rate deviation exceeds a preset deviation threshold, this represents that there is a management abnormality. To solve this problem, the system terminal first locates a line for which the line loss rate deviation exceeds a preset deviation threshold. And define these lines as management exception lines. Once the abnormal line is determined to be managed, the system terminal collects historical electric energy metering time sequence information of the electric energy metering nodes in the abnormal line. And then, carrying out metering cycle abnormality recognition based on the collected historical electric energy metering time sequence information, and generating second alarm information so as to remind an operator of paying attention to abnormality in power distribution management. The alarm information aims to help operators to quickly locate the problem and take effective measures to repair so as to restore the normal operation of the power grid and reduce the electric energy loss.
Further, the present application provides for performing management exception node positioning on the management exception line, including:
Acquiring a plurality of electric energy metering nodes in the management abnormal line; and collecting a plurality of historical electric energy metering time sequence information of the plurality of electric energy metering nodes, wherein the deadline of any historical electric energy metering time sequence information is the current moment.
Optionally, when management anomaly lines are detected, the system terminal first obtains a plurality of power metering nodes on these anomaly lines for further analysis and localization of the root cause of the problem. The electric energy metering nodes are directly connected with the user side and are responsible for monitoring and recording the electric energy use condition of the user in real time. Subsequently, a plurality of historical power metering timing information for the metering nodes is collected. This information details the power usage data of each metering node from a point in time in the past until the present moment. These timing data are critical to analyzing power loss and anomalies because they can reflect the user's power usage behavior over various periods of time. Through the collection of the historical electric energy metering time sequence information, the system terminal can more accurately know which users or which areas have abnormal electricity consumption conditions, and then possible management problems such as electricity stealing behaviors, equipment faults or human errors are located.
Performing measurement period abnormality recognition on the historical electric energy measurement time sequence information to obtain period abnormality nodes; and generating the second alarm information by the periodic abnormal node.
Optionally, after the abnormal line is electrically discovered and managed, in order to further analyze the specific cause of the problem, the system terminal performs deep abnormal recognition of the metering cycle on the historical electric energy metering time sequence information of the plurality of electric energy metering nodes. Because the metering node is directly connected with the user, the electricity consumption of the user usually shows a certain regular change in a period of time, such as a daily electricity consumption peak period, a weekend and a difference of daily electricity consumption of work. And the system terminal detects whether abnormal change of the electricity consumption occurs in a regular period or not by comparing and analyzing the historical electricity metering time sequence information. If the electricity consumption of a certain metering node has obvious deviation or abnormal fluctuation in a regular period, the system terminal judges that the metering node has period abnormality and marks the metering node as a period abnormality node. Once the periodic abnormal nodes are identified, the system terminal generates second alarm information according to the abnormal nodes. The alarm information can clearly indicate which metering nodes have cycle abnormality, and comprises detailed information such as the time period of occurrence of the abnormality, the concrete expression of the abnormality and the like. After receiving the alarm information, operators can quickly locate a specific abnormal metering node, and further check and maintain metering equipment so as to ensure normal operation and accurate metering of the power grid.
In the above, a smart line loss detection alarm method for a power distribution network according to an embodiment of the present invention is described in detail with reference to fig. 1. Next, an intelligent line loss detection alarm device for a power distribution network according to an embodiment of the present invention will be described with reference to fig. 2.
According to the intelligent line loss detection alarm device for the power distribution network, which is disclosed by the embodiment of the invention, the technical problems that the early warning cannot be performed pertinently and the assistance of the subsequent line loss abnormal cause investigation is low due to various reasons of line loss in a line loss analysis mode based on threshold direct judgment are solved, and the effects of improving the line loss detection accuracy and enabling the operation management of the power distribution network to be more efficient and accurate are achieved. An intelligent line loss detection alarm device for a power distribution network comprises: the system comprises an empty load loss identification module 1, a data analysis module 2, an electric energy loss identification module 3, a variable line loss rate identification module 4, a dynamic loss analysis module 5 and a line loss abnormality alarm module 6.
