Power data processing method, device and equipment for simulation and storage medium

Abstract

The application discloses a power data processing method and device for simulation, equipment and a storage medium. The method comprises the following steps: collecting power data from different data sources, classifying the power data, obtaining a plurality of power data sets of different data types, coarsely screening each power data set to divide each power data set into a normal data set and an abnormal data set, finely screening each normal data set to screen abnormal data from the normal data set and add the abnormal data to an abnormal data set of the same data type as the normal data set, correcting the power data in each abnormal data set, and generating a simulation data set based on the corrected abnormal data set. The simulation data set is used for simulation calculation of a power distribution network, reduces the labor intensity of manual correction of power data, can efficiently process problems such as data loss, data inaccuracy and data redundancy, and improves the authenticity and reliability of simulation data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a power data processing method, device and equipment for simulation and a storage medium. BACKGROUND

[0002] In simulation calculation of a power distribution network, a large amount of power data from different systems is needed. When power data is collected by a power distribution network related system, due to communication blockage, failure of a collection device, user maintenance and other problems, there are often missing or incorrect power data, and if the original power data is directly used without processing, the simulation calculation cannot converge, and power supply quality analysis fails. SUMMARY

[0003] The present application provides a power data processing method, device and equipment for simulation to solve the problem that power data for simulation comes from different power systems and causes simulation failure due to missing or incorrect data.

[0004] According to an aspect of the present application, a power data processing method for simulation is provided, and the method comprises:

[0005] Collecting power data from different data sources, and classifying the power data to obtain a plurality of power data sets of different data types;

[0006] Coarsely screening each power data set to divide each power data set into a normal data set and an abnormal data set;

[0007] Fine screening each normal data set to screen out abnormal data from the normal data set and add the abnormal data to an abnormal data set of the same data type as the normal data set;

[0008] Respectively correcting the power data in each abnormal data set, and generating a simulation data set based on the corrected abnormal data set, wherein the simulation data set is used for simulation calculation of a power distribution network.

[0009] According to an aspect of the present application, a power data processing device for simulation is provided, and the device comprises:

[0010] A power data set determination module configured to collect power data from different data sources, and classify the power data to obtain a plurality of power data sets of different data types;

[0011] A coarse screening module configured to coarsely screen each power data set to divide each power data set into a normal data set and an abnormal data set;

[0012] The fine screening module is configured to perform fine screening on each normal data set to screen out abnormal data from the normal data set and add the abnormal data to an abnormal data set of the same data type as the normal data set.

[0013] The correction module is configured to correct power data in each abnormal data set respectively and generate a simulation data set based on the corrected abnormal data set, where the simulation data set is used for simulation calculation of the power distribution network.

[0014] According to another aspect of the present application, an electronic device is provided, which comprises:

[0015] at least one processor; and

[0016] a memory connected to the at least one processor in communication; wherein

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the power data processing method for simulation according to any one of the embodiments of the present application.

[0018] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to perform the power data processing method for simulation according to any one of the embodiments of the present application when executed by the processor.

[0019] The technical scheme of the embodiments of the present application provides a power data processing method for simulation, which comprises: collecting power data from different data sources and classifying the power data to obtain a plurality of power data sets of different data types; performing coarse screening on each power data set to divide the power data set into a normal data set and an abnormal data set; screening out abnormal data that has no correlation and that violates electrical principles; performing fine screening on each normal data set to screen out abnormal data from the normal data set and add the abnormal data to an abnormal data set of the same data type as the normal data set; determining abnormal data that has electrical logical errors in the normal data set; correcting power data in each abnormal data set respectively; and generating a simulation data set based on the corrected abnormal data set, where the simulation data set is used for simulation calculation of the power distribution network. The power data is double-filtered through coarse screening and fine screening, and the abnormal data is finally corrected to obtain a data set that meets the requirements of power distribution network simulation, which can reduce the workload of manual correction of power data from different data sources, efficiently handle problems such as data loss, data misalignment and data redundancy, and improve the authenticity and reliability of simulation data.

