Emergency strategy determination method and device for low-voltage power failure, equipment, medium and product

Abstract

The invention provides a low-voltage power failure emergency strategy determination method and device, equipment, a medium and a product. The method comprises the steps of obtaining a power data set of distributed energy before power failure of a low-voltage transformer area; performing data division processing on the power data set to obtain a training data matrix and a test data matrix; constructing a fuzzy set membership matrix according to a fuzzy domain theory and the training data matrix; obtaining a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix; and comparing the power prediction result with a preset power threshold, and determining an emergency strategy of low-voltage power failure. According to the technical scheme, the power supply reliability and accuracy of the low-voltage power grid are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, equipment, medium, and product for determining an emergency strategy for a low-voltage power outage. Background Art

[0002] In the field of low-voltage power grids, low-voltage power outages have always been a key factor affecting the quality of power grid operation and users' electricity experience. Frequent low-voltage power outages have seriously weakened the reliability of power supply, reduced users' trust in power supply, and had a negative impact on commercial activities and social operations.

[0003] In the existing technology, low-voltage power outage response strategies usually use linear models to perform linear combinations of input features to predict outputs. Information such as response time, path cost, and resource waste rate can be comprehensively considered to derive a response strategy for low-voltage power outages.

[0004] However, the above response strategies cannot accurately identify the correlation of complex data, which reduces the accuracy of emergency response strategies. Summary of the Invention

[0005] The present application provides a method, device, equipment, medium and product for determining an emergency strategy for a low-voltage power outage, so as to solve the technical problem of inaccurate emergency strategy determination for a low-voltage power outage in the prior art.

[0006] In a first aspect, the present application provides a method for determining an emergency strategy for a low-voltage power outage, comprising:

[0007] Obtain the power dataset of distributed energy before the low-voltage power outage;

[0008] Performing data partitioning processing on the power data set to obtain a training data matrix and a test data matrix;

[0009] Constructing a fuzzy set membership matrix based on fuzzy domain theory and the training data matrix;

[0010] Obtaining a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix;

[0011] The power prediction result is compared with a preset power threshold to determine an emergency strategy for low-voltage power outage.

[0012] Furthermore, data partitioning is performed on the power data set to obtain a training data matrix and a test data matrix, including:

[0013] Based on the amount of data in the power data set, dividing the power data set into data segments to determine training data and test data;

[0014] According to the preset sliding window width, the training data and the test data are processed respectively to obtain a training data matrix and a test data matrix.

[0015] Furthermore, according to the fuzzy domain theory and the training data matrix, a fuzzy set membership matrix is ​​constructed, including:

[0016] generating fuzzy domains and fuzzy sets according to fuzzy domain theory and the training data matrix;

[0017] A fuzzy set membership matrix is ​​constructed according to the fuzzy domain and the fuzzy set.

[0018] Furthermore, according to the fuzzy set membership matrix and the test data matrix, a power prediction result of the distributed energy is obtained, including:

[0019] Determining a target fuzzy set that meets a preset membership requirement based on the membership data of each fuzzy set in the fuzzy set membership matrix;

[0020] Performing product quantization processing on the membership data to obtain activation data;

[0021] generating a fuzzy rule matrix and a triggerable rule matrix according to the activation data, the target fuzzy set and the test data matrix;

[0022] According to the fuzzy rule matrix and the triggerable rule matrix, a power prediction result of the distributed energy is obtained.

[0023] Furthermore, generating a fuzzy rule matrix and a triggerable rule matrix according to the activation data, the target fuzzy set and the test data matrix includes:

[0024] generating a rule matrix according to the activation data and the target fuzzy set;

[0025] Performing feature extraction processing on the rule matrix to obtain a fuzzy rule matrix;

[0026] Fuzzy set calculation processing is performed on the fuzzy rule matrix and the test data matrix to obtain a triggerable rule matrix.

[0027] Furthermore, according to the fuzzy rule matrix and the triggerable rule matrix, a power prediction result of the distributed energy is obtained, including:

[0028] Constructing a trigger matrix according to the fuzzy rule matrix and the triggerable rule matrix;

[0029] Performing feature extraction on the trigger matrix to obtain a target trigger matrix;

[0030] Calculating membership values ​​of the fuzzy rule matrix and the test data matrix to obtain a target membership matrix;

[0031] A power prediction result of the distributed energy is obtained according to the target trigger matrix and the membership matrix.