No-load loss identification module 1: the no-load loss identification module 1 is used for acquiring a plurality of line design information of a plurality of distribution lines of a target distribution network, carrying out line no-load loss identification according to the plurality of line design information, and generating a plurality of no-load line loss rates;
Data analysis module 2: the data analysis module 2 is used for receiving a preset power distribution plan of the target power distribution network in a preset time zone and collecting electricity selling information in the preset time zone;
the power loss identification module 3: the electric energy loss identification module 3 is used for carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates;
Variable line loss rate identification module 4: the variable line loss rate identification module 4 is configured to identify a variable line loss rate according to the real-time line loss rates and the idle line loss rates, and collect a plurality of line load state data sets of the distribution lines if the variable line loss rate is greater than a preset variable line loss rate;
dynamic loss analysis module 5: the dynamic loss analysis module 5 is configured to perform dynamic loss analysis based on the multiple line load state data sets, and generate multiple dynamic line loss rates;
Line loss abnormality alarm module 6: the line loss abnormality alarming module 6 is configured to combine the plurality of dynamic line loss rates, the plurality of idle line loss rates, and the plurality of real-time line loss rates to generate alarming information to perform line loss abnormality alarming.
Further, the no-load loss identification module 1 further includes:
Extracting first circuit design information of a first distribution circuit according to the plurality of circuit design information, wherein the first circuit design information comprises the specification and the number of power grid elements in the first distribution circuit; carrying out no-load loss accumulation calculation on the power grid element according to the first circuit design information to generate a first no-load loss; and combining the rated distribution power of the first distribution line and the first no-load loss, calculating and obtaining a first no-load line loss rate, and adding the first no-load line loss rate into the multiple no-load line loss rates.
Further, the dynamic loss analysis module 5 further includes:
Screening and dimension-reducing the plurality of line load state data sets according to a preset load factor set to generate a plurality of dimension-reducing load data; analyzing the plurality of dimension reduction load data through a dynamic loss identification model, and outputting the plurality of dynamic line loss rates; the dynamic loss identification model comprises a plurality of single-factor identification channels and a factor weighting fusion channel, and the construction method of the dynamic loss identification model comprises the following steps: collecting line loss detection logs according to the preset load factor set, wherein the line loss detection logs comprise a plurality of groups of line loss detection records, and any group of line loss detection records comprise a plurality of preset load factor record data and a plurality of line loss rate record data; training the plurality of single factor identification channels by utilizing the plurality of groups of line loss detection records, and recording a plurality of convergence accuracy rates; and training and constructing the factor weighted fusion channel by using the plurality of convergence accuracy rates, and connecting the plurality of single factor recognition channels with the factor weighted fusion channel to obtain the dynamic loss recognition model.
Further, the dynamic loss analysis module 5 further includes:
Constructing an initial load factor set; taking the initial load factor set as a variable, performing line loss detection record mining to generate a plurality of initial load factor record sequences and line loss rate record sequences; performing association identification on the plurality of initial load factor record sequences and the line loss rate record sequences to generate a plurality of association degrees; and extracting initial load factors with the association degree larger than or equal to a preset association degree according to the association degrees, and constructing the preset load factor set.
Further, the line loss abnormality alarm module 6 further includes:
performing superposition calculation on the dynamic line loss rates and the idle line loss rates to generate a plurality of reference line loss rates; judging whether line loss rate deviation of the plurality of reference line loss rates and the plurality of real-time line loss rates meets a preset deviation threshold, if so, generating first alarm information to carry out line loss abnormal alarm.
Further, the line loss abnormality alarm module 6 further includes:
if the line loss rate deviation does not meet a preset deviation threshold value, positioning and managing an abnormal line; and positioning the management abnormal node of the management abnormal line, and generating second alarm information by the management abnormal node to perform distribution management abnormal alarm.