[0020] It is to be understood that the details set forth in the description contained herein do not limit the scope of the embodiments of the application. Other embodiments of the application will be readily apparent to one of ordinary skill in the art from the description herein, including the working examples. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0022] Figure 1 is a flow chart of a power data processing method for simulation according to the first embodiment of the present application;

[0023] Figure 2 is a processing flow schematic diagram of power data for simulation according to the first embodiment of the present application;

[0024] Figure 3 is a structural schematic diagram of a power data processing device for simulation according to the second embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of an electronic device for implementing the power data processing method for simulation according to the present application. DETAILED DESCRIPTION

[0026] In order to make the technical personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort should belong to the scope of protection of the present application.

[0027] It is to be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described drawings are intended to distinguish similar objects and not necessarily to describe a particular sequential or chronological order. It is to be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present application described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusions, for example, processes, methods, systems, products, or devices that comprise a list of steps or units are not necessarily limited to those steps or units that are clearly listed, but can include other steps or units that are not clearly listed or inherent to such processes, methods, products, or devices.

[0028] Embodiment one

[0029] Figure 1 A flow chart of a power data processing method for simulation is provided for the first embodiment of the present application.

[0030] In the simulation calculation of 10kV distribution network, the main simulation objects are 10kV lines and distribution transformers, and the data sources are numerous and have different structures. The data source systems involved include metering automation systems, dispatching automation systems (including distribution automation), power grid GIS systems, safety production management systems, voltage monitoring systems, etc., and the data involved include user numbers, user names, metering methods, property rights, line and distribution transformer names, line and distribution transformer parameters, device numbers, topological connection relationships, geographic coordinates, real-time electrical quantities (voltage, current, active power, reactive power, power factor, etc.) and non-electrical quantities (temperature and humidity, weather, etc.), as well as patrol conditions, maintenance conditions, power outage events, complaint events, etc.

[0031] The main data problems existing in each power system are as follows:

[0032] 1) Data missing: including but not limited to, missing of user numbers, distribution transformer names, device numbers, etc., resulting in inability to associate and match data between different systems; missing of line or distribution transformer parameters, resulting in inaccurate impedance calculation results; missing of electrical quantity data such as voltage, current, phase, etc., resulting in inability of simulation calculation at missing time points to converge, etc.

[0033] 2) Data misalignment: including but not limited to, different data granularities, such as 15 minutes / point (96 points / day) of metering data in the metering automation system and 5 minutes / point (288 points / day) of measurement data of switches in the distribution automation system; mismatch between voltage data and corresponding voltage levels; occurrence of excessively high or low data of a phase voltage (difference exceeding 30% of the rated value, without obvious change of other phases); occurrence of abnormal overload of a distribution transformer (load rate reaching 200% or more); negative values of single-phase or multi-phase data, etc.

[0034] 3) Data redundancy: including but not limited to, multiple sets of metering data for the same transformer, mainly from the settings of the main meter, auxiliary meter and reference meter in the metering automation system; one user number corresponds to multiple transformer names; one transformer name corresponds to multiple user numbers, which all need to be manually judged;

[0035] 4) System problem: including but not limited to, part of the data system is not unified, such as non-integral time (15 minutes or 1 hour), non-numeric type, unit error, no variable ratio conversion, etc.

[0036] In view of the above data quality problems, the power data processing method for simulation provided in the embodiment can exclude abnormal data or replace it with an estimated value, automatically complete the missing data, replace manual judgment and identification, and as much as possible reflect the system operation, so that the data analysis can be more effective when the power simulation is performed.

[0037] The method can be performed by a power data processing device for simulation, which can be realized in the form of hardware and / or software.

[0038] As shown in the method, the method comprises the following steps: Figure 1

[0039] S110, collect power data from different data sources, and classify the power data to obtain a plurality of power data sets of different data types.

[0040] When collecting power data from different data sources, the collection can be performed according to a specified time length, for example, in units of months or in units of quarters.

