Electric quantity data restoration method and system based on power grid operation mechanism

Abstract

The invention provides an electric quantity data restoration method and system based on a power grid operation mechanism. The method comprises the following steps: obtaining operation data of a power distribution network; based on a power grid operation mechanism, performing data checking on the operation data of the power distribution network by using a consistency checking method to obtain abnormal electric quantity data of the power distribution network; performing anomaly classification on the abnormal electric quantity data by using a rule-based classification method to obtain an anomaly type to which the abnormal electric quantity data belongs; according to the abnormal type, performing data restoration on the abnormal electric quantity data by using a pre-constructed electric quantity balance model; according to the invention, the operation data of the power distribution network is checked based on the power grid operation mechanism, so that judgment errors caused by data errors can be reduced; according to the invention, the pre-constructed electric quantity balance model is utilized to carry out data restoration on the abnormal electric quantity data after data checking, so that the abnormal electric quantity data can be corrected quickly, automatically and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution networks, and in particular to a method and system for repairing electric quantity data based on a power grid operation mechanism. Background Art

[0002] At present, the influence of switch state changes is considered, topological relationships are constructed, and daily power repair and deduction are carried out based on the power balance model. On the one hand, by identifying the state changes of medium-voltage line interconnection switches, section switches, and branch switches, the power balance objects are selected, and daily power repair and deduction are carried out to solve the problem of power imbalance caused by the change of topological relationships due to the transfer of power supply in the medium-voltage distribution network; on the other hand, by identifying the state changes of 35 kV and above power grid circuit breakers, the power balance objects are selected, and daily power repair and deduction are carried out to solve the possible weak coupling relationship between the buses of the same voltage level at the same station.

[0003] For medium-voltage distribution networks, the existing power repair methods only consider the power balance under normal operation of the power grid, and do not consider the changes in the power balance object under the power transfer mode, which leads to power imbalance and poor accuracy of power repair. Especially for 35 kV and above power grids, the existing power repair methods construct the power balance model of each voltage level bus of the substation as a whole, and do not consider the further decoupling of the power balance model under the condition of busbar split operation, which leads to high data correlation and low power repair rate.

[0004] In summary, the power repair method in the prior art only considers the power balance under the normal operation mode of the power grid, and does not consider the power balance under abnormal power data, which leads to the problem of poor accuracy of power repair. Summary of the invention

[0005] In order to solve the problem that the existing power repair method only considers the power balance under the normal operation mode of the power grid, but does not consider the power balance under abnormal power data, thereby resulting in poor accuracy of power repair, the present invention proposes a power data repair method based on the power grid operation mechanism, comprising:

[0006] Obtaining the operation data of the distribution network;

[0007] Based on the operation mechanism of the power grid, the operation data of the distribution network is verified by using a consistency verification method to obtain abnormal power data of the distribution network;

[0008] Using a rule-based classification method, the abnormal power data is classified to obtain the abnormal type to which the abnormal power data belongs;

[0009] According to the abnormality type, the abnormal power data is repaired using a pre-built power balance model.

[0010] Optionally, the power balance model includes the following construction process:

[0011] Obtaining switch status change information of the distribution network;

[0012] Constructing a topological relationship of the distribution network according to the switch state change information;

[0013] According to the topological relationship, an electricity balance model of the distribution network is constructed.

[0014] Optionally, constructing the topological relationship of the distribution network according to the switch state change information includes:

[0015] According to the switch state change information, the distribution network is divided into regions using a depth-first search algorithm to obtain switch state change information corresponding to different electrical regions of the distribution network;

[0016] According to the switch state change information of the distribution network in different electrical areas, the connection relationship between each node and edge in different electrical areas is determined by an adjacency matrix method;

[0017] The topological relationship of the distribution network is constructed according to the connection relationship between each node and the edge in the different electrical areas.

[0018] Optionally, constructing the power balance model of the distribution network according to the topological relationship includes:

[0019] Calculating the line loss rate of each electrical device in the distribution network according to the topological relationship and the acquired input power data and output power data of the distribution network;

[0020] Constructing a power balance model for each electrical device according to the line loss rate of each electrical device;

[0021] The electrical equipment includes one or more of the following: transmission lines, distribution lines, transformers and busbars.

[0022] Optionally, the repairing the abnormal power data by using a pre-built power balance model according to the abnormality type includes:

[0023] According to the abnormality type, selecting an electric quantity balance model corresponding to the electrical equipment to which the abnormal electric quantity data belongs;

[0024] The abnormal electric quantity data is repaired by using an electric quantity balance model corresponding to the electrical equipment to which the abnormal electric quantity data belongs.

[0025] Optionally, based on the power grid operation mechanism, using a consistency verification method to perform data verification on the operation data of the distribution network to obtain abnormal power data of the distribution network includes:

[0026] Based on the operation mechanism of the power grid, extracting time series features of the operation data of the distribution network to obtain time series feature data corresponding to the operation data;

[0027] Performing a time series consistency check on the time series feature data using a consistency check method to obtain normal time series data and abnormal time series data corresponding to the time series feature data;

[0028] The abnormal power quantity is extracted from the abnormal time series data, the abnormal node and time point are located, and the abnormal power quantity data is generated.

[0029] Optionally, the using a rule-based classification method to perform abnormal classification on the abnormal power data to obtain the abnormal type to which the abnormal power data belongs includes:

[0030] Performing null value verification on the abnormal electric quantity data by a range matching method, and dividing the abnormal electric quantity data into null value electric quantity data and non-null value electric quantity data;

[0031] Performing a reverse check on the non-empty power data by a threshold method, and dividing the non-empty power data into reverse power data and non-reverse power data;

[0032] The non-reverse power data is subjected to jump check by conditional logic method, and the non-reverse power data is divided into jump power data and non-jump power data.

