Voltage sag treatment method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of electric energy quality treatment, in particular to a voltage sag treatment method and device, electronic equipment and a storage medium. Then performing per-unit processing on each sag power data set, and performing sliding window processing on each sag power data set subjected to per-unit processing to obtain a plurality of power eigenvalue vectors; clustering the plurality of power eigenvalue vectors to obtain a plurality of power sag classes; and finally, determining a plurality of power sag intervals according to the plurality of power sag classes, and determining a plurality of protection schemes according to the load capacities of the plurality of class centers and the plurality of power sag intervals. According to the method, the power eigenvalue vector for describing the power sag curve is constructed according to the power data, the requirement for the capacity of the protection equipment can be clarified, clustering is carried out based on the power eigenvalue vector, and the influence range of equipment of different sag types is accurately reflected.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality management, and in particular to a voltage sag management method, device, electronic equipment and storage medium. Background Art

[0002] Voltage sag is the power quality indicator that users are most concerned about. When voltage sag occurs, many sensitive users will be disconnected from the grid, and the production workshops of high-tech enterprises use a large number of sensitive equipment. Once sensitive equipment is disconnected from the grid, a large number of defective products will be produced, and the enterprise will suffer huge economic losses.

[0003] Currently, the voltage sag assessment mainly focuses on the depth and duration of the sag, but this assessment method cannot express the scope and size of the user's affected equipment. At the same time, in order to avoid or reduce the losses caused by voltage sags, companies choose to install governance equipment. However, the voltage sag tolerance of different sensitive equipment is significantly different. The relevant standards for voltage sags only give the tolerance curves of equipment in the computer industry and the semiconductor industry, but it is difficult to give the governance requirements for other sensitive equipment. At present, there is an urgent need for a universal assessment and governance solution that can adapt to multiple industries and multiple devices.

[0004] Based on this, it is necessary to develop and design a method for voltage sag control. Summary of the invention

[0005] The embodiments of the present invention provide a voltage sag management method, device, electronic device and storage medium, which are used to solve the problem that voltage sag assessment in the prior art cannot express the range of user's affected devices.

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling a voltage sag, comprising:

[0007] Acquire multiple power sag data sets, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs;

[0008] Normalizing each power sag data set, and performing sliding window processing on each normalized power sag data set to obtain a plurality of power eigenvalue vectors, wherein each power eigenvalue vector corresponds to a power sag data set;

[0009] Clustering the multiple power eigenvalue vectors to obtain multiple power sag classes;

[0010] Multiple power sag intervals are determined according to the multiple power sag classes, and multiple protection schemes are determined according to the load capacity of the multiple class centers and the multiple power sag intervals, wherein the power sag interval includes a power sag depth and a power sag duration.

[0011] In a possible implementation, each power sag data set is normalized, and each normalized power sag data set is subjected to sliding window processing to obtain multiple power eigenvalue vectors, including:

[0012] For each of the multiple power dip data sets, the following steps are performed respectively:

[0013] Get the initial window length;

[0014] Performing per-unit processing on the power sag data set to obtain a first data set;

[0015] Extracting the power segment of the initial window length from the first data set to obtain a segment to be processed;

[0016] Calculating an average value of the section to be processed as a first average value;

[0017] Adding the first average value as a vector element to the power eigenvalue vector;

[0018] Extracting the power segment of the initial window length to obtain a segment to be processed;

[0019] Calculating an average value of the section to be processed as a second average value;

[0020] If the deviation between the second average value and the first average value is less than a threshold, the initial window length is adjusted, and the process jumps to the power segment for extracting the initial window length to obtain a segment to be processed;

[0021] otherwise, adding the second average value as a vector element to the power eigenvalue vector;

[0022] If the traversal of the first data set is not completed, the offset of the extraction position is performed, and the process jumps to the step of extracting the power segment of the initial window length to obtain the segment to be processed.

[0023] In a possible implementation manner, the step of normalizing the power sag data set to obtain the first data set includes:

[0024] The power sag data set is normalized according to a first formula to obtain a first data set, wherein the first formula is:

[0025]

[0026] Where P * P(n) is the nth data in the first data set, P(n) is the nth data in the power sag data set, and P0 is the power of the cycle before the sag occurs.