[0041] After collecting the power data from different data sources, the power data can be uploaded to a database for storage. In the database, a plurality of data sets can be obtained by classifying different data sources, such as a metering automation system data set, a dispatching automation system data set (including power distribution automation), and a power grid geographic information system data set.

[0042] ​In each different data source dataset, the data can be classified according to data types to obtain power data sets of different data types. The data types can be identity information type, static parameter type, dynamic operation type, and event type. For example, in the metering automation system dataset, the user name, user number, metering point number, property ownership (public or private), load nature (class I, class II, or class III load), and the like belong to identity information type data. The CT transformation ratio (ratio between the currents on both sides of the current transformer), PT transformation ratio (ratio between the voltages on both sides of the voltage transformer), capacity, and the like belong to static parameter type data. The voltage, current, active power, reactive power, power factor, and the like of the distribution transformer summary table belong to dynamic operation type data. In a specific implementation, the embodiment aims to correct identity information type, static parameter type, and dynamic operation type data, and event type data is only used as auxiliary reference.

[0043] S120, respectively, each power data set is coarsely screened to divide each power data set into a normal data set and an abnormal data set.

[0044] For the power data in each power data set, coarse screening can be performed to quickly determine data with obvious abnormalities. For example, data with obvious abnormalities can refer to missing data, unit errors, and the like. Each power data set is divided into a corresponding normal data set and an abnormal data set to store the normal data in the power data set into the corresponding normal data set and store the abnormal data in the power data set into the corresponding abnormal data set. It should be noted that since this step only completes coarse screening, the normal data in the normal data set screened out does not represent all data that can be used for final simulation calculation, and further screening is required to ensure the effectiveness of the data used.

[0045] In an embodiment, S120 includes the following steps:

[0046] S120-1, for each power data set, determining whether the power data in each power data set has a correlation;

[0047] S120-2, determining the power data determined as not having a correlation as abnormal data, and storing the abnormal data into an abnormal data set corresponding to the current power data set;

[0048] S120-3, determining the power data determined as having a correlation as normal data, and storing the normal data into a normal data set corresponding to the current power data set.

[0049] In the collection of power data from different data sources for simulation, since at least one key field must be used to associate the power data from different systems to indicate the association between the data when simulating the input power data, all the power data should have a specific association. In a specific implementation, the association of the power data of different data sources can be determined according to identity information type data. For example, the identity information type data can include a user number, and the power data sets are associated through the user number. The power data without an association is determined as abnormal data, and the absence of an association can include the following cases: the key field indicating the association is missing; the key field indicating the association is inconsistent with the pre-determined key field.

[0050] In an embodiment, after step S120-3, the following steps are further included:

[0051] The power data in the normal data set is screened by using a pre-set screening condition, wherein the screening condition is set based on electrical principles for different data type power data sets;

[0052] The power data that does not meet the screening condition is determined as abnormal data, and the abnormal data is stored in an abnormal data set of the same data type as the current normal data set.

[0053] After determining that the power data in the normal data set has an association, the screening condition can be set based on electrical principles for different data type power data sets. The electrical principles can be the format requirement of the power data, the normal value range, etc. In a specific implementation, the screening condition can be set according to different power data in the power data set. For example, the current normal data set contains real-time electrical quantities. When the real-time electrical quantities appear as null, single-phase voltage is higher than 2p.u. (voltage limit), load rate is greater than 200%, etc., the current real-time electrical quantities can be determined as abnormal data of the power data set, and the abnormal data is stored in an abnormal data set of the same data type as the current normal data set.

[0054] S130, each normal data set is finely screened to screen out abnormal data from the normal data set and add it to an abnormal data set of the same data type as the normal data set.

[0055] After rough screening of each power data set, the power data in each normal data set is in a correlation relationship, and there is no obvious situation that does not conform to the electrical principle. At this time, part of the power data in the normal data set may exist within the normal range, but there may be a logical error. This logical error can be screened out by cross verification of power data from different data sources. The abnormal data screened out from the current normal data set can be added to the abnormal data set of the same data type as the normal data set, so as to realize fine screening of the normal data set.