[0033] Optionally, the operation data of the distribution network includes one or more of the following: line data, switch data, substation data, power plant data, bus data, main transformer data, distribution transformer data, measuring point data, dedicated line data, distributed power supply data, office power consumption data, user data and structure data;

[0034] The line data includes one or more of the following: line identification information, line number, line name, line type, voltage level, start switch identification information, start station identification information, end switch identification information, end station identification information, commissioning time, decommissioning time, operating status, asset nature, management unit, line length, line model, line region information and line resource identification information;

[0035] The switch data includes one or more of the following: switch identification information, switch number, switch name, switch type, switch voltage, switch line, switch station, switch location and switch resource identification information;

[0036] The substation data includes one or more of the following: substation identification information, substation number, substation name, substation type, asset nature, voltage level, substation capacity, substation management unit information, substation region information and substation resource identification information;

[0037] The power plant data includes one or more of the following: power plant identification information, power plant number, power plant name, voltage level and metering point identification information;

[0038] The bus data includes one or more of the following: bus identification information, bus number, bus name, bus voltage, bus station, bus resource identification information;

[0039] The main transformer data includes one or more of the following: main transformer identification information, main transformer number, main transformer name, main transformer voltage, main transformer capacity, main transformer station and main transformer resource identification information;

[0040] The distribution transformer data includes one or more of the following: distribution transformer identification information, distribution transformer number, distribution transformer name, distribution transformer type, asset nature, distribution transformer line, distribution transformer rated capacity and distribution transformer resource identification information;

[0041] The measuring point data includes one or more of the following: the relationship between the measuring point and the switch, the relationship between the measuring point and the measuring point equipment, and the measuring point location attribute;

[0042] The dedicated line data includes one or more of the following: dedicated line user identification information, dedicated line user number, dedicated line user name, voltage level, dedicated line station, dedicated line line;

[0043] The distributed power data includes one or more of the following: distributed power user identification information, distributed power user number, distributed power user name and distributed power metering point identification information;

[0044] The office electricity consumption data includes one or more of the following: office electricity user identification information, office electricity user number, office electricity user name, office electricity line and office electricity metering point identification information;

[0045] The user data includes one or more of the following: user identification information, user number, user name, user nature, voltage level, user start / stop status;

[0046] The structural data includes one or more of the following: power grid topology data, switch status data and daily power data of collection points.

[0047] Optionally, after repairing the abnormal power data by using a pre-built power balance model according to the abnormality type, the method further includes:

[0048] Acquire a node in the distribution network where no data collection device is installed;

[0049] The power balance model is used to deduce the power of the node without the collection device installed, so as to obtain the power data corresponding to the node without the collection device installed.

[0050] Based on the same inventive concept, the present invention also provides an electric quantity data repair system based on the operation mechanism of a power grid, comprising:

[0051] A data acquisition module, used to acquire the operation data of the distribution network;

[0052] A data verification module is used to verify the operation data of the distribution network based on the operation mechanism of the power grid by using a consistency verification method to obtain abnormal power data of the distribution network;

[0053] An abnormal classification module is used to classify the abnormal power data using a rule-based classification method to obtain the abnormal type to which the abnormal power data belongs;

[0054] The data repair module is used to repair the abnormal power data according to the abnormality type by using a pre-built power balance model.

[0055] Optionally, the power data repair system further includes: a model building module, which is used to:

[0056] Obtaining switch status change information of the distribution network;

[0057] Constructing a topological relationship of the distribution network according to the switch state change information;

[0058] According to the topological relationship, an electricity balance model of the distribution network is constructed.

[0059] Optionally, the model building module includes:

[0060] A region division submodule, for dividing the distribution network into regions according to the switch state change information by using a depth-first search algorithm, and obtaining switch state change information corresponding to different electrical regions of the distribution network;

[0061] A connection relationship confirmation submodule, used to determine the connection relationship between each node and edge in different electrical areas through an adjacency matrix method according to the switch state change information of the distribution network in different electrical areas;

[0062] The topology relationship building submodule is used to build the topology relationship of the distribution network according to the connection relationship between each node and edge in the different electrical areas.

[0063] Optionally, the model building module further includes:

[0064] A line loss rate calculation submodule, used to calculate the line loss rate of each electrical device in the distribution network according to the topological relationship and the acquired input power data and output power data of the distribution network;

[0065] A balance model building submodule, used to build a power balance model for each electrical device according to the line loss rate of each electrical device;

[0066] The electrical equipment includes one or more of the following: transmission lines, distribution lines, transformers and busbars.

[0067] Optionally, the data repair module includes:

[0068] A model selection submodule, used to select, according to the abnormality type, an electric quantity balance model corresponding to the electrical equipment to which the abnormal electric quantity data belongs;

[0069] The abnormality repair submodule is used to repair the abnormal power data by using the power balance model corresponding to the electrical equipment to which the abnormal power data belongs.

[0070] Optionally, the data verification module includes:

[0071] A feature extraction submodule, used for extracting time series features of the operation data of the distribution network based on the operation mechanism of the power grid, and obtaining time series feature data corresponding to the operation data;

[0072] Performing a time series consistency check on the time series feature data using a consistency check method to obtain normal time series data and abnormal time series data corresponding to the time series feature data;

[0073] The abnormal power quantity is extracted from the abnormal time series data, the abnormal node and time point are located, and the abnormal power quantity data is generated.

[0074] Optionally, the abnormal classification module includes:

[0075] A null value checking submodule, used for performing null value checking on the abnormal electric quantity data by a range matching method, and dividing the abnormal electric quantity data into null value electric quantity data and non-null value electric quantity data;

[0076] A reverse check submodule, used for performing a reverse check on the non-empty power data by a threshold method, and dividing the non-empty power data into reverse power data and non-reverse power data;

[0077] The jump check submodule is used to perform jump check on the non-reverse power data through a conditional logic method, and divide the non-reverse power data into jump power data and non-jump power data.

[0078] Optionally, the operation data of the distribution network includes one or more of the following: line data, switch data, substation data, power plant data, bus data, main transformer data, distribution transformer data, measuring point data, dedicated line data, distributed power supply data, office power consumption data, user data and structure data;

[0079] The line data includes one or more of the following: line identification information, line number, line name, line type, voltage level, start switch identification information, start station identification information, end switch identification information, end station identification information, commissioning time, decommissioning time, operating status, asset nature, management unit, line length, line model, line region information and line resource identification information;

[0080] The switch data includes one or more of the following: switch identification information, switch number, switch name, switch type, switch voltage, switch line, switch station, switch location and switch resource identification information;

[0081] The substation data includes one or more of the following: substation identification information, substation number, substation name, substation type, asset nature, voltage level, substation capacity, substation management unit information, substation region information and substation resource identification information;

[0082] The power plant data includes one or more of the following: power plant identification information, power plant number, power plant name, voltage level and metering point identification information;

[0083] The bus data includes one or more of the following: bus identification information, bus number, bus name, bus voltage, bus station, bus resource identification information;

[0084] The main transformer data includes one or more of the following: main transformer identification information, main transformer number, main transformer name, main transformer voltage, main transformer capacity, main transformer station and main transformer resource identification information;

