Power grid online safety analysis abnormal parameter identification and correction method and device

Abstract

The invention discloses a power grid online safety analysis abnormal parameter identification and correction method and device. The method comprises the following steps: acquiring a power grid line parameter real-time detection value, a transformer operation parameter real-time detection value, SCADA real-time measurement data and power grid operation state estimation data; performing multi-source data fusion based on the SCADA real-time measurement data and the power grid operation state estimation data to obtain a power estimation value output by a power generation device in a power grid and a power estimation value consumed by a power grid load; on the basis of the power grid line parameter real-time detection value, the transformer operation parameter real-time detection value, the power estimation value output by the power generation device and the power estimation value consumed by the power grid load, carrying out online safety analysis to obtain steady-state power flow operation state data; and based on the intelligent identification model, in combination with SCADA measurement data, power grid operation state estimation data and steady-state power flow operation state data, identifying whether the power grid line parameter real-time detection value and the transformer operation parameter real-time detection value are abnormal or not, and performing correction.

Description

Technical Field

[0001] The present invention relates to the field of power grid state detection, and in particular to a method and device for identifying and correcting abnormal parameters in online safety analysis of a power grid. Background Art

[0002] As energy transformation continues to deepen, the construction of new power systems is accelerating, and the power supply composition, grid form, load characteristics, technical foundation, and operation characteristics have undergone profound changes. The safety and stability of the power system are facing new situations, new requirements, and new challenges. As the material and technical foundations related to primary energy characteristics, power supply layout and functions, network scale and form, load structure and characteristics, and new technologies in the power system continue to undergo profound changes, the new generation of online safety analysis systems requires that all links must be completed quickly and accurately in a limited time. However, online safety analysis has many technical links and a long business chain. Any deviation in any link or parameter may cause errors in the online safety analysis results, resulting in the inability of online safety analysis to operate normally and effectively. The application of online safety analysis in power systems faces new problems and challenges. Therefore, studying the identification and correction methods of abnormal parameters in online safety analysis of power grids is of great significance to promoting the sustainable development and reliable operation of power systems.

[0003] At present, a few methods for identifying abnormal parameters of power grid equipment have been applied in power systems. Due to the wide sources of various model data and measured data in power systems, errors or errors will inevitably occur in the maintenance, transmission, storage, and processing of data. Existing studies have carried out line parameter identification based on different data or improved algorithms. Most methods ignore the impact of some abnormal data, and there is a situation of "not being able to cover". Online safety analysis only makes a simple judgment and inspection on abnormal data, and lacks effective means for identifying steady-state parameters of equipment under the influence of measurement errors and parameter errors. In addition, with the increasing emergence of time-varying nonlinearity, partial observability and random uncertainty on the source and load sides of new power systems, the operation mode of the power grid is complex and changeable, and the simulation scale is further expanded. Although existing studies have studied the reasons for non-convergence of power flow and line parameter identification, they have ignored the huge impact of some abnormal data. In the current online safety analysis, only a simple judgment and inspection is made on abnormal data, and there is still a lack of effective means for identifying steady-state parameters of equipment under the influence of measurement errors and parameter errors.

[0004] In the rapidly changing environment of new power system operation analysis scenarios, inaccurate static and dynamic parameters of equipment models will not only lead to large power flow errors, but may also cause problems such as non-convergence of power flow and abnormal termination of simulation analysis calculations, affecting the accuracy and reliability of online safety analysis. It is urgent to carry out research on abnormal diagnosis and adaptive fault-tolerant technology for the entire process of online safety analysis, improve the accuracy and reliability of online safety analysis, and ultimately improve the practical level of online safety analysis calculations under new power systems. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and device for identifying and correcting abnormal parameters in online safety analysis of power grids. By combining multi-source data such as SCADA measurements and power grid operation status estimation, abnormal parameters are analyzed, identified and corrected, and rapid tracing and adaptive fault tolerance of key parameters and process anomalies are achieved, providing accuracy, timeliness and reliability of online safety analysis.

[0006] In order to solve the above technical problems, a first aspect of an embodiment of the present invention provides a method for identifying and correcting abnormal parameters of online safety analysis of a power grid, comprising the following steps:

[0007] Obtain real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, real-time SCADA measurement data and power grid operating status estimation data;

[0008] Based on the SCADA real-time measurement data and the power grid operation status estimation data, multi-source data fusion is performed to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load;

[0009] Based on the real-time detection value of the grid line parameter, the real-time detection value of the transformer operation parameter, the estimated value of the power output by the power generation device and the estimated value of the power consumed by the grid load, an online safety analysis steady-state power flow calculation is performed to obtain steady-state power flow operation status data;

[0010] Based on the intelligent recognition model of abnormal parameters of power grid equipment, combining the SCADA real-time measurement data and its historical measurement data, the power grid operation status estimation data and the steady-state power flow operation status data, identifying whether the real-time detection values ​​of power grid line parameters and the real-time detection values ​​of transformer operation parameters are abnormal;

[0011] Correction is performed based on the recognition results.