[0056] In an embodiment, the fine screening of each normal data set in S130 includes the following steps:

[0057] S130-1, obtaining the influence relationship and influence logic between each power data;

[0058] S130-2, determining the power data that has an influence relationship with the power data in each normal data set;

[0059] S130-3, based on the influence logic, using the power data that has an influence relationship to verify the power data in each normal data set, and determining the power data that fails the verification as abnormal data.

[0060] The power data representing different information has different influence relationships and influence logics. When verifying whether the power data in the normal data set has a logical error, the power data indicating other information that will affect the power data can be retrieved first according to the pre-configured influence relationship, and the verification can be performed according to the influence logic.

[0061] In specific implementation, in order to ensure the reliability of verification, when retrieving the power data indicating other information that will affect the power data, the redundancy of the power data indicating other information can also be confirmed, that is, the redundancy of the data is confirmed. If the redundancy of a certain power data reaches a certain specified threshold in different data sources, it means that the power data indicating the information is reliable and can be used for data verification. In specific calculation of redundancy, the power data can be arranged according to the time axis, arranged according to the time axis d and the power data b, and the following formula is used:

[0062] R = 1-(Q / bd)

[0063] Wherein, R is the redundancy, Q is the cumulative sum of the number of adjacent attribute value changes, b is the power data, and d is the time axis.

[0064] Exemplarily, when the redundancy meets the condition, when verifying the active power and reactive power values of the distribution transformer total table at a certain time point, if the active power and reactive power values of the distribution transformer total table at the time point are negative numbers, the installation records of the low-voltage distributed power (low-voltage photovoltaic) which has an influence relationship with the distribution transformer in the data set of the metering automation system and the weather conditions of the place where the distribution transformer is located at the time point in the data set of the dispatching automation system are called to verify, and if there is no installation record or the weather is not sunny, it is proved that the active power and reactive power values of the distribution transformer total table at the time point are abnormal data values. In another example, when there is one user number corresponding to multiple distribution transformers, the correspondence between the user number and the multiple distribution transformers is verified, and the total installation capacity of the user in the data set of the metering automation system and the capacities of the distribution transformers in the data set of the power grid GIS system are called to verify, and if the total installation capacity of the user is inconsistent with the sum of the capacities of the multiple distribution transformers, the data of the total installation capacity of the user and the capacities of the multiple distribution transformers are determined as abnormal data. For example, when there is one user number corresponding to multiple main table metering point numbers, the topological connection relationship in the data set of the power grid GIS system is called to verify, and if the user does not exist double power connection, the multiple main table metering point numbers are determined as abnormal data.

[0065] In S140, the power data in each abnormal data set is corrected, and a simulation data set is generated based on the corrected abnormal data set, and the simulation data set is used for simulation calculation of the power distribution network.

[0066] After the rough screening and the fine screening of the power data from different data sources, multiple abnormal data sets of different data types are obtained, and the power data in each abnormal data set can be corrected so that complete and correct simulation data sets can be used in simulation. When correcting the abnormal data, different correction strategies can be formulated according to the characteristics of different abnormal data, so that the correction result is more scientific and accurate.

[0067] In an implementation, the data types include: static parameter type and identity information type.

[0068] In S140, the power data in each abnormal data set is corrected, including the following steps:

[0069] The correction strategy is determined according to the data type of each abnormal data set, and when the data type is the static parameter type or the identity information type, the correction strategy is the same.

[0070] The power data in each abnormal data set is corrected by using the correction strategy.

[0071] Different correction strategies can be determined according to different data types of each set of abnormal data. For power data of the data types of identity information and static parameters, since the power data of the two data types both have certain semantic and logical association, when determining the correction strategy, the abnormal data can be calculated according to the Bayesian algorithm, the abnormal data is replaced by the estimated value, the possible value of the missing data is obtained, and the probability of the possible value of the abnormal data is calculated. For example, for a plurality of abnormal data in which the user number and the distribution transformer name cannot be corresponded on a line, the corresponding relationship between the user number and the distribution transformer name can be inferred according to the missing probability of the metering data corresponding to each user number when the line section where the distribution transformer is located has a power failure event, and the correction of the data is completed.