[0085] The distribution transformer data includes one or more of the following: distribution transformer identification information, distribution transformer number, distribution transformer name, distribution transformer type, asset nature, distribution transformer line, distribution transformer rated capacity and distribution transformer resource identification information;

[0086] The measuring point data includes one or more of the following: the relationship between the measuring point and the switch, the relationship between the measuring point and the measuring point equipment, and the measuring point location attribute;

[0087] The dedicated line data includes one or more of the following: dedicated line user identification information, dedicated line user number, dedicated line user name, voltage level, dedicated line station, dedicated line line;

[0088] The distributed power data includes one or more of the following: distributed power user identification information, distributed power user number, distributed power user name and distributed power metering point identification information;

[0089] The office electricity consumption data includes one or more of the following: office electricity user identification information, office electricity user number, office electricity user name, office electricity line and office electricity metering point identification information;

[0090] The user data includes one or more of the following: user identification information, user number, user name, user nature, voltage level, user start / stop status;

[0091] The structural data includes one or more of the following: power grid topology data, switch status data and daily power data of collection points.

[0092] Optionally, the power data repair system further includes: a power deduction module for

[0093] Acquire a node in the distribution network where no data collection device is installed;

[0094] The power balance model is used to deduce the power of the node without the collection device installed, so as to obtain the power data corresponding to the node without the collection device installed.

[0095] In another aspect, the present invention further provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0096] The memory is used to store one or more programs;

[0097] When the one or more programs are executed by the at least one processor, the aforementioned method for repairing electric quantity data based on the operation mechanism of a power grid is implemented.

[0098] On the other hand, the present invention further provides a computer-readable storage medium having an execution program stored thereon, and when the execution program is executed, the aforementioned method for repairing electric quantity data based on the operation mechanism of a power grid is implemented.

[0099] Compared with the prior art, the present invention has the following beneficial effects:

[0100] The present invention provides an electric quantity data repair method and system based on the operation mechanism of a power grid, comprising: acquiring the operation data of a distribution network; based on the operation mechanism of a power grid, performing data verification on the operation data of the distribution network by using a consistency verification method to obtain abnormal electric quantity data of the distribution network; performing abnormal classification on the abnormal electric quantity data by using a rule-based classification method to obtain the abnormal type to which the abnormal electric quantity data belongs; performing data repair on the abnormal electric quantity data by using a pre-constructed electric quantity balance model according to the abnormal type; the present application performs data verification on the operation data of the distribution network based on the operation mechanism of a power grid, which is conducive to reducing misjudgment caused by data errors; and performs data repair on the abnormal electric quantity data after data verification by using a pre-constructed electric quantity balance model, which is conducive to fast, automatic and accurate correction of the abnormal electric quantity data. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 A schematic diagram of a data verification process in a power data repair method based on a power grid operation mechanism provided by the present invention;

[0102] Figure 2 A schematic diagram of a flow chart of abnormal classification in a method for repairing power data based on a power grid operation mechanism provided by the present invention;

[0103] Figure 3 A schematic diagram of constructing an electric power balance model in an electric power data repair method based on a power grid operation mechanism provided by the present invention;

[0104] Figure 4 A schematic diagram of the structure of an electric quantity data repair system based on the power grid operation mechanism provided by the present invention;

[0105] Figure 5 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0106] The present invention proposes a method, system, device and medium for repairing electric quantity data based on the operation mechanism of a power grid. The specific implementation manner of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0107] Embodiment 1:

[0108] The present invention provides a method for repairing power data based on the operation mechanism of the power grid, the flow chart of which is as follows: Figure 1 As shown, including:

[0109] Step 1: Obtain the operation data of the distribution network;

[0110] Step 2: Based on the operation mechanism of the power grid, the operation data of the distribution network is verified by using the consistency verification method to obtain the abnormal power data of the distribution network;

[0111] Step 3: Use a rule-based classification method to classify the abnormal power data and obtain the abnormal type to which the abnormal power data belongs;

[0112] Step 4: Based on the abnormality type, use the pre-built power balance model to repair the abnormal power data.

[0113] In this embodiment, data collection is the first step in implementing the technical solution. By collecting the operating data of the distribution network, the structure and operating status of the distribution network can be reflected. These data are important bases for analyzing the performance of the power grid, identifying problems and optimizing them. They are also key inputs for building power balance models, performing data repair and deduction. Therefore, accurate and real-time acquisition of these data can ensure that other steps have a reliable source of information and provide a basis for subsequent data verification and repair. For example, the operating data of the above-mentioned distribution network may include one or more of the following: line data, switch data, substation data, power plant data, bus data, main transformer data, distribution transformer data, measuring point data, dedicated line data, distributed power supply data, office power data, user data and structural data;

[0114] For example, the above-mentioned line data may include one or more of the following: line identification information, line number, line name, line type, voltage level, starting switch identification information, starting station identification information, ending switch identification information, ending station identification information, commissioning time, decommissioning time, operating status, asset nature, management unit, line length, line model, line region information and line resource identification information;

[0115] By way of example, the switch data may include one or more of the following: switch identification information, switch number, switch name, switch type, switch voltage, switch-to-line, switch-to-station, switch location, and switch resource identification information;

[0116] For example, the above-mentioned substation data may include one or more of the following: substation identification information, substation number, substation name, substation type, asset nature, voltage level, substation capacity, substation management unit information, substation region information and substation resource identification information;

[0117] For example, the power plant data may include one or more of the following: power plant identification information, power plant number, power plant name, voltage level and metering point identification information;

[0118] For example, the above bus data may include one or more of the following: bus identification information, bus number, bus name, bus voltage, bus station, bus resource identification information;

[0119] For example, the main transformer data may include one or more of the following: main transformer identification information, main transformer number, main transformer name, main transformer voltage, main transformer capacity, main transformer station and main transformer resource identification information;

[0120] For example, the distribution transformer data may include one or more of the following: distribution transformer identification information, distribution transformer number, distribution transformer name, distribution transformer type, asset nature, distribution transformer-affiliated line, distribution transformer rated capacity, and distribution transformer resource identification information;

[0121] For example, the above-mentioned measuring point data may include one or more of the following: the relationship between the measuring point and the switch, the relationship between the measuring point and the measuring point device, and the measuring point location attribute;

[0122] For example, the above-mentioned dedicated line data may include one or more of the following: dedicated line user identification information, dedicated line user number, dedicated line user name, voltage level, dedicated line station, dedicated line line; in this example, obtaining dedicated line data can help realize personalized power consumption analysis, for example, when performing abnormal data repair, it is helpful to ensure the accuracy of user power consumption data, thereby better analyzing the user's power consumption behavior and supporting demand response plans;