[0012] Further, the parameter types of the real-time detection values ​​of the power grid line parameters include: resistance, reactance and shunt susceptance of each line in the power grid;

[0013] The parameter types of the real-time detection value of the transformer operating parameters include: the transformer's exciting impedance, leakage impedance and tap position;

[0014] The parameter types of the power grid operation status estimation data include: each node voltage, each line power, transformer transmission power, power generation device output power and power grid load consumption power.

[0015] Furthermore, the grid operation status estimation data includes: the voltage amplitude and phase of each node in the grid, the active power and reactive power transmitted by each line, the active power and reactive power transmitted by the transformer, the active power and reactive power output by the power generation device, and the active power and reactive power consumed by the grid load.

[0016] Furthermore, the correction further includes:

[0017] Obtaining the corresponding steady-state power flow operation status data under abnormal parameter scenarios;

[0018] Calculate the Euclidean distance between the steady-state power flow operation status data and several groups of steady-state power flow operation status data in the training set of the intelligent recognition model for abnormal parameters of power grid equipment;

[0019] A set of steady-state power flow operation status data with the smallest Euclidean distance value is selected to correct the abnormal parameters.

[0020] Furthermore, the calculation formula of the Euclidean distance value is:

[0021]

[0022] Among them, the vector It is all the steady-state power flow operation status data in the training set; is the power flow operation state vector x under the current abnormal parameters and any The Euclidean distance of , i is the node number, and N is the number of grid nodes.

[0023] Furthermore, the method for identifying and correcting abnormal parameters of online safety analysis of a power grid further includes:

[0024] The credibility evaluation of parameter anomaly is performed, and the credibility evaluation formula is:

[0025]

[0026] Among them, θ is the credibility of parameter anomaly, 1 represents credibility, and 0 represents untrustworthiness; d0 is The minimum Euclidean distance threshold in .

[0027] Furthermore, the fusion method of the multi-source data fusion is:

[0028]

[0029] Among them, S i The active and reactive power variables of the power generation device and grid load at node i required for the online safety analysis of steady-state power flow calculation, i = 1, 2, ..., N, N is the total number of nodes in the grid; is the estimated power output of the power generation device of node i and the estimated power consumption of the grid load. Usually, the number of node power measurement values ​​is less than N. Here, i∈[1,2,…,M], M is the total number of measurement nodes in the grid, usually M<N; is the estimated output power of the power generation device at node i and the estimated power consumption of the grid load, where i∈[M+1,M+2,...,N].

[0030] Furthermore, the judgment formula for whether the real-time detection value of the power grid line parameter and the real-time detection value of the transformer operation parameter are abnormal is:

[0031]

[0032] Among them, κ ij is the parameter of the branch ij where the power grid line or transformer is located, ij is the node i and the node j connected to the branch respectively, ij=1, 2, ..., L, and i≠j, L is the total number of branches in the power grid; is the parameter of the real line and the branch ij where the transformer is located; α is the abnormal coefficient of the data;

[0033] When the value of the abnormal coefficient α is greater than 3, the parameter is judged to be abnormal.

[0034] Furthermore, the abnormal parameters intelligent recognition model of power grid equipment is a DNN deep neural network.

[0035] Accordingly, a second aspect of an embodiment of the present invention further provides a method and device for identifying and correcting abnormal parameters of an online safety analysis of a power grid, comprising:

[0036] A detection data acquisition module is used to obtain real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, SCADA real-time measurement data and power grid operating status estimation data;

[0037] A data fusion processing module, which is used to perform multi-source data fusion based on the SCADA real-time measurement data and the power grid operation status estimation data to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load;

[0038] A steady-state power flow calculation module, which is used to perform online safety analysis steady-state power flow calculation based on the real-time detection value of the power grid line parameter, the real-time detection value of the transformer operation parameter, the estimated power output of the power generation device and the estimated power consumed by the power grid load, to obtain steady-state power flow operation status data;

[0039] A data anomaly judgment module, which is used to identify whether the real-time detection values ​​of power grid line parameters and the real-time detection values ​​of transformer operating parameters are abnormal based on the intelligent recognition model of abnormal parameters of power grid equipment, combined with the SCADA real-time measurement data and its historical measurement data, the power grid operation status estimation data and the steady-state power flow operation status data;

[0040] The data anomaly correction module is used to perform correction according to the recognition result.