[0072] When the abnormal data is corrected and it is determined whether a data y i can replace the abnormal data, the Bayesian algorithm can be used, and the formula is as follows:

[0073]

[0074] Wherein, p(y j |x) represents the posterior probability, p(x|y j ) represents the likelihood function, p(y j ) represents the prior probability, x represents normal data, y j represents the data to be determined, j represents the index subscript of the data to be determined, and n represents the number of data to be determined.

[0075] The probability calculation formula of the possible value p of the abnormal data is:

[0076]

[0077] Wherein, m is the total amount of all collected power data, K(p) is the number of times that the possible value p of the abnormal data appears at the same abnormal position in each set of abnormal power data, and P(p) is the probability of the possible value p of the abnormal data.

[0078] The data type also includes dynamic running class. For the continuous change property of the dynamic running class data, the corresponding correction strategy can be that the time granularity of the dynamic running class data is unified, for example, unified to 96 points / day, then the data unit and system are unified according to the electrical basic rules, and then the correction is performed by using the supporting estimation algorithm, the historical matching method, the least square method and the like.

[0079] For example, the least square method can be used to correct the abnormal data of active and reactive power. The correction process is as follows: the remaining active and reactive power can be calculated according to the total active and reactive power data of the 10kV line and the known active and reactive power data of the nodes (referred to as real measurement points, i.e. the corresponding active and reactive power data in the normal data set), and then the remaining active and reactive power is proportionally distributed to each unknown active and reactive power node (referred to as pseudo measurement points, i.e. data that can be used to replace abnormal data), and then the real measurement points and pseudo measurement points are used together to correct the data error by the least square method, and the group with the minimum error is selected as the corrected data.

[0080] In an embodiment, the simulation data set is generated based on the corrected abnormal data set in S140, including the following steps:

[0081] The corrected abnormal data set is merged with the normal data set of the same data type, and the simulation data set is generated based on the merged result.

[0082] After the correction of the abnormal data is completed, the corrected abnormal data set can be merged with the normal data set of the same data type, and the merged result is obtained. The merged normal data set of all data types is obtained, and the normal data set of all data types is merged into the simulation data set.

[0083] In another implementation, the corrected abnormal data can also be stored in the normal data set of the same data type after each correction, until there is no abnormal data in the abnormal data set, and then the normal data set of all data types is merged into the simulation data set.

[0084] In an embodiment, before merging the corrected abnormal data set with the normal data set of the same data type, the following steps are further included:

[0085] The reference correction data set is obtained, and the number of data in the reference correction data set is determined. The reference correction data set is generated by sampling the power data and manually correcting the abnormal data in the sampled power data;

[0086] The power data in all corrected abnormal data sets is matched with the power data in the reference correction data set, and the number of matched data pairs is determined;

[0087] The number of data is divided by the number of matched data pairs, and the correction success rate is determined according to the obtained calculation result;

[0088] When the success rate of the correction is greater than or equal to a specified threshold, a step of merging the corrected abnormal data set with a normal data set belonging to the same data type is performed.

[0089] After the correction of the abnormal data is completed, the result of the correction needs to be verified. If the verification is passed, the corrected data can be considered reliable and can be used as simulation data. Then, a step of merging the corrected abnormal data set with a normal data set belonging to the same data type is performed. If the verification is not passed, i.e., when the success rate of the correction is less than a specified threshold, the corrected data can be considered unreliable, and the power data collected from different data sources at this time can also be considered unreliable and cannot be used as simulation data. Therefore, the power data collected from different data sources at this time can be discarded.