Further, the line loss abnormality alarm module 6 further includes:
Acquiring a plurality of electric energy metering nodes in the management abnormal line; collecting a plurality of historical electric energy metering time sequence information of the plurality of electric energy metering nodes, wherein the deadline of any historical electric energy metering time sequence information is the current moment; performing measurement period abnormality recognition on the historical electric energy measurement time sequence information to obtain period abnormality nodes; and generating the second alarm information by the periodic abnormal node.
The intelligent line loss detection and alarm device for the power distribution network provided by the embodiment of the invention can execute the intelligent line loss detection and alarm method for the power distribution network provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Although the present application makes various references to certain modules in an apparatus according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or a server, including units and modules that are merely divided by functional logic, but are not limited to the above-described division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (8)
1. An intelligent line loss detection and alarm method for a power distribution network is characterized by comprising the following steps:
Acquiring a plurality of line design information of a plurality of distribution lines of a target distribution network, and carrying out line no-load loss identification according to the plurality of line design information to generate a plurality of no-load line loss rates;
receiving a preset power distribution plan of the target power distribution network in a preset time zone, and collecting electricity selling information in the preset time zone;
Carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates;
Variable line loss rate identification is carried out according to the real-time line loss rates and the idle line loss rates, and if the variable line loss rate is larger than a preset variable line loss rate, a plurality of line load state data sets of the distribution lines are collected;
performing dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates;
and generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to perform line loss abnormality alarm.
2. The method of claim 1, wherein performing line no-load loss identification based on the plurality of line design information to generate a plurality of no-load line loss rates comprises:
Extracting first circuit design information of a first distribution circuit according to the plurality of circuit design information, wherein the first circuit design information comprises the specification and the number of power grid elements in the first distribution circuit;
Carrying out no-load loss accumulation calculation on the power grid element according to the first circuit design information to generate a first no-load loss;
And combining the rated distribution power of the first distribution line and the first no-load loss, calculating and obtaining a first no-load line loss rate, and adding the first no-load line loss rate into the multiple no-load line loss rates.
3. The method of claim 1, wherein generating alert information for line loss anomaly alerts in combination with the plurality of dynamic line loss rates, the plurality of idle line loss rates, and the plurality of real-time line loss rates, comprises:
Performing superposition calculation on the dynamic line loss rates and the idle line loss rates to generate a plurality of reference line loss rates;
Judging whether line loss rate deviation of the plurality of reference line loss rates and the plurality of real-time line loss rates meets a preset deviation threshold, if so, generating first alarm information to carry out line loss abnormal alarm.
4. The method of claim 3, wherein determining whether a line loss rate deviation of the plurality of reference line loss rates from the plurality of real-time line loss rates meets a preset deviation threshold further comprises:
if the line loss rate deviation does not meet a preset deviation threshold value, positioning and managing an abnormal line;
And positioning the management abnormal node of the management abnormal line, and generating second alarm information by the management abnormal node to perform distribution management abnormal alarm.
5. The method of claim 4, wherein managing the anomalous node location for the managing anomalous line comprises:
Acquiring a plurality of electric energy metering nodes in the management abnormal line;
Collecting a plurality of historical electric energy metering time sequence information of the plurality of electric energy metering nodes, wherein the deadline of any historical electric energy metering time sequence information is the current moment;
Performing measurement period abnormality recognition on the historical electric energy measurement time sequence information to obtain period abnormality nodes;
and generating the second alarm information by the periodic abnormal node.
6. The method of claim 1, wherein performing dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates comprises:
Screening and dimension-reducing the plurality of line load state data sets according to a preset load factor set to generate a plurality of dimension-reducing load data;
Analyzing the plurality of dimension reduction load data through a dynamic loss identification model, and outputting the plurality of dynamic line loss rates;
The dynamic loss identification model comprises a plurality of single-factor identification channels and a factor weighting fusion channel, and the construction method of the dynamic loss identification model comprises the following steps:
collecting line loss detection logs according to the preset load factor set, wherein the line loss detection logs comprise a plurality of groups of line loss detection records, and any group of line loss detection records comprise a plurality of preset load factor record data and a plurality of line loss rate record data;
Training the plurality of single factor identification channels by utilizing the plurality of groups of line loss detection records, and recording a plurality of convergence accuracy rates;
and training and constructing the factor weighted fusion channel by using the plurality of convergence accuracy rates, and connecting the plurality of single factor recognition channels with the factor weighted fusion channel to obtain the dynamic loss recognition model.