[0123] For example, the above-mentioned distributed power data may include one or more of the following: distributed power user identification information, distributed power user number, distributed power user name and distributed power metering point identification information; in this example, by monitoring and repairing abnormal data of distributed power sources, the coordination ability of renewable energy and conventional power sources can be further optimized, thereby facilitating the improvement of the adaptability of the power grid to the volatility of new energy;

[0124] For example, the above-mentioned office electricity consumption data may include one or more of the following: office electricity user identification information, office electricity user number, office electricity user name, office electricity line and office electricity metering point identification information;

[0125] For example, the above user data may include one or more of the following: user identification information, user number, user name, user nature, voltage level, user start / stop status;

[0126] For example, the above-mentioned structural data may include one or more of the following: power grid topology data, switch status data, and daily power data of collection points; in this example, by acquiring the power grid topology data and the switch status data collected in real time, the subsequent abnormal repair can optimize the layout of the entire network, rather than only solving single point failures, which is conducive to improving the robustness of the overall power grid;

[0127] When obtaining the operating data of the distribution network, by utilizing rich identification information and detailed equipment data, the source of anomalies can be traced and identified more accurately. For example, by combining the commissioning and decommissioning time with the operating status, the start and stop of equipment that is not planned can be automatically identified, which is conducive to quickly locating problem equipment and lines; various asset data can accurately reflect the status, nature and management unit of the equipment in the distribution network. When performing anomaly detection, these records can be updated and maintained in a timely manner, thereby improving asset life cycle management; through long-term monitoring of the equipment's operating status, fault history and repair record information, it can be used to evaluate the operating health of equipment and lines, which is not only conducive to planned maintenance, but also can be used to expand the prediction of the service life of assets; in addition, by obtaining accurate and real-time bus, main transformer, and line data, the dispatching system can respond quickly when anomalies occur and make intelligent dispatching decisions.

[0128] The above distribution network operation data can be obtained through a variety of channels, including but not limited to: directly obtaining real-time operation data from the power system monitoring system, extracting historical operation data from the historical database, obtaining equipment parameters from equipment manufacturers or suppliers, etc. After being obtained, the above distribution network operation data needs to be processed and analyzed to ensure the accuracy and reliability of the data. In order to effectively support the operation status evaluation and anomaly detection of the distribution network, it is necessary to further verify and analyze the operation data in combination with the mechanism characteristics of the power grid operation. Specifically:

[0129] In one implementation, in the above step 2, based on the power grid operation mechanism, the operation data of the distribution network is verified by using a consistency verification method, and the process of obtaining abnormal power data of the distribution network may include:

[0130] Based on the operation mechanism of the power grid, the time series characteristics of the operation data of the distribution network are extracted to obtain the time series characteristic data corresponding to the operation data;

[0131] The time series feature data is checked for time series consistency by using a consistency check method to obtain time series data without abnormalities and time series data with abnormalities corresponding to the time series feature data;

[0132] Extract abnormal power from abnormal time series data, locate abnormal nodes and time points, and generate abnormal power data;

[0133] In this implementation, by combining the power grid operation mechanism and consistency verification method, intelligent verification of distribution network operation data is achieved, which can more accurately understand the actual operation status of the power grid and locate abnormal nodes and time points, which is conducive to optimizing the dispatching and operation strategies of the power grid, improving the efficiency and stability of the power grid, and promoting the development of the power grid towards a more intelligent and automated direction.

[0134] After completing the intelligent verification of the distribution network operation data and generating abnormal power data, the next step is to further analyze the nature and source of these abnormal data in order to formulate a more accurate response strategy. Therefore, the abnormal power data can be classified in detail through a rule-based classification method, and classified into different abnormal types to provide a basis for subsequent processing. Specifically:

[0135] In one implementation, in the above step 3, the rule-based classification method is used to classify the abnormal power data, and the process of obtaining the abnormal type to which the abnormal power data belongs may include:

[0136] The abnormal power data is checked for null values ​​by using the range matching method, and the abnormal power data is divided into null value power data and non-null value power data;

[0137] The non-empty power data is checked backwards by using the threshold method, and the non-empty power data is divided into backward power data and non-reverse power data;

[0138] The non-reverse power data is checked for jumps by conditional logic method, and the non-reverse power data is divided into jump power data and non-jump power data;

[0139] In this implementation, by accurately repairing the daily power of the power grid equipment node, the problems of null value, jump, reverse and so on at the collection point are solved; for example, through the null value check, the null value problem in the power data can be discovered and processed in time to ensure the continuity and availability of the data. At the same time, the reverse check and jump check can further eliminate or correct the unreasonable power data, such as power reverse and sudden jump, thereby improving the accuracy and reliability of the data; secondly, through the classification method, the abnormal power data is subdivided into different abnormal types, such as null value power data, reverse power data and jump power data, which enables the operation and maintenance personnel to quickly identify the nature and location of the problem and take targeted measures to repair it, thereby improving the efficiency of problem solving. In addition, accurate abnormal classification and positioning are conducive to the operation and maintenance personnel to better understand the operating status of the power grid equipment, discover potential problems in time, and perform preventive maintenance, which is conducive to reducing the power outage time and economic losses caused by equipment failure, and improving the power supply reliability and service quality of the power grid. Finally, by combining rule-based classification methods and data verification technology, this implementation method can realize intelligent identification and processing of abnormal power data compared to using a single method, which is conducive to improving the efficiency and management level of power grid operation and maintenance.