[0090] In the verification of the result of the correction, a reference correction data set can be established first. The reference correction data set can be obtained by sampling the power data collected from different data sources at the beginning. In order to ensure the randomness and effectiveness of the sampled power data, a certain amount of power data can be extracted from each data source after classification according to the data source, for example, 10% of the sample data can be extracted from the power data of each data source. After obtaining the sample data, the sample data can be manually identified and corrected for abnormal data. All the corrected abnormal data form the reference correction data set.

[0091] The power data in all the corrected abnormal data sets is matched with the power data in the reference correction data set. The matching result can reflect how many power data in the reference correction data set are contained in the corrected abnormal data set. The more the matching is successful, the more power data in the reference correction data set is contained in the corrected abnormal data set, and the higher the success rate of the correction is.

[0092] In the calculation of the success rate of the correction, the success rate (%) = the number of matched data pairs / the number of data in the reference correction data set * 100%.

[0093] In the specific implementation, if the success rate of the correction is greater than or equal to 95%, the power data in all the corrected abnormal data sets can be used for 10kV power distribution network simulation calculation. Otherwise, all the power data processed at this time is discarded, and power data in another time range, for example, power data in another month, is selected to start data processing again.

[0094] For a clearer understanding of the present embodiment, reference can be made to FIG. 1, which is a schematic diagram of a processing flow of power data for simulation according to an embodiment of the present application. The power data processing process is as follows: Figure 2

[0095] ​After the power data from different data sources is collected for a specified period of time, the power data can be classified according to the data types in the power data of each data source to obtain a classified power data set;

[0096] Part of the power data can be extracted from the power data set of different data types for manual identification of abnormal data and correction to form a reference correction data set, which is used for verification of the correction result in S208. It should be noted that when part of the power data is extracted as a sample, the original collected data is not affected, that is, the extraction is only a copy of the data in the original collected data;

[0097] The power data sets are subjected to preliminary screening (equivalent to the above-mentioned rough screening), the purpose of which is to screen out abnormal data that does not exist in the correlation and does not conform to the electrical principle, and the obtained abnormal data is used for abnormal data correction in S207;

[0098] For the power data that passes the preliminary screening, data fine screening can be continued, and cross verification of the power data is performed by calling power data from different data sources to ensure that all power data conforms to the electrical logic, and the power data that fails the fine screening is determined as abnormal data;

[0099] After all the abnormal data is determined through preliminary screening and fine screening, the abnormal data can be corrected. The correction strategy can be different according to the data type of each power data;

[0100] After the correction of the abnormal data is completed, the matching condition of all the corrected data with the reference correction data set formed in S202 can be determined to determine the correction success rate;

[0101] When the correction success rate exceeds a specified threshold, for example, 95%, the power data that passes the fine screening and the corrected power data can be used for simulation calculation together. If the correction success rate is low, all the data collected this time can be discarded, and other time period power data is used to re-enter the step of S201 for data processing.

[0102] In the embodiment of the present application, a power data processing method for simulation is disclosed, which comprises: collecting power data from different data sources, classifying the power data, obtaining a plurality of power data sets of different data types, respectively performing coarse screening on each power data set to divide each power data set into a normal data set and an abnormal data set, screening out abnormal data that does not exist in the correlation relationship and exists in violation of the electrical principle, performing fine screening on each normal data set to screen out abnormal data from the normal data set and add it to the abnormal data set of the same data type as the normal data set, determining the abnormal data that exists in the electrical logic error in the normal data set, respectively modifying the power data in each abnormal data set, and generating a simulation data set based on the modified abnormal data set, wherein the simulation data set is used for simulation calculation of the power distribution network. Through coarse screening and fine screening, the power data is double filtered, and finally the abnormal data is modified to obtain a data set that meets the simulation requirements of the power distribution network, which can reduce the workload of manually modifying the power data from different data sources, efficiently handle data missing, data misalignment and data redundancy, and improve the authenticity and reliability of the simulation data.

[0103] Embodiment two

[0104] Figure 3 A structural schematic diagram of a power data processing device for simulation is provided in the second embodiment of the present application, and the device comprises:

[0105] A power data set determination module 310 is configured to collect power data from different data sources, classify the power data, and obtain a plurality of power data sets of different data types.