[0041] Correspondingly, the third aspect of an embodiment of the present invention also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned method for identifying and correcting abnormal parameters of online safety analysis of the power grid.

[0042] Correspondingly, the fourth aspect of the embodiments of the present invention further provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for identifying and correcting abnormal parameters of online safety analysis of power grids.

[0043] The above technical solution of the embodiment of the present invention has the following beneficial technical effects:

[0044] 1. By acquiring real-time detection values ​​of power grid lines, transformers, and other aspects, as well as SCADA real-time measurement data and power grid operation status estimation data, and performing multi-source data fusion, various types of scattered data can be effectively integrated, so that the power status of power generation equipment output and power consumption of power grid load can be estimated more comprehensively and accurately, providing a reliable data basis for subsequent analysis and decision-making, and helping to accurately grasp the operation status of the power grid;

[0045] 2. Perform online safety analysis and steady-state flow calculation based on the integrated data to obtain steady-state flow operation status data. This enables accurate analysis of the power flow distribution and other conditions of the power grid under the current operation state, and early insight into possible safety hazards, such as line overload and voltage over-limit, so as to provide strong support for ensuring the safe and stable operation of the power grid and take corresponding measures in time for adjustment and optimization;

[0046] 3. By using the intelligent recognition model of abnormal parameters of power grid equipment and combining rich real-time and historical data for comprehensive judgment, it can intelligently identify whether there are abnormalities in the real-time detection values ​​of power grid line parameters and real-time detection values ​​of transformer operation parameters. Once an abnormality is found, it can be corrected in time, effectively avoiding power grid operation failures or inaccurate analysis results caused by abnormal parameters, improving the reliability of power grid operation and the accuracy of analysis results, and reducing operation and maintenance costs and potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a method for identifying and correcting abnormal parameters in online safety analysis of a power grid provided by an embodiment of the present invention;

[0048] Figure 2 It is an IEEE-39 node standard topology diagram provided by an embodiment of the present invention;

[0049] Figure 3a It is a schematic diagram of a model identification result of a typical line 1 parameter anomaly provided by an embodiment of the present invention;

[0050] Figure 3b It is a schematic diagram of the model recognition result of the typical line 5 parameter anomaly provided by the embodiment of the present invention;

[0051] Figure 3c It is a schematic diagram of the model recognition result of the typical line 9 parameter anomaly provided by the embodiment of the present invention;

[0052] Figure 3d It is a schematic diagram of the model recognition result of the typical line 13 parameter anomaly provided by the embodiment of the present invention;

[0053] Figure 4 is a schematic diagram of correction results of abnormal parameters provided by an embodiment of the present invention;

[0054] Figure 5 It is a block diagram of a module of an abnormal parameter identification and correction device for online safety analysis of a power grid provided by an embodiment of the present invention.

[0055] Reference numerals:

[0056] 1. Detection data acquisition module, 2. Data fusion processing module, 3. Steady-state power flow calculation module, 4. Data anomaly judgment module, 5. Data anomaly correction module. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0058] Please refer to Figure 1 A first aspect of an embodiment of the present invention provides a method for identifying and correcting abnormal parameters of an online safety analysis of a power grid, comprising the following steps:

[0059] Step S100, obtaining real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, SCADA real-time measurement data and power grid operating status estimation data.

[0060] Specifically, the parameter types of the real-time detection values ​​of the power grid line parameters include: the resistance, reactance and shunt susceptance of each line in the power grid; the parameter types of the real-time detection values ​​of the transformer operation parameters include: the magnetizing impedance, leakage impedance and tap position of the transformer; the parameter types of the power grid operation status estimation data include: the voltage of each node, the power of each line, the transformer transmission power, the output power of the power generation device and the power consumption of the power grid load.

[0061] Furthermore, the grid operation status estimation data refers to the operation status of the entire grid estimated by mathematical methods such as least squares. The obtained operation status data include the voltage amplitude and phase of each node in the grid, the active power and reactive power transmitted by each line, the active power and reactive power transmitted by the transformer, the active power and reactive power output by the power generation device, and the active power and reactive power consumed by the grid load.

[0062] The SCADA (Supervisory Control and Data Acquisition) system can collect data from many devices and nodes in the power grid in real time, including the current, voltage, switch status and other information of each line. This information directly reflects the actual operation of each monitoring point of the power grid at the current moment; the above information has high real-time performance and can quickly provide feedback on various changes in the power grid. For example, when the load of a line in the power grid suddenly increases, the SCADA system can detect the change in the current of the line almost instantly and transmit the relevant data.

[0063] Step S200, multi-source data fusion is performed based on the SCADA real-time measurement data and the power grid operation status estimation data to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load.