[0032] Furthermore, the power prediction result is compared with a preset power threshold to determine an emergency strategy for low-voltage power outage, including:

[0033] Comparing the power prediction result with a preset power threshold to obtain a power comparison result;

[0034] If the power comparison result indicates that the power prediction result is greater than or equal to the preset power threshold, determining that the first emergency strategy is a low-voltage power outage emergency strategy;

[0035] If the power comparison result indicates that the prediction result is less than a preset power threshold, the second emergency strategy is determined to be a low-voltage power outage emergency strategy.

[0036] In a second aspect, the present application provides a low-voltage power outage emergency strategy determination device, comprising:

[0037] The power data set acquisition module is used to obtain the power data set of distributed energy before the low-voltage area power outage;

[0038] A data matrix obtaining module is used to perform data partitioning processing on the power data set to obtain a training data matrix and a test data matrix;

[0039] A fuzzy set membership matrix construction module is used to construct a fuzzy set membership matrix based on fuzzy domain theory and the training data matrix;

[0040] A power prediction result obtaining module, configured to obtain a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix;

[0041] The emergency strategy determination module is used to compare the power prediction result with a preset power threshold to determine the emergency strategy for low-voltage power outage.

[0042] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0043] The memory stores computer-executable instructions;

[0044] The processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0046] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method as described in any one of the first aspects.

[0047] The method, device, equipment, medium and product for determining an emergency strategy for low-voltage power outages provided in the present application obtain a power data set of distributed energy before the low-voltage power outage; perform data partitioning on the power data set to obtain a training data matrix and a test data matrix; construct a fuzzy set membership matrix based on fuzzy domain theory and the training data matrix; obtain a power prediction result of the distributed energy based on the fuzzy set membership matrix and the test data matrix; compare the power prediction result with a preset power threshold to determine the means of the emergency strategy for the low-voltage power outage, thereby improving the power supply reliability of the low-voltage power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] Figure 1 A flowchart of a first embodiment of a method for determining an emergency strategy for a low-voltage power outage provided by this application;

[0050] Figure 2 A flow chart of a second embodiment of a method for determining an emergency strategy for a low-voltage power outage provided in this application;

[0051] Figure 3 A flowchart of a third embodiment of a method for determining an emergency strategy for a low-voltage power outage provided in this application;

[0052] Figure 4 A flowchart of a fourth embodiment of a method for determining an emergency strategy for a low-voltage power outage provided in this application;

[0053] Figure 5 A flowchart of a fifth embodiment of a method for determining an emergency strategy for a low-voltage power outage provided by this application;

[0054] Figure 6 A flowchart of a sixth embodiment of a method for determining an emergency strategy for a low-voltage power outage provided in this application;

[0055] Figure 7 A schematic diagram of power prediction results in the method for determining an emergency strategy for a low-voltage power outage provided in this application;

[0056] Figure 8A schematic diagram of the structure of the low-voltage power outage emergency strategy determination device provided in this application;

[0057] Figure 9 This is a schematic diagram of the structure of the electronic device provided in this application.

[0058] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0059] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0060] Existing emergency response mechanisms for low-voltage power outages rely primarily on manual experience or static rules, lacking accurate prediction and quantitative assessment of the output capacity of distributed energy resources (such as photovoltaics). Traditional methods are unable to dynamically perceive the local power supply capacity in the outage area, which can easily lead to delayed emergency response strategies, errors in load transfer arrangements, and even resource mismatches and prolonged power outages.

[0061] To address the above problems, this technical solution introduces a combination of fuzzy reasoning theory and power time series modeling, proposes a data matrix form based on sliding window construction, divides historical photovoltaic power data into training and test samples, and establishes a power prediction mechanism that can be dynamically learned and updated. It realizes the intelligent evaluation and strategy optimization of the auxiliary power supply capacity of distributed energy in low-voltage power outage events, effectively improving the accuracy and reliability of emergency response in power outage scenarios.

[0062] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] Figure 1 This is a flow chart of the first embodiment of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 1 As shown, including:

[0064] S101. Obtain a power dataset of distributed energy before a power outage in a low-voltage area.

[0065] The low-voltage substation refers to the low-voltage portion of the distribution network, supplying 380V / 220V and serving residential and commercial users. Distributed energy can refer to photovoltaic modules, which are independent of the central power grid and primarily generate electricity through photovoltaic modules. A power dataset represents a time series of photovoltaic power values ​​recorded at regular intervals over a period of time.