[0140] In this implementation, the abnormal power data is classified by using a rule-based classification method, which mainly includes: null value verification, reverse verification and jump verification. Specifically:

[0141] Empty value check: by judging whether the power is empty, if it is empty, it is determined that the power has a empty value;

[0142] Reverse check: by judging whether the forward / reverse power is less than 0, if so, it is determined that the forward / reverse power is reversed;

[0143] Jump check: Let Z = daily power consumption / daily power integral. If Z is greater than the threshold (the threshold is a manually set value), there is a jump in the daily power consumption. Figure 2 As shown in the figure, when performing null value check, reverse check, and jump check on the power data, the power data should be divided into forward power and reverse power, and they should be checked respectively; among them, the forward power usually represents the electric energy transmitted from the power grid to the user, that is, the power consumed by the user from the power grid. This is the most common type of power in the power system and the main basis for electricity bill settlement; the reverse power represents the electric energy transmitted from the user to the power grid, such as the power output of renewable energy such as grid-connected photovoltaic to the power grid. This type of power is becoming more and more common when distributed power generation and renewable energy are connected to the power grid. When performing null value check, the rules for null value check are the same for forward power and reverse power, that is, check whether the power data is null. However, since they represent different types of power, they may need to be processed separately in practical applications. For example, for forward power, null value may mean that the user has not used electricity or the meter is faulty; while for reverse power, null value may mean that the distributed power generation equipment has not generated electricity or related equipment is faulty. When performing reverse calibration, for the forward power, reverse flow (i.e., power indication decreases) is usually abnormal, which may mean that the meter is faulty or the user is stealing electricity. For the reverse power, reverse flow may indicate that the output of the distributed power generation equipment has decreased or stopped, which may be due to changes in weather conditions, equipment failure or maintenance. Therefore, different judgment standards and treatment measures are required for the reverse calibration of the forward and reverse power. When performing jump calibration, the judgment standards and treatment measures for the jump may also be different for the forward and reverse power. For example, a jump in the forward power may mean that the user's power consumption behavior has changed significantly or the meter has been disturbed; while a jump in the reverse power may indicate that the output power of the distributed power generation equipment has changed significantly or that the related equipment has failed. Therefore, in this implementation, by dividing the electricity data into forward electricity and reverse electricity and checking them separately, it is beneficial to improve the quality and accuracy of the data. By processing these two types of electricity separately, anomalies and errors in the data can be more effectively identified and processed, thereby ensuring the integrity and reliability of the data, which is of great significance for the operation and maintenance management of the power grid, electricity bill settlement, and operation monitoring of distributed power generation equipment.

[0144] After the abnormal power data is classified, a targeted repair plan can be further formulated based on the classification results. Different types of abnormalities often correspond to different electrical equipment characteristics and operating conditions. Therefore, combined with the pre-built power balance model, it can provide accurate repair methods for each type of abnormal data, thereby effectively improving the integrity and accuracy of the data and laying the foundation for the stable operation of the power grid. Specifically:

[0145] In one implementation, in the above step 4, according to the abnormality type, the process of repairing the abnormal power data using the pre-built power balance model may include:

[0146] According to the abnormality type, select the power balance model corresponding to the electrical equipment to which the abnormal power data belongs;

[0147] The abnormal power data is repaired by using the power balance model corresponding to the electrical equipment to which the abnormal power data belongs. This implementation method selects the corresponding power balance model according to the abnormal type and constructs the topological relationship based on the change of the switch state during the operation of the power grid to accurately repair the abnormal power data, effectively reducing data errors and outliers and improving the overall quality of the data. This improvement is not only applicable to medium-voltage distribution networks, but also places special emphasis on the power repair rate of power grids of 35 kV and above, ensuring the accuracy and reliability of power data at all levels of power grids from low voltage to high voltage; secondly, by timely repairing abnormal power data and combining it with the real-time update of the power grid topology, it can be ensured that The normal operation of power grid equipment and the accurate transmission of power data can avoid power grid failures or unstable operations caused by data anomalies, which is conducive to improving the power supply capacity and service quality of the power grid, providing users with a more stable and reliable power supply, and ensuring the safe and stable operation of the power grid. In addition, this implementation method also uses the power balance model and power grid topology relationship to automatically process and intelligently analyze abnormal power data, reducing the possibility of manual intervention and misjudgment, which is conducive to improving the efficiency and accuracy of power grid operation and maintenance and reducing operation and maintenance costs. At the same time, it is also conducive to promoting the power grid to develop in a more intelligent and automated direction, and realizing lean management and intelligent operation and maintenance of the power grid.

[0148] In this implementation, the above power balance model may include the following construction process:

[0149] Obtain switch status change information of the distribution network;

[0150] Construct the topological relationship of the distribution network based on the switch status change information;

[0151] According to the topological relationship, the power balance model of the distribution network is constructed; in this implementation method, by obtaining the switch state change information of the distribution network in real time and constructing the topological relationship of the distribution network accordingly, the actual operation state of the power grid can be accurately reflected. The establishment of this dynamic topological relationship provides a solid foundation for the construction of the power balance model, so that the model can more accurately reflect the power balance state of the power grid. Therefore, when the power abnormality occurs in the power grid, the model can more accurately locate the abnormal source and improve the accuracy of power repair; secondly, since the change of the switch state during the operation of the power grid is considered, the constructed topological relationship and power balance model can more comprehensively cover various operation scenarios in the power grid. When the switch state in the power grid changes, the model can be quickly adjusted to ensure the accuracy and integrity of the power data. This dynamic adjustment capability makes the model more robust when dealing with power grid faults or abnormalities, thereby improving the efficiency of power repair; in addition, by real-time monitoring of switch state changes and constructing topological relationships, power grid operation and maintenance personnel can more intuitively understand the operation state of the power grid, timely discover and deal with potential problems. At the same time, the construction of the power balance model also provides strong support for the intelligent operation and maintenance of the power grid, so that the power grid can be operated and managed more efficiently.

[0152] In this implementation, the process of constructing the topological relationship of the distribution network according to the switch state change information may include:

[0153] According to the switch state change information, the distribution network is divided into regions using a depth-first search algorithm to obtain the switch state change information corresponding to different electrical areas of the distribution network;

[0154] According to the switch state change information of the distribution network in different electrical areas, the connection relationship between each node and edge in different electrical areas is determined by the adjacency matrix method;

[0155] The topological relationship of the distribution network is constructed according to the connection relationship between each node and edge in different electrical areas. In this implementation, the distribution network is divided into regions through the depth-first search algorithm, which can clearly identify different electrical regions in the distribution network, and accurately determine the connection relationship between each node and edge according to the switch state change information in these regions. This method avoids the errors and omissions that may occur in traditional methods and improves the accuracy of topological construction. At the same time, the depth-first search algorithm, as an efficient graph traversal algorithm, can quickly complete the region division and the determination of the connection relationship, thereby improving the efficiency of topological construction. Secondly, since the switch state in the distribution network will constantly change, the topological relationship between the nodes and the edges can be determined. The topological relationship also needs to be updated in real time. This implementation method ensures the real-time and accuracy of the topology by monitoring the switch status change information in real time and dynamically adjusting the topological relationship accordingly. The improvement of this dynamic adaptability enables the distribution network to respond more quickly when facing faults or abnormalities, which is conducive to improving the stability and reliability of the power grid. In addition, by building accurate topological relationships, operation and maintenance personnel can more intuitively understand the structure and operating status of the distribution network, and promptly discover and deal with potential problems. At the same time, the real-time update of topological relationships also provides more accurate information support for operation and maintenance operations such as fault location, fault recovery and load transfer, thereby improving the efficiency and accuracy of operation and maintenance.