[0064] Specifically, the fusion method of multi-source data fusion is:

[0065]

[0066] Among them, S iThe active and reactive power variables of the power generation device and grid load at node i required for the online safety analysis of steady-state power flow calculation, i = 1, 2, ..., N, N is the total number of nodes in the grid; is the estimated power output of the power generation device of node i and the estimated power consumption of the grid load. Usually, the number of node power measurement values ​​is less than N. Here, i∈[1,2,…,M], M is the total number of measurement nodes in the grid, usually M<N; is the estimated output power of the power generation device at node i and the estimated power consumption of the grid load, where i∈[M+1,M+2,…,N].

[0067] Step S300, based on the real-time detection values ​​of grid line parameters, the real-time detection values ​​of transformer operating parameters, the estimated power output of the power generating device and the estimated power consumed by the grid load, an online safety analysis steady-state power flow calculation is performed to obtain steady-state power flow operating status data.

[0068] In addition, when performing the above-mentioned online safety analysis steady-state power flow calculation, the number of groups of steady-state power flow operation status data G ≥ 1000 groups is usually selected.

[0069] Step S400, based on the intelligent recognition model of abnormal parameters of power grid equipment, combined with SCADA real-time measurement data and its historical measurement data, power grid operation status estimation data and steady-state power flow operation status data, identify whether the real-time detection values ​​of power grid line parameters and real-time detection values ​​of transformer operation parameters are abnormal, and correct them if abnormal.

[0070] Specifically, the judgment formula for whether the real-time detection value of the power grid line parameter and the real-time detection value of the transformer operation parameter are abnormal is:

[0071]

[0072] Among them, κ ij is the parameter of the power grid line or the branch ij where the transformer is located, ij is the node i and the node j connected to the branch where the transformer is located, ij = 1, 2, ..., L, and i ≠ j, L is the total number of branches in the power grid; are the parameters of the real line and transformer at ij; α is the abnormal coefficient of the data.

[0073] The training set of the model contains a sufficient number of normal parameter groups and abnormal parameter groups to meet the statistical law's requirements for data volume, thereby ensuring the effectiveness and reliability of model training. Among them, normal parameters refer to the line and transformer equipment parameters that have been entered into the SCADA system, and abnormal parameters are composed of two parts. The first part is based on the deep experience of field experts and engineers and industry standards to clearly identify abnormal parameters. These parameters directly reflect the various abnormal situations that may be encountered in actual operation. The second part is to make up for the possible scarcity of abnormal data. The data set is screened twice to obtain. These abnormal parameters refer to the large deviation of parameters of a certain power grid equipment due to human negligence or other reasons.

[0074] Generally speaking, the deviation range of abnormal parameters usually exceeds 3 times the original parameter value of the real equipment, that is, when the value of the abnormal coefficient α is greater than 3, the parameter is judged to be abnormal.

[0075] Normal or abnormal parameters κ of multiple groups of power grid equipment ij , combined with the above-obtained active and reactive power variables S of the power generation devices and grid loads of each node i , perform DSA steady-state power flow calculation, and obtain the steady-state power flow operation status data x under each set of parameters i , i=1,2,…,N, including the voltage amplitude and phase of all nodes in the system, and the active and reactive power transmitted by the branches; wherein the present invention does not limit the specific calculation method of the steady-state power flow calculation.

[0076] Select appropriate thresholds to mark abnormal parameters of power grid equipment, that is, to determine the parameter κ of the line or transformer branch ij according to the 3σ criterion. ij Whether it is abnormal or not is marked as 1 or 0 respectively. The specific marking method is as follows:

[0077]

[0078] Where: Parameter κ representing the line or transformer branch ij ij normal; Parameter κ representing the line or transformer branch ij ij Abnormal; ∩ represents and, σ i ,σ j is the power flow operation status data x of the nodes on both sides of any power grid equipment i and x j The mean and variance of .

[0079] In addition, the above thresholds can be further combined with data verified by manual experience and industry standards to improve the accuracy of the model.

[0080] The above-mentioned intelligent recognition model for abnormal parameters of power grid equipment specifically refers to the use of SCADA measurement data State estimation data and DSA online power flow calculation data x i As input, all branch parameters κ ij Is the exception output Get the artificial intelligence model f AI as follows:

[0081]

[0082] Where: Output is the branch parameter κ ij Is it abnormal? 1 represents κ ij Normal, 0 represents kappa ij abnormal.

[0083] Optionally, the SCADA system historical data includes complete records of historical measurement data for no less than 1 year.

[0084] Step S500: perform correction according to the recognition result.

[0085] Furthermore, after the correction in step S500, the method further includes:

[0086] Step S610, obtaining corresponding steady-state power flow operation status data under abnormal parameter scenario.