[0066] In this step, we first obtain the photovoltaic power data of a low-voltage area before the power outage, for example, collect the historical output of the last 1000 time points (the unit can be minutes or 5-minute intervals). Then store these raw data as a one-dimensional array P = [P1, P2, ..., P 1000 ] for the subsequent construction of training samples and test samples.

[0067] S102: Perform data partitioning on the power data set to obtain a training data matrix and a test data matrix.

[0068] The training data matrix is ​​a two-dimensional matrix used for model learning, with rows representing samples and columns representing power data points within a sliding window. Sliding windows are a technique for segmenting time series data into multiple overlapping subsequences to capture local variations. The test data matrix, used for model validation, has the same structure as the training matrix. This step forms a standard data structure that can be fed into fuzzy inference or deep learning models.

[0069] S103. Construct a fuzzy set membership matrix based on fuzzy domain theory and training data matrix.

[0070] The fuzzy domain maps power values ​​to a specific interval (e.g., 0-1) and is used to define the operational space of fuzzy concepts. Fuzzy sets represent concepts such as "low power," "medium power," and "high power" in fuzzy logic. The membership matrix TRIMFX represents the degree of membership of each input in each fuzzy set (ranging from 0-1).

[0071] Specifically, according to the fuzzy domain theory and the training data matrix, the fuzzy domain and fuzzy sets are generated;

[0072] According to the fuzzy domain and fuzzy set, the fuzzy set membership matrix is ​​constructed.

[0073] For example, first generate the fuzzy domain x, that is, linearly divide the strategy value into N3 points (such as N3 = 100); then construct the membership function, that is, for each fuzzy set (such as "low", "medium", "high"), define the corresponding triangular function; then beautiful each fuzzy threshold x i, calculate its membership value for each fuzzy set, and finally generate the fuzzy set membership matrix TRIMFX with a shape of (100, 3) for subsequent fuzzy rule matching.

[0074] S104. Obtain the power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix.

[0075] The fuzzy rule matrix (RRMM) contains the fuzzy rules with the highest activation strength in known training samples and their corresponding target outputs. The triggerable rule matrix (FRMM) is the set of fuzzy rules that can be activated from the test data. The activation strength is the product of the membership degrees of multiple input points, reflecting the confidence level of the rule.

[0076] Specifically, the processing of each sample (each row) in the test sample tex is as follows: the membership of each column data under each fuzzy set is calculated to obtain the fuzzy number fsc and membership value mgc; these fsc and mgc are permuted and combined to construct the fuzzy set number combination (FRMM) and the corresponding membership value combination (MGMM); then, the RRMM is matched to see if there is an identical rule head. If the match is successful, the product of the MGMM is used as the activation strength, and the final weighted prediction power value FC is calculated:

[0077]

[0078] Among them, K2 is the scaling factor and weights(d) is the product of each row of MGMM.

[0079] S105: Compare the power prediction result with the preset power threshold to determine the emergency strategy for low-voltage power outage.

[0080] Among them, the power threshold is a reference value for judging whether the current photovoltaic power is sufficient to maintain the operation of priority loads.

[0081] The first emergency strategy involves using backup power sources and photovoltaic restoration priority high loads to repair faults.

[0082] The second emergency strategy is to use backup power and be ready to transfer to high priority loads.

[0083] This embodiment constructs a complete low-voltage power outage emergency strategy decision-making process, combines distributed energy power prediction with fuzzy logic reasoning, realizes intelligent assessment of the local power supply capacity of the power grid, provides data-driven decision support for subsequent emergency response, and significantly improves the efficiency and accuracy of emergency strategy formulation in power outage scenarios.

[0084] Figure 2 This is a flow chart of the second embodiment of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 2 As shown, in Figure 1 Based on the embodiment, the power data set is partitioned to obtain a training data matrix and a test data matrix, including:

[0085] S201 : Based on the amount of data in the power data set, divide the power data set into data segments to determine training data and test data.

[0086] Data partitioning involves dividing the original time series into training and test sets based on quantity. The training set is used for model training, while the test set is used to verify prediction results. Training data is the sample used to learn prediction rules, while test data is the input for predicting future power consumption based on simulated power outages.

[0087] For example, the first N1=504 points from the photovoltaic power sequence (e.g., 1000 points) are taken as training data; the last N2=496 points are taken as test data; this division is based on the power outage time: the time before the power outage is used for training, and the time period near the power outage is used for verification.

[0088] S202: Process the training data and the test data according to the preset sliding window width to obtain a training data matrix and a test data matrix.