7. The method of claim 6, wherein screening and dimension-reducing the plurality of line load state data sets according to a set of preset load factors to generate a plurality of dimension-reduced load data comprises:
Constructing an initial load factor set;
taking the initial load factor set as a variable, performing line loss detection record mining to generate a plurality of initial load factor record sequences and line loss rate record sequences;
performing association identification on the plurality of initial load factor record sequences and the line loss rate record sequences to generate a plurality of association degrees;
and extracting initial load factors with the association degree larger than or equal to a preset association degree according to the association degrees, and constructing the preset load factor set.
8. An intelligent line loss detection and alarm device for a power distribution network, which is characterized in that the device is used for implementing the intelligent line loss detection and alarm method for the power distribution network according to any one of claims 1-7, and comprises the following steps:
No-load loss identification module: acquiring a plurality of line design information of a plurality of distribution lines of a target distribution network, and carrying out line no-load loss identification according to the plurality of line design information to generate a plurality of no-load line loss rates;
and a data analysis module: receiving a preset power distribution plan of the target power distribution network in a preset time zone, and collecting electricity selling information in the preset time zone;
The electric energy loss identification module: carrying out electric energy loss identification on the plurality of distribution lines according to the electricity selling information and the preset distribution plan, and generating a plurality of real-time line loss rates;
Variable line loss rate identification module: variable line loss rate identification is carried out according to the real-time line loss rates and the idle line loss rates, and if the variable line loss rate is larger than a preset variable line loss rate, a plurality of line load state data sets of the distribution lines are collected;
Dynamic loss analysis module: performing dynamic loss analysis based on the plurality of line load state data sets to generate a plurality of dynamic line loss rates;
Line loss abnormality alarm module: and generating alarm information by combining the dynamic line loss rates, the idle line loss rates and the real-time line loss rates to perform line loss abnormality alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410910456.5A CN118473097B (en) | 2024-07-09 | 2024-07-09 | Intelligent line loss detection and alarm method and device for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410910456.5A CN118473097B (en) | 2024-07-09 | 2024-07-09 | Intelligent line loss detection and alarm method and device for power distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118473097A CN118473097A (en) | 2024-08-09 |
| CN118473097B true CN118473097B (en) | 2024-09-06 |
Family
ID=92166805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410910456.5A Active CN118473097B (en) | 2024-07-09 | 2024-07-09 | Intelligent line loss detection and alarm method and device for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118473097B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105958654A (en) * | 2016-07-13 | 2016-09-21 | 广东电网有限责任公司 | Real-time monitoring method and system for line loss rate |
| CN107832855A (en) * | 2017-09-14 | 2018-03-23 | 北京中恒博瑞数字电力科技有限公司 | Line loss multi-source diagnostic method and system based on correlation analysis |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120316688A1 (en) * | 2011-06-08 | 2012-12-13 | Alstom Grid | Coordinating energy management systems and intelligent electrical distribution grid control systems |
| US9799083B2 (en) * | 2014-10-28 | 2017-10-24 | Oracle International Corporation | Correlating consumption and voltage data to identify line loss in an electric grid |
| JP7134236B2 (en) * | 2017-12-28 | 2022-09-09 | 北京小米移動軟件有限公司 | Method and apparatus for determining path loss |
| CN110362894B (en) * | 2019-06-28 | 2023-04-18 | 贵州电网有限责任公司 | Distribution line and transformer comprehensive loss reduction and energy saving calculation analysis method and system |