[0156] In this implementation, the process of constructing the power balance model of the distribution network according to the topological relationship may include:

[0157] Calculate the line loss rate of each electrical device in the distribution network based on the topological relationship and the acquired input power data and output power data of the distribution network;

[0158] According to the line loss rate of each electrical equipment, the power balance model of each electrical equipment is constructed;

[0159] The electrical equipment mentioned above may include one or more of the following: transmission lines, distribution lines, transformers and busbars;

[0160] In this implementation, the above-mentioned electrical equipment mainly includes 35 kV and above lines (i.e. corresponding transmission lines), 35 kV and above main transformers (i.e. corresponding transformers), 10 kV and above busbars (i.e. corresponding busbars), and 10 kV distribution lines (i.e. corresponding distribution lines);

[0161] (1) Electricity balance model for 35 kV and above lines

[0162] Line loss rate calculation formula: Line loss rate = (input power - output power) / input power;

[0163] Where: Input power = total input power at both ends of the line;

[0164] Output power = total output power at both ends of the line;

[0165] (2) Electricity balance model for main transformers of 35 kV and above

[0166] Line loss rate calculation formula: Line loss rate = (input power - output power) / input power;

[0167] Where: Input power = total input power of high, medium and low voltage sides of main transformer;

[0168] Output power = total output power of the high, medium and low voltage sides of the main transformer;

[0169] (3) Electricity balance model for buses of 10 kV and above

[0170] Line loss rate calculation formula: Line loss rate = (input power - output power) / input power;

[0171] Where: Input power = total input power before and after the busbar;

[0172] Output power = total output power before and after the busbar;

[0173] (4) Electricity balance model of 10 kV distribution line

[0174] Line loss rate calculation formula: Line loss rate = (input power - output power - power sales) / input power

[0175] Among them: input power = power off the line meter + distributed power supply on the grid + power on the grid of power generation customers + power reversed by the total meter of the substation;

[0176] Output power = power on the line gateway + office power + station power;

[0177] Electricity sales = total electricity in the area + electricity consumption by high-voltage users;

[0178] like Figure 3As shown in the figure, in this implementation, by identifying the switch status within the repair cycle and taking the normally open point of the switch as the dividing point, an accurate topological relationship is constructed. This step is the basis for the subsequent construction of the power balance model, which ensures that the model can truly reflect the actual operating status of the power grid. On this basis, corresponding power balance models are constructed for different types of electrical equipment, and their respective line loss rates are calculated. These models not only consider the input power and output power of the electrical equipment, but also make detailed divisions according to the characteristics of the equipment. For example, the power balance model of the 10 kV distribution line also specifically considers the factor of power sales; secondly, the power data without abnormalities, the topological relationship and the power balance model are combined, and the abnormal power data are iterated through multiple times. This method not only improves the accuracy of power data processing, but also effectively reduces the accumulation of data errors. Through iterative repair, it can more accurately locate the cause and location of power anomalies, providing strong support for subsequent troubleshooting and operation and maintenance decisions. More importantly, this implementation method can accurately locate the power balance object of the 10 kV power grid and reduce the coupling relationship between busbars of the same voltage level in 35 kV and above substations. The realization of this effect is due to the refined modeling and power balance analysis of different electrical equipment in the power grid. By constructing an independent power balance model, the power balance relationship between each electrical equipment can be more clearly revealed, thereby reducing the coupling relationship between busbars and improving the stability and reliability of the power grid.

[0179] After the abnormal power data is repaired, in order to further improve the integrity and coverage of the distribution network data, power deduction can be performed for nodes in the distribution network where no data collection devices are installed. Specifically:

[0180] In one implementation, after the abnormal power data is repaired using a pre-built power balance model according to the abnormality type in step 4, the following may also be included:

[0181] Obtain nodes in the distribution network that do not have data collection devices installed;

[0182] Using the power balance model, the power deduction is performed on the nodes without the collection device installed, and the power data corresponding to the nodes without the collection device installed is obtained;

[0183] In this implementation, considering that there may be nodes without collection devices installed in the distribution network, the power data of these nodes is often difficult to obtain directly. Through the power balance model, these data gaps can be filled, which can not only make up for the missing data, but also provide a reliable estimation basis for the power changes of unmonitored nodes, so as to achieve a comprehensive grasp of the global operation status of the distribution network, making the power data of the entire power grid more complete and accurate; the power deduction process can be carried out in real time as needed, without being restricted by the installation progress or maintenance status of the collection device. Therefore, even if the collection devices of some nodes are temporarily unable to work, their power data can be obtained through deduction, ensuring the timely update of the power data of the power grid; by deducing the daily power information of the uninstalled collection device until there are no new repair points and deduction points, this technical solution realizes the holographic perception of the power of the power grid. Holographic perception means that the power data of every node, every line, and every electrical equipment in the power grid can be monitored and accurately obtained in real time. This comprehensive power data monitoring and analysis capability provides strong data support for the operation and maintenance management, troubleshooting, and energy efficiency improvement of the power grid. In addition, this implementation method is also conducive to optimizing the resource allocation and dispatching strategy of the power grid: by performing power simulation on nodes without data collection devices installed, the load distribution and power flow of the power grid can be understood more accurately, thereby allocating power resources more reasonably, formulating more scientific dispatching strategies, and improving the operating efficiency and safety of the power grid.

[0184] In summary, the present invention aims at the problem that the existing power repair method only considers the power balance under the normal operation mode of the power grid, but does not consider the power balance under abnormal power data, which leads to the problem of poor accuracy of power repair. An power data repair method based on the operation mechanism of the power grid is proposed. By using the consistency verification method to perform data verification on the operation data of the distribution network, the inconsistency in the data can be timely discovered and corrected, thereby ensuring the accuracy and consistency of the data; then, the abnormal power data is abnormally classified by a rule-based classification method, and the type and cause of the abnormal data can be accurately identified; finally, according to the abnormal type, the abnormal power data is repaired using a pre-constructed power balance model, which is the core of the present invention. Through this step, the original state of the data can be restored, and the accuracy and availability of the data can be improved. At the same time, this technical solution is also beneficial to improving the daily power repair rate and accuracy of 10 kV and above power grids, and provides strong support for the stable operation and troubleshooting of the power grid.