[0087] Step S620, calculating the Euclidean distance values ​​between the steady-state power flow operation status data and several groups of steady-state power flow operation status data in the training set of the intelligent recognition model for abnormal parameters of power grid equipment.

[0088] Step S630: Select a group of steady-state power flow operation status data with the smallest Euclidean distance value to correct the abnormal parameters.

[0089] For the abnormal parameters of the real-time detection values ​​of the power grid line parameters and the real-time detection values ​​of the transformer operation parameters that are identified, the Euclidean distance between the power flow operation status data and all G groups of data under the abnormal parameter scenario is calculated, and then the credibility of the parameter anomaly is evaluated. The power grid equipment parameters of the group of data samples with the smallest distance are selected to correct the unreliable abnormal parameters.

[0090] Specifically, the calculation formula for the Euclidean distance value is:

[0091]

[0092] Among them, the vector It is all the steady-state power flow operation status data in the training set; is the power flow operation state vector x under the current abnormal parameters and any The Euclidean distance of , i is the node number, and N is the number of grid nodes.

[0093] Furthermore, the method for identifying and correcting abnormal parameters of online safety analysis of power grid also includes:

[0094] Conduct credibility evaluation of parameter anomalies. The credibility evaluation formula is:

[0095]

[0096] Among them, θ is the credibility of parameter anomaly, 1 represents credibility, and 0 represents untrustworthiness; d0 is The minimum Euclidean distance threshold in is usually selected as 0.0001.

[0097] Select the power grid equipment parameters of the group of data samples with the smallest distance and correct the unreliable abnormal parameters:

[0098]

[0099] Where: κ i ' j is the branch abnormality parameter κ ij Correction value of for The sample corresponding to the minimum Euclidean distance The original grid equipment parameters.

[0100] The above identification and correction method comprehensively integrates the real-time detection values ​​of power grid lines and transformers, as well as multi-source information such as SCADA real-time measurement data and power grid operation status estimation data, and accurately obtains the power estimation values ​​of the power generation device output and power grid load consumption in the power grid through multi-source data fusion, providing a reliable basis for subsequent analysis; based on rich data, steady-state power flow calculation can accurately obtain steady-state power flow operation status data, thereby achieving an in-depth understanding of the power grid operation status. In addition, by using the intelligent recognition model of abnormal parameters of power grid equipment, combined with SCADA real-time and historical measurement data, power grid operation status estimation data and steady-state power flow operation status data, it can intelligently and accurately identify the abnormal conditions of the real-time detection values ​​of power grid line and transformer operation parameters, and make corrections in time, thereby improving the safety and reliability of power grid operation, effectively reducing the risk of power grid failures caused by parameter abnormalities, and at the same time improving the efficiency and accuracy of power grid operation analysis and maintenance, providing a strong guarantee for the stable and efficient operation of the power grid.

[0101] Optionally, the abnormal parameter intelligent recognition model of power grid equipment is a DNN deep neural network.

[0102] The above recognition and correction process is described below by taking a specific implementation of an embodiment of the present invention as an example:

[0103] Step 1: Data collection and multi-source fusion

[0104] The data of the power grid system comes from the resistance, reactance and shunt susceptance of each line in the power grid, the exciting impedance, leakage impedance and tap position of the transformer, the voltage of each node, the power of each line, the transmission power of the transformer, the output power of the power generation device and the power consumption of the power grid load. These data come from different data sources such as sensors, SCADA systems, and historical databases, forming the basis for the identification and correction of abnormal parameters of the power grid. These data sources may use different encoding standards. For subsequent data processing and analysis, it is first necessary to convert these multi-source data into a unified format. The specific operation is to convert all data to the same encoding standard (UTF-8), establish a data mapping table for each data source, map the original data fields to the corresponding fields of the unified data model, and save the converted data.

[0105] Step 2: Data verification and formatting

[0106] Given that data comes from diverse information sources, especially text data (such as model identification and name details of equipment such as lines and transformers in power grid systems), the data storage process often faces the challenge of inconsistent formats. To ensure the excellence of data quality, this step introduces a unified formatting mechanism, which aims to standardize the multiple components of equipment model information, such as transformer names and voltage levels, into the standardized format of "NN-XX / YY". This measure not only promotes the clarity and consistency of the internal structure of the data, but also lays a solid foundation for subsequent data processing and analysis.

[0107] Subsequently, a strict data verification process is implemented to ensure that all information complies with the preset format standards. Next, in order to optimize data characteristics and improve the learning efficiency and stability of the neural network model, a data normalization processing strategy is implemented. This strategy scales all feature dimensions to the same order of magnitude through precise mathematical transformations, effectively alleviating the gradient vanishing or exploding problems caused by feature scale differences, thereby accelerating the convergence speed of the training process and significantly enhancing the robustness and prediction accuracy of the model. In addition, data normalization further optimizes the distribution characteristics of the data, creating more favorable conditions for subsequent data mining and pattern recognition tasks.