[0106] A coarse screening module 320 is configured to respectively perform coarse screening on each power data set to divide each power data set into a normal data set and an abnormal data set.

[0107] A fine screening module 330 is configured to perform fine screening on each normal data set to screen out abnormal data from the normal data set and add it to the abnormal data set of the same data type as the normal data set.

[0108] A modification module 340 is configured to respectively modify the power data in each abnormal data set and generate a simulation data set based on the modified abnormal data set, wherein the simulation data set is used for simulation calculation of the power distribution network.

[0109] In one embodiment, the coarse screening module 320 comprises the following sub-modules:

[0110] The association relationship judgment submodule is configured to judge whether the power data in each power data set has an association relationship;

[0111] The first abnormal data determination submodule is configured to determine the power data determined as not having an association relationship as abnormal data, and store the abnormal data in an abnormal data set corresponding to the current power data set;

[0112] The normal data determination submodule is configured to determine the power data determined as having an association relationship as normal data, and store the normal data in a normal data set corresponding to the current power data set.

[0113] In an embodiment, the system further comprises the following modules:

[0114] The screening execution module is configured to screen the power data in the normal data set by using a preset screening condition, wherein the screening condition is set based on an electrical principle and for power data sets of different data types;

[0115] The abnormal data determination module is configured to determine the power data not meeting the screening condition as abnormal data, and store the abnormal data in an abnormal data set of the same data type as the current normal data set.

[0116] In an embodiment, the fine screening module 330 comprises the following submodules:

[0117] The influence relationship and influence logic acquisition submodule is configured to acquire the influence relationship and influence logic between the power data;

[0118] The power data determination submodule is configured to determine the power data having the influence relationship with the power data in each normal data set;

[0119] The verification submodule is configured to verify the power data in each normal data set by using the power data having the influence relationship based on the influence logic, and determine the power data failing to pass the verification as abnormal data.

[0120] In an embodiment, the data types include static parameter types and identity information types; and the correction module 340 comprises the following submodules:

[0121] The correction strategy determination submodule is configured to determine a correction strategy according to the data type of each abnormal data set, wherein the correction strategy is the same when the data type is a static parameter type or an identity information type;

[0122] The correction submodule is configured to correct the power data in each abnormal data set by using the correction strategy.

[0123] In an embodiment, the correction module 340 comprises the following sub-modules:

[0124] The simulation data set determination sub-module is configured to merge the corrected abnormal data set with the normal data set of the same data type, and generate the simulation data set based on the merging result.

[0125] In an embodiment, the device further comprises the following modules:

[0126] The reference correction data set acquisition module is configured to acquire a reference correction data set, and determine the number of data in the reference correction data set, wherein the reference correction data set is generated by sampling the power data and manually correcting the abnormal data in the sampled power data.

[0127] The matching module is configured to match the power data in all the corrected abnormal data sets with the power data in the reference correction data set, and determine the number of matched data pairs.

[0128] The correction success rate determination module is configured to perform division calculation on the number of data and the number of matched data pairs, and determine the correction success rate according to the calculation result.

[0129] The calling module is configured to call the simulation data set determination sub-module when the correction success rate is greater than or equal to a specified threshold.

[0130] The power data processing device for simulation provided by the embodiment of the present application can implement the power data processing method for simulation provided by the first embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0131] Embodiment three

[0132] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0133] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0135] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a method for processing power data for simulation.

[0136] In some embodiments, a method for processing power data for simulation can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of a method for processing power data for simulation described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform a method for processing power data for simulation by any other appropriate means, such as by means of firmware.