[0027] In a possible implementation manner, clustering the multiple power eigenvalue vectors to obtain multiple power sag classes includes:

[0028] Get the initial number of clusters;

[0029] Randomly selecting the vector of the initial cluster number from the multiple power eigenvalue vectors as multiple primary cluster center points;

[0030] Dividing the other multiple power eigenvalue vectors into the classes of the multiple primary clustering center points to obtain multiple primary classes;

[0031] Calculate the average value of multiple power eigenvalue vectors in each primary class to obtain multiple secondary clustering center points;

[0032] Dividing the other multiple power eigenvalue vectors into the classes of the multiple secondary clustering center points to obtain multiple secondary classes;

[0033] Verify the rationality of the initial number of clusters;

[0034] If it is unreasonable, adjust the initial cluster number;

[0035] Otherwise, the multiple secondary classes are used as the multiple power dip classes.

[0036] In a possible implementation manner, the dividing the other multiple power eigenvalue vectors into the classes of the multiple primary clustering center points to obtain multiple primary classes includes:

[0037] For each of the other multiple power eigenvalue vectors, perform the following steps respectively:

[0038] The distance between the vector and each primary cluster center point is determined according to the second formula, wherein the second formula is:

[0039]

[0040] In the formula, d(m,r) is the distance between the vector and the center point of the primary cluster. is the nth element of the vector, is the nth element of a cluster center, and nmax is the total number of vector elements;

[0041] Add the vector to the class where the nearest cluster center point is located.

[0042] In a possible implementation manner, verifying the rationality of the initial number of clusters includes:

[0043] The reasonable indication value of the initial number of clusters is obtained by verifying the third formula, wherein the third formula is:

[0044]

[0045] In the formula, S(C) is a reasonable indicator value of the number of clusters C, num(C k ) is the number of vectors in the kth class, b(i) is the distance between the i-th vector in the class and the class center, a(i) is the average distance between the i-th vector in the class and other vectors in the class, and max() is the maximum value function;

[0046] If S(C)>S(C+1) and S(C)>S(C-1), then the initial number of clusters is reasonable;

[0047] Otherwise, the initial number of clusters is unreasonable.

[0048] In a possible implementation manner, determining multiple power sag intervals according to the multiple power sag classes, and determining multiple protection schemes according to the load capacities of multiple class centers and the multiple power sag intervals, includes:

[0049] For each power reduction class, perform the following steps:

[0050] Get the maximum power sag depth, minimum power sag depth, maximum power sag duration, and minimum power sag duration in the class;

[0051] Get the load capacity of the class center;

[0052] Determining a maximum protection scheme according to the load capacity of the class center, the maximum power sag depth, and the maximum power sag duration;

[0053] A minimum protection scheme is determined according to the load capacity of the class center, the minimum power sag depth, and the minimum power sag duration.

[0054] In a second aspect, an embodiment of the present invention provides a voltage sag control device, which is used to implement the voltage sag control method described in the first aspect or any possible implementation of the first aspect, and the voltage sag control device includes:

[0055] A data acquisition module, used to acquire a plurality of power sag data sets, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs;

[0056] A feature vector extraction module is used to normalize each temporary power sag data set, and perform sliding window processing on each normalized temporary power sag data set to obtain multiple power feature value vectors, wherein each power feature value vector corresponds to a temporary power sag data set;

[0057] A power sag classification module, used for clustering the multiple power eigenvalue vectors to obtain multiple power sag classes;

[0058] as well as,

[0059] A protection scheme determination module is used to determine multiple power sag intervals according to the multiple power sag classes, and to determine multiple protection schemes according to the load capacity of multiple class centers and the multiple power sag intervals, wherein the power sag interval includes the power sag depth and the power sag duration.