[0108] Step 3: State Estimation

[0109] For an IEEE-39 node system, the grid equipment parameters and operating condition data preprocessed in step 1 are read into the program, and these data are used to estimate the state of the grid through the least square method to obtain the operating state data including the amplitude and phase of each node voltage, and the transmission active and reactive power of the line and transformer. The state estimation results are combined with the measured data of the power system data acquisition and monitoring control system to obtain the original data for the subsequent power flow calculation in this embodiment.

[0110] Step 4: Data selection and DSA power flow calculation

[0111] Combined with the parameters of the power grid line and the power data of the power generation device and the power grid load, online safety analysis steady-state power flow calculation is carried out to obtain the voltage amplitude and phase of all nodes in the system, as well as the active and reactive power data transmitted by the branch.

[0112] In order to ensure the statistical regularity and subsequent training effect, this embodiment selects more than 1,000 sets of data, including data in normal and abnormal states. Normal data refers to the line and transformer equipment parameters set according to the common range in engineering practice and the typical values ​​recorded by the SCADA system, while abnormal data mainly comes from data clearly identified by experts and engineers based on deep experience and industry standards, supplemented by data obtained by secondary screening using the abnormal parameter judgment formula. Combining the two parts of abnormal data can ensure that the model can learn the characteristics of extreme abnormal situations.

[0113] Step 5: Establishment of artificial intelligence model for abnormal parameter identification

[0114] Using the selected data set in step 4, an intelligent recognition model for abnormal parameters of power grid equipment based on artificial intelligence is established, and a prediction model is constructed using a DNN deep neural network. State estimation data and DSA online power flow calculation data x i As input, whether all branch parameters are abnormal is output to obtain the artificial intelligence model.

[0115] Combination Figure 2 , Figure 3a , Figure 3b , Figure 3c and Figure 3d The results of parameter anomaly identification of some lines are shown, among which typical lines 1, 5, 9, and 13 represent Figure 2 In the data set, there are 25,316 samples in total for the lines between nodes 0-38, 2-17, 4-7, and 7-8, and only 11 of them are misjudged. The correct recognition rate of parameter anomalies reaches more than 99%. It can be seen that the present invention can use the artificial intelligence model to recognize line anomalies with high recognition accuracy.

[0116] In order to characterize the accuracy of the artificial intelligence model recognition, this implementation selects a part of the data that has completed parameter anomaly annotation as a test set for training. The training results are shown in Table 1 below.

[0117] Table 1 Artificial intelligence model parameter recognition effect table

[0118]

[0119]

[0120] For dataset 2, which is significantly different from the training set, although the recognition difficulty increases, it still maintains extremely high recognition accuracy. Among the total 25,100 samples, the number of misjudged samples is 426, which means a correct recognition rate of 98.30%. This verifies that the model is still highly stable and effective when facing datasets with significant differences.

[0121] Step 6: Abnormal parameter correction.

[0122] For the identified abnormal parameters of power grid equipment, the Euclidean distance calculation formula is used to calculate the Euclidean distance between the flow operation status data and all data under the abnormal parameter scenario, and then the credibility of the parameter anomaly is evaluated according to the credibility evaluation formula, and the power grid equipment parameters of the group of data samples with the smallest distance are selected to correct the unreliable abnormal parameters.

[0123] The identification and correction method in the above embodiment is data-driven and can make full use of a large amount of historical and online real-time data to identify abnormal parameters in the power grid, which helps to improve the accuracy of the power system model, thereby making the theoretical analysis closer to the actual operation situation; and through automated and intelligent abnormal parameter identification and correction, it can reduce dependence on manual monitoring, reduce labor costs, and improve operation and maintenance efficiency; finally, the introduction and application of the above method has promoted the development of the power system towards intelligence and automation, and provided strong technical support for the construction of new power systems.

[0124] In addition, if Figure 4 As shown, in a specific application scenario, the initial resistance value of a line is measured to be 10.4742Ω, which deviates significantly from the normal or expected range and is considered abnormally large. Based on the abnormal parameter identification and correction method for online safety analysis of the power grid in the present invention, the resistance value of the line is accurately corrected. After correction, the resistance value of the line is significantly reduced to 1.792176Ω. The above process not only effectively eliminates the abnormally large resistance value, but also returns the resistance value to a reasonable and stable range, thereby ensuring the accuracy and reliability of the power grid operation.