[0185] Embodiment 2:

[0186] The present invention based on the same inventive concept also provides an electric quantity data repair system based on the operation mechanism of the power grid, and the structural composition diagram is as follows: Figure 4 As shown, including:

[0187] A data acquisition module, used to acquire the operation data of the distribution network;

[0188] The data verification module is used to verify the operation data of the distribution network based on the operation mechanism of the power grid and use the consistency verification method to obtain the abnormal power data of the distribution network;

[0189] The abnormal classification module is used to classify the abnormal power data using a rule-based classification method to obtain the abnormal type to which the abnormal power data belongs;

[0190] The data repair module is used to repair abnormal power data according to the abnormality type using a pre-built power balance model.

[0191] By way of example, the above-mentioned operation data of the distribution network may include one or more of the following: line data, switch data, substation data, power plant data, bus data, main transformer data, distribution transformer data, measuring point data, dedicated line data, distributed power supply data, office power consumption data, user data and structure data;

[0192] For example, the above-mentioned line data may include one or more of the following: line identification information, line number, line name, line type, voltage level, starting switch identification information, starting station identification information, ending switch identification information, ending station identification information, commissioning time, decommissioning time, operating status, asset nature, management unit, line length, line model, line region information and line resource identification information;

[0193] By way of example, the switch data may include one or more of the following: switch identification information, switch number, switch name, switch type, switch voltage, switch-to-line, switch-to-station, switch location, and switch resource identification information;

[0194] For example, the above-mentioned substation data may include one or more of the following: substation identification information, substation number, substation name, substation type, asset nature, voltage level, substation capacity, substation management unit information, substation region information and substation resource identification information;

[0195] For example, the power plant data may include one or more of the following: power plant identification information, power plant number, power plant name, voltage level and metering point identification information;

[0196] For example, the above bus data may include one or more of the following: bus identification information, bus number, bus name, bus voltage, bus station, bus resource identification information;

[0197] For example, the main transformer data may include one or more of the following: main transformer identification information, main transformer number, main transformer name, main transformer voltage, main transformer capacity, main transformer station and main transformer resource identification information;

[0198] For example, the distribution transformer data may include one or more of the following: distribution transformer identification information, distribution transformer number, distribution transformer name, distribution transformer type, asset nature, distribution transformer-affiliated line, distribution transformer rated capacity, and distribution transformer resource identification information;

[0199] For example, the above-mentioned measuring point data may include one or more of the following: the relationship between the measuring point and the switch, the relationship between the measuring point and the measuring point device, and the measuring point location attribute;

[0200] For example, the above-mentioned dedicated line data may include one or more of the following: dedicated line user identification information, dedicated line user number, dedicated line user name, voltage level, dedicated line station, dedicated line line;

[0201] For example, the above-mentioned distributed power data may include one or more of the following: distributed power user identification information, distributed power user number, distributed power user name and distributed power metering point identification information;

[0202] For example, the above-mentioned office electricity consumption data may include one or more of the following: office electricity user identification information, office electricity user number, office electricity user name, office electricity line and office electricity metering point identification information;

[0203] For example, the above user data may include one or more of the following: user identification information, user number, user name, user nature, voltage level, user start / stop status;

[0204] For example, the above-mentioned structural data may include one or more of the following: power grid topology data, switch status data and daily electricity data of collection points.

[0205] In one implementation, the data verification module may include:

[0206] The feature extraction submodule is used to extract the time series features of the operation data of the distribution network based on the operation mechanism of the power grid, and obtain the time series feature data corresponding to the operation data;

[0207] The time series feature data is checked for time series consistency by using a consistency check method to obtain time series data without abnormalities and time series data with abnormalities corresponding to the time series feature data;

[0208] Extract abnormal power from abnormal time series data, locate abnormal nodes and time points, and generate abnormal power data.

[0209] In one implementation, the above-mentioned abnormal classification module may include:

[0210] A null value check submodule is used to perform null value check on abnormal power data by using a range matching method, and to divide the abnormal power data into null value power data and non-null value power data;

[0211] The reverse check submodule is used to perform reverse check on the non-empty power data by using a threshold method, and divide the non-empty power data into reverse power data and non-reverse power data;

[0212] The jump check submodule is used to perform jump check on the non-reverse power data through the conditional logic method, and divide the non-reverse power data into jump power data and non-jump power data.

[0213] In one implementation, the data repair module may include:

[0214] A model selection submodule is used to select a power balance model corresponding to the electrical equipment to which the abnormal power data belongs according to the abnormality type;

[0215] The abnormality repair submodule is used to repair the abnormal power data by using the power balance model corresponding to the electrical equipment to which the abnormal power data belongs.

[0216] In one implementation, the power data repair system may further include: a model building module, specifically used to:

[0217] Obtain switch status change information of the distribution network;

[0218] Construct the topological relationship of the distribution network based on the switch status change information;

[0219] According to the topological relationship, the power balance model of the distribution network is constructed.

[0220] In this implementation, the above-mentioned model building module may include:

[0221] The regional division submodule is used to divide the distribution network into regions according to the switch state change information using the depth-first search algorithm to obtain the switch state change information of the distribution network corresponding to different electrical regions;

[0222] The connection relationship confirmation submodule is used to determine the connection relationship between each node and edge in different electrical areas through the adjacency matrix method according to the switch state change information of the distribution network in different electrical areas;

[0223] The topology relationship construction submodule is used to construct the topology relationship of the distribution network according to the connection relationship between each node and edge in different electrical areas.

[0224] In this implementation, the above-mentioned model building module may also include:

[0225] The line loss rate calculation submodule is used to calculate the line loss rate of each electrical device in the distribution network according to the topological relationship and the acquired input power data and output power data of the distribution network;

[0226] The balance model building submodule is used to build a power balance model for each electrical device according to the line loss rate of each electrical device;

[0227] Among them, electrical equipment includes one or more of the following: transmission lines, distribution lines, transformers and busbars.

[0228] In one implementation, the power data repair system may further include: a power deduction module, specifically used for:

[0229] Obtain nodes in the distribution network that do not have data collection devices installed;

[0230] The power balance model is used to deduce the power of nodes without data collection devices installed, and the power data corresponding to the nodes without data collection devices installed are obtained.

[0231] Embodiment 3:

[0232] like Figure 5 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0233] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a power data repair method based on the power grid operation mechanism in the above-mentioned embodiment.