[0060] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation method of the first aspect.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0062] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0063] The embodiment of the present invention discloses a voltage sag control method, which first obtains multiple sag power data sets, wherein the sag power data set characterizes the volatility of load capacity over time when the voltage sag occurs; then each sag power data set is normalized, and each normalized sag power data set is subjected to sliding window processing to obtain multiple power eigenvalue vectors, wherein each power eigenvalue vector corresponds to a sag power data set; then the multiple power eigenvalue vectors are clustered to obtain multiple power sag classes; finally, multiple power sag intervals are determined according to the multiple power sag classes, and multiple protection schemes are determined according to the load capacity of the multiple class centers and the multiple power sag intervals, wherein the power sag interval includes the power sag depth and the power sag duration. The embodiment of the present invention obtains power data during voltage sag, and constructs a power eigenvalue vector that depicts a power sag curve according to the power data, so that the demand for protection device capacity can be clarified. The embodiment of the present invention performs clustering based on the power eigenvalue vector, and sets protection schemes for different types, which more accurately reflects the scope of influence of different sag types of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0065] Figure 1 is a flow chart of a voltage sag control method provided by an embodiment of the present invention;

[0066] Figure 2 It is a schematic diagram depicting the existing voltage sag process provided by an embodiment of the present invention;

[0067] Figure 3 is a schematic diagram of a power eigenvalue vector provided by an embodiment of the present invention;

[0068] Figure 4 is a diagram showing the relationship between duration and sag depth in a typical power loss scenario provided by an embodiment of the present invention;

[0069] Figure 5 It is a functional block diagram of a voltage sag control device provided in an embodiment of the present invention;

[0070] Figure 6 It is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0072] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0073] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0074] Figure 1 The present invention provides a flowchart of a method for controlling voltage sag according to an embodiment of the present invention.

[0075] like Figure 1As shown, it shows a flowchart of the voltage sag control method provided by an embodiment of the present invention, which is described in detail as follows:

[0076] In step 101, a plurality of power sag data sets are acquired, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs.

[0077] In step 102, each power sag data set is normalized, and each normalized power sag data set is subjected to sliding window processing to obtain a plurality of power eigenvalue vectors, wherein each power eigenvalue vector corresponds to a power sag data set.

[0078] In some implementations, step 102 includes:

[0079] For each of the multiple power dip data sets, the following steps are performed respectively:

[0080] Get the initial window length;

[0081] Performing per-unit processing on the power sag data set to obtain a first data set;

[0082] Extracting the power segment of the initial window length from the first data set to obtain a segment to be processed;

[0083] Calculating an average value of the section to be processed as a first average value;

[0084] Adding the first average value as a vector element to the power eigenvalue vector;

[0085] Extracting the power segment of the initial window length to obtain a segment to be processed;

[0086] Calculating an average value of the section to be processed as a second average value;

[0087] If the deviation between the second average value and the first average value is less than a threshold, the initial window length is adjusted, and the process jumps to the power segment for extracting the initial window length to obtain a segment to be processed;

[0088] otherwise, adding the second average value as a vector element to the power eigenvalue vector;

[0089] If the traversal of the first data set is not completed, the offset of the extraction position is performed, and the process jumps to the step of extracting the power segment of the initial window length to obtain the segment to be processed.

[0090] In some implementations, the step of normalizing the power sag data set to obtain the first data set includes:

[0091] The power sag data set is normalized according to a first formula to obtain a first data set, wherein the first formula is:

[0092]

[0093] Where P * (n) is the nth data in the first data set, p(n) is the nth data in the temporary sag power data set, and P0 is the power of the cycle before the temporary sag occurs.

[0094] For example, voltage sag is the power quality indicator that high-tech enterprises and other sensitive users are most concerned about and complain about the most. The existing analysis and description of voltage sag mainly focuses on the duration of the sag and the magnitude of the voltage drop. The usual description methods are as follows: Figure 2 As shown, it mainly depicts the relationship between voltage amplitude and time during the voltage sag. For sensitive users such as high-tech enterprises, users are more concerned about which loads are affected after the voltage sag occurs, how much capacity of the treatment equipment is installed, how long these devices need to be protected, and how low the voltage sag depth is.

[0095] In describing the voltage sag, the embodiment of the present invention constructs a power characteristic value vector of a power change curve. In order to unify the data set, the embodiment of the present invention performs per-unit processing on the sag power data set based on the power of the cycle before the sag occurs and the sag power data set. The per-unit processing process is expressed by the formula:

[0096]

[0097] Where P * P(n) is the nth data in the first data set, P(n) is the nth data in the power sag data set, and P0 is the power of the cycle before the sag occurs.