[0089] In this step, the sliding window moves one bit at a time in the time series to extract a subsequence of fixed length and construct a two-dimensional matrix input model.

[0090] Each row of the training data matrix and the test data matrix represents a power sequence window. There are a total of "number of sliding windows" rows and the number of columns is equal to the sliding window width.

[0091] Specifically, the sliding window width w can be defined as 5, that is, every five consecutive power data are considered as one input sample. For example, the training set is constructed from the first 504 points: 500 sliding window samples are extracted from P[0] to P

[503] , with each row being [P[i], P[i+1], ..., P[i+4]], resulting in a training matrix trx with a shape of (500, 5); the test set is constructed from the last 496 points. Similarly, the test matrix tex is obtained with a shape of (492, 5).

[0092] The embodiment of the present application introduces a sliding window mechanism to matrix the historical power data, so that the model can effectively capture the local features in the time series, enhance the consistency and interpretability of the training and test data, and thus improve the learning ability and generalization performance of the prediction model.

[0093] Figure 3 This is a flow chart of the third embodiment of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 3 As shown, in Figure 1Based on the embodiment, the power prediction results of distributed energy are obtained according to the fuzzy set membership matrix and the test data matrix, including:

[0094] S301 , determining a target fuzzy set that meets preset membership requirements based on the membership data of each fuzzy set in the fuzzy set membership matrix.

[0095] Among them, the target fuzzy set refers to the fuzzy subset that satisfies “close to a certain central value” in the membership value, such as “medium power”.

[0096] Exemplarily, the fuzzy domain length N3 is defined, where the fuzzy domain point x(i) satisfies:

[0097] x(i)∈[(trx(m,j)-KD), (trx(m,j)+K1)]

[0098] Then, all data indexes that meet the above conditions are found as similar historical states for the subsequent construction of fuzzy rules.

[0099] S302: Perform product quantization processing on the membership data to obtain activation data.

[0100] Among them, activation data refers to the degree to which a fuzzy rule is activated or triggered, usually expressed as a numerical weight, which is used to measure the contribution of the fuzzy rule to the prediction result.

[0101] In this step, the maximum membership fsmax in each fuzzy set is extracted from the fuzzy set membership matrix TRIMFX; then the product of this set of memberships is used as the activation intensity Rdmax, which is the final activation data.

[0102] S303: Generate a fuzzy rule matrix and a triggerable rule matrix according to the activation data, the target fuzzy set and the test data matrix.

[0103] Specifically, in this step, the fuzzy number matrix fsc and membership value mgc are generated from the first four columns of the test data matrix; then, the triggerable rule matrix FRMM is constructed based on all number combinations, and the membership matrix MGMM is generated from all membership combinations; these combinations are used for subsequent rule matching and output calculations.

[0104] S304: Obtain the power prediction result of the distributed energy according to the fuzzy rule matrix and the triggerable rule matrix.

[0105] In this step, each fuzzy combination in the triggerable rule matrix FRMM is traversed. A search is performed to determine whether there is a completely matching rule in the fuzzy rule matrix RRMM (with the same first few fuzzy numbers). If a match is found, the rule is considered "triggered" and its corresponding output value is extracted. The output values ​​are then weighted and summed using the activation weights in the membership matrix MGMM (i.e., the degree to which each rule is triggered in the current sample). Finally, a final power prediction result FC is obtained for each test sample.

[0106] The embodiments of the present application achieve fuzzy cognition and nonlinear modeling of complex power changes by constructing target fuzzy sets, activation data, fuzzy rules and trigger mechanisms. When faced with data uncertainty and photovoltaic output fluctuations, stable and reasonable prediction and reasoning results can still be made.

[0107] Figure 4 This is a flow chart of the fourth embodiment of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 4 As shown, in Figure 3 Based on the embodiment, a fuzzy rule matrix and a triggerable rule matrix are generated according to the activation data, the target fuzzy set and the test data matrix, including:

[0108] S401. Generate a rule matrix based on activation data and target fuzzy set.

[0109] The rule matrix RL refers to a set of fuzzy rules containing fuzzy condition combinations and activation intensities.

[0110] For example, the membership matrix TRIMFX is used to find the fuzzy set number (fsmax) corresponding to the maximum membership of each column from the training sample; then the membership value product Rdmax corresponding to the group number is calculated; wherein the construction form is:

[0111] RL=[fsmax_1, fsmax_2,..., fsmax_W, Rdmax]

[0112] Finally, multiple training samples generate multiple RL rules, preparing for subsequent matrix generation.