| CN111985794B (en) * | 2020-07-31 | 2023-09-29 | 广东卓维网络有限公司 | Line loss management method based on marketing and distribution information integration platform |
| CN114297920A (en) * | 2021-12-22 | 2022-04-08 | 国网辽宁省电力有限公司营销服务中心 | Line loss calculation method based on data prediction filling and global dynamic model |
| CN115409317A (en) * | 2022-07-11 | 2022-11-29 | 国网湖南省电力有限公司 | Transformer area line loss detection method and device based on feature selection and machine learning |
| CN115622236A (en) * | 2022-09-30 | 2023-01-17 | 国网浙江省电力有限公司宁波供电公司 | Power distribution network line loss management micro application method, device and medium |
| CN116298675B (en) * | 2023-02-15 | 2023-09-22 | 东北电力大学 | Intelligent algorithm-based power distribution network line loss anomaly detection method and system |
| CN115982608A (en) * | 2023-02-16 | 2023-04-18 | 国网上海市电力公司 | Line loss abnormity judgment method based on line loss dynamic analysis |
| CN117708707B (en) * | 2024-02-06 | 2024-05-17 | 国网安徽省电力有限公司营销服务中心 | Intelligent early warning method and system for abnormal line loss rate of big data lower station area |
| CN118095896A (en) * | 2024-03-26 | 2024-05-28 | 国网浙江省电力有限公司嘉兴供电公司 | Power system line loss assessment method based on big data analysis |
-
2024
- 2024-07-09 CN CN202410910456.5A patent/CN118473097B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105958654A (en) * | 2016-07-13 | 2016-09-21 | 广东电网有限责任公司 | Real-time monitoring method and system for line loss rate |
| CN107832855A (en) * | 2017-09-14 | 2018-03-23 | 北京中恒博瑞数字电力科技有限公司 | Line loss multi-source diagnostic method and system based on correlation analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118473097A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103245881B (en) | Power distribution network fault analyzing method and device based on tidal current distribution characteristics | |
| Kang et al. | Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters | |
| CN112131441B (en) | Method and system for rapidly identifying abnormal electricity consumption behavior | |
| CN105573997A (en) | Method and device for determining electric larceny suspect user | |
| CN117554821A (en) | Energy storage battery on-line monitoring management method and system based on deep learning network | |
| CN106875124B (en) | State evaluation method, device and system for electric energy metering device | |
| CN113554361B (en) | Comprehensive energy system data processing and calculating method and processing system | |
| CN112001644A (en) | Power distribution network operation reliability detection method, device, terminal and storage medium | |
| CN117277435A (en) | Health assessment method, system and device for photovoltaic inverter | |
| CN112101673A (en) | Power grid development trend prediction method and system based on hidden Markov model | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN116840767A (en) | Electric energy metering device overall error assessment method and device, storage medium and terminal | |
| CN111080484A (en) | Method and device for monitoring abnormal data of power distribution network | |
| CN117856245A (en) | Grid management-based method, device and storage medium for analyzing line loss of transformer area | |
| CN115146715B (en) | Method, device, equipment and storage medium for diagnosing potential safety hazard of electricity | |
| CN108845285A (en) | Electric energy metering device detection method and system | |
| CN117148048A (en) | Power distribution network fault prediction method and system based on digital twin technology | |
| CN118473097B (en) | Intelligent line loss detection and alarm method and device for power distribution network | |
| CN117235441A (en) | Cable operation state evaluation method, device, equipment, medium and program product | |
| Zhong et al. | Rapid Identification Method for the Sudden Change of Operating Errors in Smart Electricity Meters | |
| Yang et al. | Smart Meter Fault Diagnosis based on Directional Gradient KNN | |
| Li et al. | Research and application of electricity anti-stealing system based on neural network | |
| CN118157325B (en) | Real-time monitoring method and system for new energy power | |
| Guo et al. | A Reliability Evaluation Model for Smart Meters Based on Survival Analysis Theory | |
| Gómez et al. | Analysis of Asset Management Models for a Transformer Fleet in the National Laboratory of Smart Grids (LAB+ i) |
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 |