[0098] For each first data set, the power section of the voltage sag process is divided by a sliding window. Assuming the length of the first section is w, its average power is obtained by formula (2):

[0099]

[0100] In the formula, is the average power of the first segment, P * (j) is the jth data in the first data set. Then, read w power data backwards and calculate the power of the second segment with reference to the formula If the two segments satisfy formula (3), they are divided into the second segment. If not, the second window length is increased to w+1, and the values ​​are increased successively. The value can be taken according to the proportion of user sensitive load, usually 0.05.

[0101]

[0102] Finally, we get Figure 3 The power range curve is shown.

[0103] In step 103, the multiple power eigenvalue vectors are clustered to obtain multiple power dip classes.

[0104] In some implementations, step 103 includes:

[0105] Get the initial number of clusters;

[0106] Randomly selecting the vector of the initial cluster number from the multiple power eigenvalue vectors as multiple primary cluster center points;

[0107] Dividing the other multiple power eigenvalue vectors into the classes of the multiple primary clustering center points to obtain multiple primary classes;

[0108] Calculate the average value of multiple power eigenvalue vectors in each primary class to obtain multiple secondary clustering center points;

[0109] Dividing the other multiple power eigenvalue vectors into the classes of the multiple secondary clustering center points to obtain multiple secondary classes;

[0110] Verify the rationality of the initial number of clusters;

[0111] If it is unreasonable, adjust the initial cluster number;

[0112] Otherwise, the multiple secondary classes are used as the multiple power dip classes.

[0113] In some implementations, the dividing the other multiple power eigenvalue vectors into the multiple classes of primary clustering centers to obtain multiple primary classes includes:

[0114] For each of the other multiple power eigenvalue vectors, perform the following steps respectively:

[0115] The distance between the vector and each primary cluster center point is determined according to the second formula, wherein the second formula is:

[0116]

[0117] In the formula, d(m,r) is the distance between the vector and the center point of the primary cluster. is the nth element of the vector, is the nth element of a cluster center, and nmax is the total number of vector elements;

[0118] Add the vector to the class where the nearest cluster center point is located.

[0119] In some implementations, verifying the rationality of the initial number of clusters includes:

[0120] The reasonable indication value of the initial number of clusters is obtained by verifying the third formula, wherein the third formula is:

[0121]

[0122] In the formula, S(C) is a reasonable indicator value of the number of clusters C, num(C k ) is the number of vectors in the kth class, b(i) is the distance between the i-th vector in the class and the class center, a(i) is the average distance between the i-th vector in the class and other vectors in the class, and max() is the maximum value function;

[0123] If S(C)>S(C+1) and S(C)>S(C-1), then the initial number of clusters is reasonable;

[0124] Otherwise, the initial number of clusters is unreasonable.

[0125] For example, in terms of the governance capacity of different typical scenarios obtained by clustering, the load off-grid power caused by different voltage sag events occurring in a user within a period of time (for example, one year) is different. The typical scenario is obtained by classification through the aggregation algorithm. Assume that the total number of voltage sag events occurring in one year is M, and the power eigenvalue vector obtained in the above steps is divided into multiple types by the mean clustering method. The specific steps are:

[0126] Step 1: Set the initial number of clusters to C, and randomly select C power eigenvalue vectors as cluster centers.

[0127] Step 2: Calculate the distance between each power eigenvalue vector and the cluster center point through formula (4), and divide all power eigenvalue vectors into C types.

[0128]

[0129] In the formula, d(m,r) is the distance between the vector and the center point of the primary cluster. is the nth element of the vector, is the nth element of a cluster center, and nmax is the total number of vector elements.

[0130] Step 3: Calculate the average value of the power eigenvalue vectors contained in each category as the new cluster center, and re-divide the power eigenvalue vectors into new categories according to the method in step 2.

[0131] Step 4: Determine whether the number of clusters C is reasonable, based on formula (5)

[0132]

[0133] In the formula, S(C) is a reasonable indicator value of the number of clusters C, num(C k ) is the number of vectors in the k-th class, b(i) is the distance between the ith vector in the class and the class center, a(i) is the average distance between the ith vector in the class and other vectors in the class, and max() is the maximum value function.