[0113] S402: Perform feature extraction processing on the rule matrix to obtain a fuzzy rule matrix.

[0114] Feature extraction refers to removing invalid or redundant items from the rule matrix to improve computational efficiency. The fuzzy rule matrix RRMM is the set of all valid fuzzy rules, where valid means the activation strength is non-zero.

[0115] For example, by removing zero elements from the rule matrix RL, a fuzzy rule matrix RRMM with a unified structure can be obtained, wherein the first W columns of each row of the fuzzy rule matrix RRMM are the fuzzy set numbers, and the W+1th column is the activation strength of the rule.

[0116] S403 , performing fuzzy set calculation processing on the fuzzy rule matrix and the test data matrix to obtain a triggerable rule matrix.

[0117] Among them, the triggerable rule matrix FRMM refers to the rule head set formed by the fuzzy number permutation and combination of the test sample input.

[0118] Specifically, take the first four columns of the test sample matrix tex (default W = 5, take the first 4), use the fuzzy membership function, and calculate each input x k Membership degree μ for different fuzzy sets kj , then extract the maximum membership fuzzy set number to form the fuzzy set fsc. Finally, the values ​​of each input position in the fuzzy set fsc are fully permuted and combined. All possible combinations can form the triggerable matrix FRMM, and the product of the membership corresponding to each group can form the target membership matrix RMGM.

[0119] The embodiment of the present application significantly improves the accuracy and execution efficiency of the fuzzy rule system by structuring the activation data and the target fuzzy set to generate a rule matrix, and performs feature extraction, redundancy removal and other processing, thereby avoiding the waste of computing resources caused by invalid rules.

[0120] Figure 5 This is a flow chart of the fifth embodiment of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 5 As shown, in Figure 3 Based on the embodiment, the power prediction results of distributed energy are obtained according to the fuzzy rule matrix and the triggerable rule matrix, including:

[0121] S501: Construct a trigger matrix according to the fuzzy rule matrix and the triggerable rule matrix.

[0122] The trigger matrix FR refers to the complete rule rows selected after the fuzzy rule matrix RRMM and the triggerable rule matrix FRMM are matched, including the output prediction value.

[0123] For example, for each row i1 in the triggerable rule matrix FEMM, it is determined whether:

[0124] FRMM[i1,:]==RRMM[j2,1:4],

[0125] If the match is successful, the entire row in the fuzzy rule matrix RRMM[j2] is copied to FR[i1,:]; finally, each row in the trigger matrix FR contains a complete fuzzy rule and output prediction value.

[0126] S502: Extract features from the trigger matrix to obtain a target trigger matrix.

[0127] The target trigger matrix refers to a matrix that contains only valid activation rules (i.e., triggered rules). Specifically, the trigger matrix FR is de-zeroed to obtain a valid trigger rule set, namely the target trigger rule matrix RFRM (with invalid rows removed). For example, each row of the target trigger rule matrix RFRM is [fuzzy number combination, activation strength].

[0128] S503: Calculate the membership values ​​of the fuzzy rule matrix and the test data matrix to obtain a target membership matrix.

[0129] The target membership matrix RMGM is a weighted membership matrix used to weight the target trigger rule matrix RFRM. For example, the original membership row corresponding to each rule row in the target trigger rule matrix RFRM is found; the corresponding row is extracted from the MGMM to form the target membership matrix RMGM, where the number of rows is the number of valid activation rules and the number of columns is the input dimension.

[0130] S504: Obtain the power prediction result of the distributed energy according to the target trigger matrix and the membership matrix.

[0131] The power prediction result FC is a numerical prediction output obtained by weighted fusion of the membership of the activation rules.

[0132] For example, the activation weights are first calculated using the formula: weights = prod(RMGM, axis = 1), then a scaling factor k2 (a random number between 0.8 and 1.2) is introduced, and finally the power is calculated using the formula:

[0133]

[0134] Among them, d represents the data sequence number of the activation strength weight matrix weights, that is, the activation strength of the rule.

[0135] The embodiment of the present application realizes a refined power prediction mechanism based on fuzzy reasoning by constructing a trigger matrix, matching effective rules, calculating membership weights and weightedly predicting output power, thereby improving the accurate grasp of local power supply capacity in power outage scenarios and supporting more reasonable emergency decision-making.