[0125] Accordingly, please refer to Figure 5 The second aspect of the embodiment of the present invention further provides a device for identifying and correcting abnormal parameters of online safety analysis of a power grid, comprising:

[0126] Detection data acquisition module 1, which is used to obtain real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, SCADA real-time measurement data and power grid operating status estimation data;

[0127] The data fusion processing module 2 is used to perform multi-source data fusion based on the SCADA real-time measurement data and the power grid operation status estimation data to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load;

[0128] Steady-state power flow calculation module 3, which is used to perform online safety analysis steady-state power flow calculation based on real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operation parameters, power estimation values ​​output by power generation devices, and power estimation values ​​consumed by power grid loads, and obtain steady-state power flow operation status data;

[0129] The data anomaly judgment module 4 is used to identify whether the real-time detection values ​​of the power grid line parameters and the real-time detection values ​​of the transformer operating parameters are abnormal based on the intelligent recognition model of abnormal parameters of the power grid equipment, combined with the SCADA real-time measurement data and its historical measurement data, the power grid operation status estimation data and the steady-state power flow operation status data;

[0130] The data anomaly correction module 5 is used to perform correction according to the recognition result.

[0131] Correspondingly, the third aspect of an embodiment of the present invention also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned method for identifying and correcting abnormal parameters of online safety analysis of the power grid.

[0132] Correspondingly, the fourth aspect of the embodiments of the present invention further provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for identifying and correcting abnormal parameters of online safety analysis of power grids.

[0133] The embodiment of the present invention aims to protect a method for identifying and correcting abnormal parameters of online safety analysis of power grids, including the following steps: obtaining real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, SCADA real-time measurement data, and power grid operating status estimation data and power grid load; performing multi-source data fusion based on SCADA real-time measurement data and power grid operating status estimation data to obtain power estimation values ​​output by power generation devices in the power grid and power estimation values ​​consumed by power grid loads; performing online safety analysis steady-state flow calculation based on real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, power estimation values ​​output by power generation devices in the power grid, and power estimation values ​​consumed by power grid loads to obtain steady-state flow operating status data; based on the intelligent recognition model of abnormal parameters of power grid equipment, combined with SCADA real-time measurement data and its historical measurement data, power grid operating status estimation data, and steady-state flow operating status data, identifying whether the real-time detection values ​​of power grid line parameters and real-time detection values ​​of transformer operating parameters are abnormal; and making corrections based on the recognition results. The above technical solution has the following effects:

[0134] 1. By acquiring real-time detection values ​​of power grid lines, transformers, and other aspects, as well as SCADA real-time measurement data and power grid operation status estimation data, and performing multi-source data fusion, various types of scattered data can be effectively integrated, so that the power status of power generation equipment output and power consumption of power grid load can be estimated more comprehensively and accurately, providing a reliable data basis for subsequent analysis and decision-making, and helping to accurately grasp the operation status of the power grid;

[0135] 2. Perform online safety analysis and steady-state flow calculation based on the integrated data to obtain steady-state flow operation status data. This enables accurate analysis of the power flow distribution and other conditions of the power grid under the current operation state, and early insight into possible safety hazards, such as line overload and voltage over-limit, so as to provide strong support for ensuring the safe and stable operation of the power grid and take corresponding measures in time for adjustment and optimization;

[0136] 3. By using the intelligent recognition model of abnormal parameters of power grid equipment and combining rich real-time and historical data for comprehensive judgment, it can intelligently identify whether there are abnormalities in the real-time detection values ​​of power grid line parameters and real-time detection values ​​of transformer operation parameters. Once an abnormality is found, it can be corrected in time, effectively avoiding power grid operation failures or inaccurate analysis results caused by abnormal parameters, improving the reliability of power grid operation and the accuracy of analysis results, and reducing operation and maintenance costs and potential risks.

[0137] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0138] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0139] 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.

[0140] 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.

[0141] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying and correcting abnormal parameters in online safety analysis of power grid, characterized in that: The steps include: Obtain real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, real-time SCADA measurement data and power grid operating status estimation data; Based on the SCADA real-time measurement data and the power grid operation status estimation data, multi-source data fusion is performed to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load; Based on the real-time detection value of the grid line parameter, the real-time detection value of the transformer operation parameter, the estimated value of the power output by the power generation device and the estimated value of the power consumed by the grid load, an online safety analysis steady-state power flow calculation is performed to obtain steady-state power flow operation status data; Based on the intelligent recognition model of abnormal parameters of power grid equipment, combining the SCADA real-time measurement data and its historical measurement data, the power grid operation status estimation data and the steady-state power flow operation status data, identifying whether the real-time detection values ​​of power grid line parameters and the real-time detection values ​​of transformer operation parameters are abnormal; Correction is performed based on the recognition results.