[0134] Step 5: When S(C)>S(C+1) and S(C)>S(C-1), C is the number of nearest clusters. Otherwise, adjust the initial number of clusters to C and jump to step 2.

[0135] In this way, a plurality of power sag classes are obtained, and the power sag curves of these power sag classes are similar, and they usually correspond to the same or similar voltage sag events and the causes causing the voltage sag events.

[0136] In step 104, multiple power dip intervals are determined according to the multiple power dip classes, and multiple protection schemes are determined according to the load capacity of the multiple class centers and the multiple power dip intervals, wherein the power dip interval includes a power dip depth and a power dip duration.

[0137] In some implementations, step 104 includes:

[0138] For each power reduction class, perform the following steps:

[0139] Get the maximum power sag depth, minimum power sag depth, maximum power sag duration, and minimum power sag duration in the class;

[0140] Get the load capacity of the class center;

[0141] Determining a maximum protection scheme according to the load capacity of the class center, the maximum power sag depth, and the maximum power sag duration;

[0142] A minimum protection scheme is determined according to the load capacity of the class center, the minimum power sag depth, and the minimum power sag duration.

[0143] Exemplarily, in formulating a protection scheme, for each power sag class, the power sag depth and duration in the class are read to form a set, for example, a set Q is formed, Q = {(P1, T1), (P2, T2), ..., (P z ,T z)}, in which z is the number of vectors in the class. Based on this set, we can get the maximum power sag depth Pmax, the minimum power sag depth Pmin, the maximum power sag duration Tmax and the minimum power sag duration Tmax. Using these data, we can construct a Figure 4 Then, for the vector of the center of the cluster, obtain its power at the moment before the power drop (the power of the cycle before the sag occurs), it can be understood that when the duration of the sag event [Tmin, Tmax] and the sag depth [Pmin, Pmax] occur, the capacity will be The equipment is out of service.

[0144] Based on this, the temporary sag protection plan is as follows: In order to avoid the capacity of the temporary sag The equipment is affected and can operate continuously. It needs to be equipped with treatment equipment that can protect against temporary sag events with a protection duration of Tmin and a temporary sag depth of Pmin. For enterprises with strong investment capabilities, they can invest in equipment that can protect against temporary sag events with a protection duration of Tmax and a temporary sag depth of Pmax.

[0145] The voltage sag control method of the present invention is implemented in such a way that firstly a plurality of sag power data sets are obtained, wherein the sag power data set characterizes the volatility of load capacity over time when a voltage sag occurs; then each sag power data set is normalized, and each normalized sag power data set is subjected to sliding window processing to obtain a plurality of power eigenvalue vectors, wherein each power eigenvalue vector corresponds to a sag power data set; then the plurality of power eigenvalue vectors are clustered to obtain a plurality of power sag classes; finally, a plurality of power sag intervals are determined according to the plurality of power sag classes, and a plurality of protection schemes are determined according to the load capacities of the plurality of class centers and the plurality of power sag intervals, wherein the power sag intervals include a power sag depth and a power sag duration. The implementation method of the present invention obtains power data during a voltage sag, and constructs a power eigenvalue vector that depicts a power sag curve according to the power data, so that the demand for the capacity of the protection equipment can be clearly defined. The implementation method of the present invention performs clustering based on the power eigenvalue vectors, and sets protection schemes for different types, which more accurately reflects the scope of influence of different sag types of equipment.

[0146] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0147] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0148] Figure 5 This is a functional block diagram of a voltage sag control device provided in an embodiment of the present invention, referring to Figure 5 The voltage sag control device includes: a data acquisition module 501, a feature vector extraction module 502, a power sag classification module 503 and a protection scheme determination module 504, wherein:

[0149] The data acquisition module 501 is used to acquire a plurality of power sag data sets, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs;

[0150] The feature vector extraction module 502 is used to normalize each power sag data set, and perform sliding window processing on each normalized power sag data set to obtain multiple power feature value vectors, wherein each power feature value vector corresponds to a power sag data set;

[0151] A power sag classification module 503, configured to cluster the plurality of power eigenvalue vectors to obtain a plurality of power sag classes;

[0152] The protection scheme determination module 504 is used to determine multiple power dip intervals according to the multiple power dip classes, and determine multiple protection schemes according to the load capacity of the multiple class centers and the multiple power dip intervals, wherein the power dip interval includes the power dip depth and the power dip duration.