[0136] Figure 6 This is a flow chart of Example 6 of the method for determining the emergency strategy for low-voltage power outages provided by this application. Figure 6 As shown, in Figure 1 Based on the embodiment, the power prediction result is compared with the preset power threshold to determine the emergency strategy for low-voltage power outage, including:

[0137] S601: Compare the power prediction result with the preset power threshold to obtain a power comparison result.

[0138] The power threshold is a pre-set minimum safe power supply value, indicating whether the distributed energy resources are capable of supporting critical loads. In this embodiment, 2.5 kW can be set as the power threshold. The power comparison result is the comparison between the predicted value and the threshold, which is used to determine whether to enter the power control state.

[0139] For example, the power prediction result FC is used as a sliding prediction output value sequence, which represents the power situation in the next 30 minutes. The average value is then taken as the overall output power of the prediction window, that is, the prediction index. The formula is:

[0140]

[0141] If n=6, it corresponds to 30 minutes. Finally, the power is compared with the preset power threshold to determine whether the current photovoltaic module has the ability to independently supply power.

[0142] S602: If the power comparison result indicates that the power prediction result is greater than or equal to a preset power threshold, the first emergency strategy is determined to be a low-voltage power outage emergency strategy.

[0143] The first emergency strategy refers to the response measures when the photovoltaic system is capable of maintaining the critical load operation. In the embodiment of the present application, the first emergency strategy includes starting the backup power supply, using the photovoltaic module as an auxiliary energy source, and organizing fault repair and restoring the main power supply at the same time.

[0144] For example, when the power forecast is greater than or equal to a preset power threshold, the backup power source is set as the primary power source, and the photovoltaic modules are activated as backup power to supply the remaining loads. If power cannot be fully restored at this time, the photovoltaic system will take over the responsibility of supplying low-priority loads (such as non-essential users), and a repair team will be immediately dispatched to restore the main power line. By restoring power as much as possible through this process, the use of local distributed resources can be maximized.

[0145] S603: If the power comparison result indicates that the prediction result is less than a preset power threshold, the second emergency strategy is determined to be a low-voltage power outage emergency strategy.

[0146] The second emergency strategy is a response plan for when photovoltaic power is insufficient to maintain the load. In this embodiment of the application, the second emergency strategy includes activating the backup power supply to ensure the core load, simultaneously conducting a capacity assessment of the backup power supply line, and preparing to switch to a power transfer solution to provide power to high-priority users.

[0147] For example, when the power forecast result is less than the preset power threshold, the backup power source is activated, but the power supply range is limited, and only power is supplied to high-priority loads (such as hospitals, communication stations, and traffic lights). The backup line capacity scheduling system is then activated to check whether it can support more loads. If the assessment is feasible, load switching (transfer) is executed, such as transferring power from the upper medium-voltage line. The execution status of the load response plan is also recorded for dynamic adjustment. This step avoids large-scale power outages and protects core users through precise power scheduling in the event of power shortage.

[0148] The embodiment of the present application dynamically compares the prediction results with the preset thresholds and divides them into the first emergency strategy and the second emergency strategy, thereby establishing an emergency system on the grid side based on predictive intelligent hierarchical response, which can give priority to the operation of high-priority loads under the boundary conditions of power supply capacity and enhance the robustness and reliability of the system.

[0149] Figure 7 This is a schematic diagram of the power prediction results in the low-voltage power outage emergency strategy determination method provided by this application. Figure 7 As shown in the figure, the horizontal axis is the "data point", which represents each time segment in the test time series; the vertical axis is the "unit value of output power" (i.e., normalized power value), which is used to eliminate the influence of power amplitude differences and facilitate trend comparison; the solid line is the predicted value curve, which represents the photovoltaic power output estimated by this method based on the existing data after the power outage; the dotted line is the actual observation value in the test set (as a control value).

[0150] As can be seen from the figure, the predicted value curve and the true observation value curve are highly consistent and the trends match well, which proves that the prediction model proposed by this technical solution is highly accurate.

[0151] Specifically, the root mean square error (RMSE) of the prediction model corresponding to the figure in the evaluation was 0.1006, indicating that the average deviation of the prediction results was small; the closer the RMSE value is to 0, the more accurate the model is. The level of 0.1006 is already in a good range for photovoltaic output prediction.

[0152] This schematic diagram visually demonstrates how the proposed approach, through sliding window modeling, fuzzy reasoning, and deep learning optimization, can accurately track and predict the output trends of photovoltaic modules during low-voltage power outages. The high overlap between the predicted and true curves not only demonstrates the effectiveness of the algorithmic modeling, but also demonstrates the method's high prediction accuracy.