[0137] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0138] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0139] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0140] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0141] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0143] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0144] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A power data processing method for simulation, characterized by, The method comprises: Collecting power data from different data sources, and classifying the power data to obtain a plurality of power data sets of different data types; Coarsely screening each power data set to divide each power data set into a normal data set and an abnormal data set; Fine screening each normal data set to filter out abnormal data from the normal data set and add the abnormal data to an abnormal data set of the same data type as the normal data set; Respectively correcting the power data in each abnormal data set, and generating a simulation data set based on the corrected abnormal data set, the simulation data set being used for simulation calculation of a power distribution network; Wherein, the coarsely screening each power data set comprises: For each power data set, determining whether the power data in each power data set has a correlation; Determine the power data that is determined to have no correlation as abnormal data, and store the abnormal data in the abnormal data set corresponding to the current power data set; Determine the power data that is determined to have a correlation as normal data, and store the normal data in the normal data set corresponding to the current power data set; The fine screening of each normal data set comprises: Obtaining the influence relationship and influence logic between each power data; Determine the power data that has the influence relationship with the power data in each normal data set; Based on the influence logic, verify the power data in each normal data set using the power data that has the influence relationship, and determine the power data that fails the verification as abnormal data.

2. The method of claim 1, wherein, After storing the normal data in the normal data set corresponding to the current power data set, further comprising: Screening the power data in the normal data set using a pre-set screening condition, wherein the screening condition is set based on electrical principles for power data sets of different data types; Determine the power data that does not meet the screening condition as abnormal data, and store the abnormal data in the abnormal data set of the same data type as the current normal data set.

3. The method of claim 1, wherein, The data type includes static parameter type and identity information type; the correction of the power data in each abnormal data set comprises: Determine the correction strategy according to the data type of each abnormal data set, wherein the correction strategy is the same when the data type is static parameter type or identity information type; Correct the power data in each abnormal data set using the correction strategy.

4. The method according to any of claims 1, 2, 3, characterized in that, The simulation data set generated based on the corrected abnormal data set comprises: Merge the corrected abnormal data set with the normal data set of the same data type, and generate the simulation data set based on the merged result.

5. The method of claim 4, wherein, Before merging the corrected abnormal data set with the normal data set of the same data type, further comprising: acquire a reference correction data set, and determine a data quantity in the reference correction data set, the reference correction data set being generated by sampling the power data and manually correcting abnormal data in the sampled power data; match the power data in all the corrected abnormal data sets with the power data in the reference correction data set, and determine a quantity of matched data pairs that are successfully matched; perform division calculation on the data quantity and the quantity of matched data pairs, and determine a correction success rate according to a calculation result obtained; when the correction success rate is greater than or equal to a specified threshold, perform the step of merging the corrected abnormal data sets with normal data sets that belong to the same data type.

6. An electric power data processing apparatus for simulation, characterized by comprising: The device comprises: a power data set determination module configured to collect power data from different data sources, and classify the power data to obtain a plurality of power data sets of different data types; a coarse screening module configured to respectively perform coarse screening on each power data set to divide each power data set into a normal data set and an abnormal data set; a fine screening module configured to perform fine screening on each normal data set to screen out abnormal data from the normal data set and add the abnormal data to an abnormal data set that belongs to the same data type as the normal data set; a correction module configured to respectively correct power data in each abnormal data set, and generate a simulation data set based on the corrected abnormal data set, the simulation data set being used for simulation calculation of a power distribution network; wherein the coarse screening module comprises: a correlation relationship judgment sub-module configured to determine, for each power data set, whether power data in each power data set has a correlation relationship; a first abnormal data determination sub-module configured to determine power data that is determined to have no correlation relationship as abnormal data, and store the abnormal data in an abnormal data set corresponding to the current power data set; a normal data determination sub-module configured to determine power data that is determined to have a correlation relationship as normal data, and store the normal data in a normal data set corresponding to the current power data set; the fine screening module comprises: an influence relationship and influence logic acquisition sub-module configured to acquire an influence relationship and influence logic between power data; a power data determination sub-module configured to determine power data that has the influence relationship with power data in each normal data set; a verification sub-module configured to verify power data in each normal data set using power data that has the influence relationship based on the influence logic, and determine power data that fails the verification as abnormal data.

7. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the power data processing method for simulation according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to implement the method for processing power data for simulation according to any one of claims 1-5 when executed.

Images