[0234] Embodiment 4:

[0235] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the storage medium here may include both a built-in storage medium in an electronic device and an extended storage medium supported by the electronic device. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions may be one or more execution programs (including program codes). It should be noted that the storage medium here may be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a method for repairing power data based on the operation mechanism of the power grid in the above embodiment.

[0236] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0237] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0238] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0239] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0240] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims to be approved.

Claims

1. A method for repairing electric quantity data based on the operation mechanism of a power grid, characterized in that: include: Obtaining the operation data of the distribution network; Based on the operation mechanism of the power grid, the operation data of the distribution network is verified by using a consistency verification method to obtain abnormal power data of the distribution network; Using a rule-based classification method, the abnormal power data is classified to obtain the abnormal type to which the abnormal power data belongs; According to the abnormality type, the abnormal power data is repaired using a pre-built power balance model.

2. The method according to claim 1, characterized in that The power balance model includes the following construction process: Obtaining switch status change information of the distribution network; Constructing a topological relationship of the distribution network according to the switch state change information; According to the topological relationship, an electricity balance model of the distribution network is constructed.

3. The method according to claim 2, characterized in that The constructing the topological relationship of the distribution network according to the switch state change information includes: According to the switch state change information, the distribution network is divided into regions using a depth-first search algorithm to obtain switch state change information corresponding to different electrical regions of the distribution network; According to the switch state change information of the distribution network in different electrical areas, the connection relationship between each node and edge in different electrical areas is determined by an adjacency matrix method; The topological relationship of the distribution network is constructed according to the connection relationship between each node and the edge in the different electrical areas.

4. The method according to claim 2, characterized in that The step of constructing the power balance model of the distribution network according to the topological relationship includes: Calculating the line loss rate of each electrical device in the distribution network according to the topological relationship and the acquired input power data and output power data of the distribution network; Constructing a power balance model for each electrical device according to the line loss rate of each electrical device; The electrical equipment includes one or more of the following: transmission lines, distribution lines, transformers and busbars.

5. The method according to claim 1 or 4, characterized in that The method of repairing the abnormal power data by using a pre-built power balance model according to the abnormality type includes: According to the abnormality type, selecting an electric quantity balance model corresponding to the electrical equipment to which the abnormal electric quantity data belongs; The abnormal electric quantity data is repaired by using an electric quantity balance model corresponding to the electrical equipment to which the abnormal electric quantity data belongs.

6. The method according to claim 1, characterized in that Based on the power grid operation mechanism, the operation data of the distribution network is verified by using a consistency verification method to obtain abnormal power data of the distribution network, including: Based on the operation mechanism of the power grid, extracting time series features of the operation data of the distribution network to obtain time series feature data corresponding to the operation data; Performing a time series consistency check on the time series feature data using a consistency check method to obtain normal time series data and abnormal time series data corresponding to the time series feature data; The abnormal power quantity is extracted from the abnormal time series data, the abnormal node and time point are located, and the abnormal power quantity data is generated.

7. The method according to claim 1, characterized in that The rule-based classification method is used to classify the abnormal power data to obtain the abnormal type to which the abnormal power data belongs, including: Performing null value verification on the abnormal electric quantity data by a range matching method, and dividing the abnormal electric quantity data into null value electric quantity data and non-null value electric quantity data; Performing a reverse check on the non-empty power data by a threshold method, and dividing the non-empty power data into reverse power data and non-reverse power data; The non-reverse power data is subjected to jump check by conditional logic method, and the non-reverse power data is divided into jump power data and non-jump power data.

8. The method according to any one of claims 1 to 7, characterized in that: The operation data of the distribution network includes one or more of the following: line data, switch data, substation data, power plant data, bus data, main transformer data, distribution transformer data, measuring point data, dedicated line data, distributed power supply data, office power consumption data, user data and structure data; The line data includes one or more of the following: line identification information, line number, line name, line type, voltage level, start switch identification information, start station identification information, end switch identification information, end station identification information, commissioning time, decommissioning time, operating status, asset nature, management unit, line length, line model, line region information and line resource identification information; The switch data includes one or more of the following: switch identification information, switch number, switch name, switch type, switch voltage, switch line, switch station, switch location and switch resource identification information; The substation data includes one or more of the following: substation identification information, substation number, substation name, substation type, asset nature, voltage level, substation capacity, substation management unit information, substation region information and substation resource identification information; The power plant data includes one or more of the following: power plant identification information, power plant number, power plant name, voltage level and metering point identification information; The bus data includes one or more of the following: bus identification information, bus number, bus name, bus voltage, bus station, bus resource identification information; The main transformer data includes one or more of the following: main transformer identification information, main transformer number, main transformer name, main transformer voltage, main transformer capacity, main transformer station and main transformer resource identification information; The distribution transformer data includes one or more of the following: distribution transformer identification information, distribution transformer number, distribution transformer name, distribution transformer type, asset nature, distribution transformer line, distribution transformer rated capacity and distribution transformer resource identification information; The measuring point data includes one or more of the following: the relationship between the measuring point and the switch, the relationship between the measuring point and the measuring point equipment, and the measuring point location attribute; The dedicated line data includes one or more of the following: dedicated line user identification information, dedicated line user number, dedicated line user name, voltage level, dedicated line station, dedicated line line; The distributed power data includes one or more of the following: distributed power user identification information, distributed power user number, distributed power user name and distributed power metering point identification information; The office electricity consumption data includes one or more of the following: office electricity user identification information, office electricity user number, office electricity user name, office electricity line and office electricity metering point identification information; The user data includes one or more of the following: user identification information, user number, user name, user nature, voltage level, user start / stop status; The structural data includes one or more of the following: power grid topology data, switch status data and daily power data of collection points.

9. The method according to claim 1, characterized in that After repairing the abnormal power data using a pre-built power balance model according to the abnormal type, the method further includes: Acquire a node in the distribution network where no data collection device is installed; The power balance model is used to deduce the power of the node without the collection device installed, so as to obtain the power data corresponding to the node without the collection device installed.

10. An electric quantity data repair system based on the operation mechanism of a power grid, characterized in that: include: A data acquisition module, used to acquire the operation data of the distribution network; A data verification module is used to verify the operation data of the distribution network based on the operation mechanism of the power grid by using a consistency verification method to obtain abnormal power data of the distribution network; An abnormal classification module is used to classify the abnormal power data using a rule-based classification method to obtain the abnormal type to which the abnormal power data belongs; The data repair module is used to repair the abnormal power data according to the abnormality type by using a pre-built power balance model.

Images