[0153] Therefore, the prediction results can serve as a reliable basis for generating intelligent emergency strategies after low-voltage power outages, ensuring that the power system has quantitative support during emergency dispatch and improving the reliability and intelligence level of low-voltage substation operations.

[0154] Figure 8 This is a structural diagram of a low-voltage power outage emergency strategy determination device provided in this application.

[0155] like Figure 8 As shown, the low-voltage power outage emergency strategy determination device 80 includes:

[0156] The power data set acquisition module 801 is used to acquire the power data set of distributed energy before the low-voltage area power outage;

[0157] The data matrix obtaining module 802 is used to perform data partitioning processing on the power data set to obtain a training data matrix and a test data matrix;

[0158] A fuzzy set membership matrix construction module 803 is used to construct a fuzzy set membership matrix based on fuzzy domain theory and training data matrix;

[0159] The power prediction result obtaining module 804 is used to obtain the power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix;

[0160] The emergency strategy determination module 805 is used to compare the power prediction result with the preset power threshold to determine the emergency strategy for low-voltage power outage.

[0161] Furthermore, the data matrix obtaining module 802 is further specifically configured to:

[0162] Based on the amount of data in the power data set, the power data set is divided into data and training data and test data are determined;

[0163] According to the preset sliding window width, the training data and test data are processed separately to obtain the training data matrix and the test data matrix.

[0164] Furthermore, the fuzzy set membership matrix construction module 803 is further specifically used for:

[0165] Generate fuzzy domain and fuzzy set according to fuzzy domain theory and training data matrix;

[0166] According to the fuzzy domain and fuzzy set, the fuzzy set membership matrix is ​​constructed.

[0167] Furthermore, the power prediction result obtaining module 804 is further specifically configured to:

[0168] According to the membership data of each fuzzy set in the fuzzy set membership matrix, a target fuzzy set that meets the preset membership requirements is determined;

[0169] Perform product quantization processing on the membership data to obtain activation data;

[0170] Generate fuzzy rule matrix and triggerable rule matrix according to activation data, target fuzzy set and test data matrix;

[0171] According to the fuzzy rule matrix and the triggerable rule matrix, the power prediction results of distributed energy are obtained.

[0172] Furthermore, the power prediction result obtaining module 804 is further specifically configured to:

[0173] Generate a rule matrix based on the activation data and target fuzzy set;

[0174] Perform feature extraction on the rule matrix to obtain the fuzzy rule matrix;

[0175] The fuzzy rule matrix and the test data matrix are processed by fuzzy set calculation to obtain the triggerable rule matrix.

[0176] Furthermore, the power prediction result obtaining module 804 is further specifically configured to:

[0177] According to the fuzzy rule matrix and the triggerable rule matrix, a trigger matrix is ​​constructed;

[0178] Perform feature extraction on the trigger matrix to obtain the target trigger matrix;

[0179] Calculate the membership values ​​of the fuzzy rule matrix and the test data matrix to obtain the target membership matrix;

[0180] According to the target trigger matrix and membership matrix, the power prediction results of distributed energy are obtained.

[0181] Furthermore, the emergency strategy determination module 805 is further specifically configured to:

[0182] Comparing the power prediction result with the preset power threshold to obtain a power comparison result;

[0183] If the power comparison result indicates that the power prediction result is greater than or equal to the preset power threshold, the first emergency strategy is determined to be a low-voltage power outage emergency strategy;

[0184] If the power comparison result indicates that the prediction result is less than the preset power threshold, the second emergency strategy is determined to be a low-voltage power outage emergency strategy.

[0185] Figure 9 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 9 As shown, the electronic device 90 includes:

[0186] The electronic device 90 may include one or more processors 901 , one or more computer-readable storage media memories 902 , and a communication component 903 . The processor 901 , the memory 902 , and the communication component 903 are connected via a bus 904 .

[0187] In a specific implementation process, at least one processor 901 executes the computer-executable instructions stored in the memory 902, so that the at least one processor 901 executes the above-mentioned method for determining an emergency strategy for a low-voltage power outage.

[0188] The specific implementation process of the processor 901 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0189] In the above Figure 9 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules in the processor.

[0190] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0191] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0192] In some embodiments, a computer program product is further proposed, including a computer program or instructions, which, when executed by a processor, implements the steps in any of the above-mentioned methods for determining an emergency strategy for a low-voltage power outage.