2. The method for identifying and correcting abnormal parameters of online safety analysis of power grid according to claim 1, characterized in that: The parameter types of the real-time detection values ​​of the power grid line parameters include: resistance, reactance and shunt susceptance of each line in the power grid; The parameter types of the real-time detection value of the transformer operating parameters include: the transformer's exciting impedance, leakage impedance and tap position; The parameter types of the power grid operation status estimation data include: each node voltage, each line power, transformer transmission power, power generation device output power and power grid load consumption power.

3. The method for identifying and correcting abnormal parameters of online safety analysis of power grid according to claim 2, characterized in that: The grid operation status estimation data includes: voltage amplitude and phase of each node in the grid, active power and reactive power transmitted by each line, active power and reactive power transmitted by the transformer, active power and reactive power output by the power generation device, and active power and reactive power consumed by the grid load.

4. The method for identifying and correcting abnormal parameters in online safety analysis of power grid according to claim 1, characterized in that: The correction also includes: Obtaining the corresponding steady-state power flow operation status data under abnormal parameter scenarios; Calculate the Euclidean distance between the steady-state power flow operation status data and several groups of steady-state power flow operation status data in the training set of the intelligent recognition model for abnormal parameters of power grid equipment; A set of steady-state power flow operation status data with the smallest Euclidean distance value is selected to correct the abnormal parameters.

5. The method for identifying and correcting abnormal parameters in online safety analysis of power grid according to claim 4, characterized in that: The calculation formula of the Euclidean distance value is: Among them, the vector It is all the steady-state power flow operation status data in the training set; is the power flow operation state vector x under the current abnormal parameters and any The Euclidean distance of , i is the node number, and N is the number of grid nodes.

6. The method for identifying and correcting abnormal parameters in online safety analysis of power grid according to claim 5, characterized in that: Also includes: The credibility evaluation of parameter anomaly is performed, and the credibility evaluation formula is: Among them, θ is the credibility of parameter anomaly, 1 represents credibility and 0 represents untrustworthiness; d0 is The minimum Euclidean distance threshold in .

7. The method for identifying and correcting abnormal parameters in online safety analysis of power grid according to claim 1, characterized in that: The fusion method of the multi-source data fusion is: Among them, S i The active and reactive power variables of the power generation device and grid load at node i required for the online safety analysis of steady-state power flow calculation, i = 1, 2, ..., N, N is the total number of nodes in the grid; is the estimated power output of the power generation device of node i and the estimated power consumption of the grid load. Usually, the number of node power measurement values ​​is less than N. Here, i∈[1,2,…,M], M is the total number of measurement nodes in the grid, usually M<N; is the estimated output power of the power generation device at node i and the estimated power consumption of the grid load, where i∈[M+1,M+2,...,N].

8. The method for identifying and correcting abnormal parameters in online safety analysis of power grid according to claim 1, characterized in that: The judgment formula for whether the real-time detection value of the power grid line parameter and the real-time detection value of the transformer operation parameter are abnormal is: Among them, κ ij is a parameter of a power grid line or a branch ij where a transformer is located, ij is a node i and a node j respectively connected to the branch where the transformer is located, ij=1, 2, ..., L, and i≠j, and L is the total number of branches in the power grid; is the parameter of the real line and the branch ij where the transformer is located; α is the abnormal coefficient of the data; When the value of the abnormal coefficient α is greater than 3, the parameter is judged to be abnormal.

9. The method for identifying and correcting abnormal parameters in online safety analysis of a power grid according to any one of claims 1 to 8, characterized in that: The abnormal parameters intelligent recognition model of power grid equipment is a DNN deep neural network.

10. A device for identifying and correcting abnormal parameters in online safety analysis of power grid, characterized in that: include: A detection data acquisition module is used to obtain real-time detection values ​​of power grid line parameters, real-time detection values ​​of transformer operating parameters, SCADA real-time measurement data and power grid operating status estimation data; A data fusion processing module, which is used to perform multi-source data fusion based on the SCADA real-time measurement data and the power grid operation status estimation data to obtain the power estimation value output by the power generation device in the power grid and the power estimation value consumed by the power grid load; A steady-state power flow calculation module, which is used to perform online safety analysis steady-state power flow calculation based on the real-time detection value of the power grid line parameter, the real-time detection value of the transformer operation parameter, the estimated power output of the power generation device and the estimated power consumed by the power grid load, to obtain steady-state power flow operation status data; A data anomaly judgment module, which is used to identify whether the real-time detection values ​​of power grid line parameters and the real-time detection values ​​of transformer operating parameters are abnormal based on the intelligent recognition model of abnormal parameters of power grid equipment, combined with the SCADA real-time measurement data and its historical measurement data, the power grid operation status estimation data and the steady-state power flow operation status data; The data anomaly correction module is used to perform correction according to the recognition result.

Images