[0193] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0194] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0195] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores multiple instructions, which can be loaded by a processor to execute the steps in any low-voltage power outage emergency strategy determination method provided in the embodiment of the present application.

[0196] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0197] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program comprises computer instructions stored in a computer-readable storage medium.

[0198] Since the instructions stored in the storage medium can execute the steps in any of the low-voltage power outage emergency strategy determination methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the low-voltage power outage emergency strategy determination methods provided in the embodiments of the present application can be achieved. Please see the previous embodiments for details and will not be repeated here.

[0199] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0200] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0201] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0202] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0203] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0204] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0205] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0206] In the above embodiments, the description of each embodiment has its own focus. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0207] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0208] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining an emergency strategy for a low-voltage power outage, characterized in that: include: Obtain the power dataset of distributed energy before the low-voltage power outage; Performing data partitioning processing on the power data set to obtain a training data matrix and a test data matrix; Constructing a fuzzy set membership matrix based on fuzzy domain theory and the training data matrix; Obtaining a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix; The power prediction result is compared with a preset power threshold to determine an emergency strategy for low-voltage power outage.

2. The method for determining an emergency strategy according to claim 1, wherein: Performing data partitioning on the power data set to obtain a training data matrix and a test data matrix includes: Based on the amount of data in the power data set, dividing the power data set into data segments to determine training data and test data; According to the preset sliding window width, the training data and the test data are processed respectively to obtain a training data matrix and a test data matrix.

3. The method for determining an emergency strategy according to claim 1, wherein: According to the fuzzy domain theory and the training data matrix, a fuzzy set membership matrix is ​​constructed, including: generating fuzzy domains and fuzzy sets according to fuzzy domain theory and the training data matrix; A fuzzy set membership matrix is ​​constructed according to the fuzzy domain and the fuzzy set.

4. The method for determining an emergency strategy according to any one of claims 1 to 3, characterized in that: Obtaining a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix includes: Determining a target fuzzy set that meets a preset membership requirement based on the membership data of each fuzzy set in the fuzzy set membership matrix; Performing product quantization processing on the membership data to obtain activation data; generating a fuzzy rule matrix and a triggerable rule matrix according to the activation data, the target fuzzy set and the test data matrix; According to the fuzzy rule matrix and the triggerable rule matrix, a power prediction result of the distributed energy is obtained.

5. The method for determining an emergency strategy according to claim 4, wherein: Generating a fuzzy rule matrix and a triggerable rule matrix according to the activation data, the target fuzzy set and the test data matrix, including: generating a rule matrix according to the activation data and the target fuzzy set; Performing feature extraction processing on the rule matrix to obtain a fuzzy rule matrix; Fuzzy set calculation processing is performed on the fuzzy rule matrix and the test data matrix to obtain a triggerable rule matrix.

6. The method for determining an emergency strategy according to claim 4, wherein: Obtaining a power prediction result of the distributed energy according to the fuzzy rule matrix and the triggerable rule matrix includes: Constructing a trigger matrix according to the fuzzy rule matrix and the triggerable rule matrix; Performing feature extraction on the trigger matrix to obtain a target trigger matrix; Calculating membership values ​​of the fuzzy rule matrix and the test data matrix to obtain a target membership matrix; A power prediction result of the distributed energy is obtained according to the target trigger matrix and the membership matrix.

7. The method for determining an emergency strategy according to claim 1, wherein: Comparing the power prediction result with a preset power threshold to determine an emergency strategy for low-voltage power outages includes: Comparing the power prediction result with a preset power threshold to obtain a power comparison result; If the power comparison result indicates that the power prediction result is greater than or equal to the preset power threshold, determining that the first emergency strategy is a low-voltage power outage emergency strategy; If the power comparison result indicates that the prediction result is less than a preset power threshold, the second emergency strategy is determined to be a low-voltage power outage emergency strategy.

8. A device for determining an emergency strategy for a low-voltage power outage, characterized in that: include: The power data set acquisition module is used to obtain the power data set of distributed energy before the low-voltage area power outage; A data matrix obtaining module is used to perform data partitioning processing on the power data set to obtain a training data matrix and a test data matrix; A fuzzy set membership matrix construction module is used to construct a fuzzy set membership matrix based on fuzzy domain theory and the training data matrix; A power prediction result obtaining module, configured to obtain a power prediction result of the distributed energy according to the fuzzy set membership matrix and the test data matrix; The emergency strategy determination module is used to compare the power prediction result with a preset power threshold to determine the emergency strategy for low-voltage power outage.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images