[0153] Figure 6 is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 6 of this embodiment includes: a processor 600 and a memory 601, wherein the memory 601 stores a computer program 602 that can be run on the processor 600. When the processor 600 executes the computer program 602, the steps in the above-mentioned voltage sag control method and the embodiment are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0154] Exemplarily, the computer program 602 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 601 and executed by the processor 600 to implement the present invention.

[0155] The electronic device 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 6 may include, but is not limited to, a processor 600 and a memory 601. Those skilled in the art will appreciate that Figure 6It is only an example of the electronic device 6 and does not constitute a limitation of the electronic device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 6 may also include input and output devices, network access devices, buses, etc.

[0156] The processor 600 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0157] The memory 601 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. The memory 601 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Further, the memory 601 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 601 is used to store the computer program 602 and other programs and data required by the electronic device 6. The memory 601 may also be used to temporarily store data that has been output or is to be output.

[0158] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0159] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0161] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0163] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0164] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various methods and device implementation methods. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0165] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for controlling voltage sag, characterized in that: include: Acquire multiple power sag data sets, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs; Normalizing each power sag data set, and performing sliding window processing on each normalized power sag data set to obtain a plurality of power eigenvalue vectors, wherein each power eigenvalue vector corresponds to a power sag data set; Clustering the multiple power eigenvalue vectors to obtain multiple power sag classes; A plurality of power sag intervals are determined according to the plurality of power sag classes, and a plurality of protection schemes are determined according to the load capacity of the plurality of class centers and the plurality of power sag intervals, wherein the power sag interval includes a power sag depth and a power sag duration.

2. The voltage sag control method according to claim 1, characterized in that: The step of normalizing each power sag data set and performing sliding window processing on each normalized power sag data set to obtain a plurality of power eigenvalue vectors includes: For each of the multiple power dip data sets, the following steps are performed respectively: Get the initial window length; Performing per-unit processing on the power sag data set to obtain a first data set; Extracting the power segment of the initial window length from the first data set to obtain a segment to be processed; Calculating an average value of the section to be processed as a first average value; Adding the first average value as a vector element to the power eigenvalue vector; Extracting the power segment of the initial window length to obtain a segment to be processed; Calculating an average value of the section to be processed as a second average value; If the deviation between the second average value and the first average value is less than a threshold, the initial window length is adjusted, and the process jumps to the power segment for extracting the initial window length to obtain a segment to be processed; otherwise, adding the second average value as a vector element to the power eigenvalue vector; If the traversal of the first data set is not completed, the offset of the extraction position is performed, and the process jumps to the step of extracting the power segment of the initial window length to obtain the segment to be processed.

3. The voltage sag control method according to claim 2, characterized in that: The step of normalizing the power sag data set to obtain a first data set includes: The power sag data set is normalized according to a first formula to obtain a first data set, wherein the first formula is: Wherein, P*(n) is the nth data in the first data set, P(n) is the nth data in the power sag data set, and P0 is the power of the cycle before the sag occurs.

4. The voltage sag control method according to claim 1, characterized in that: The clustering of the multiple power eigenvalue vectors to obtain multiple power sag classes includes: Get the initial number of clusters; Randomly selecting the vector of the initial cluster number from the multiple power eigenvalue vectors as multiple primary cluster center points; Dividing the other multiple power eigenvalue vectors into the classes of the multiple primary clustering center points to obtain multiple primary classes; Calculate the average value of multiple power eigenvalue vectors in each primary class to obtain multiple secondary clustering center points; Dividing the other multiple power eigenvalue vectors into the classes of the multiple secondary clustering center points to obtain multiple secondary classes; Verify the rationality of the initial number of clusters; If it is unreasonable, adjust the initial cluster number; Otherwise, the multiple secondary classes are used as the multiple power dip classes.

5. The voltage sag control method according to claim 4, characterized in that: The dividing the other multiple power eigenvalue vectors into the classes of the multiple primary clustering center points to obtain multiple primary classes includes: For each of the other multiple power eigenvalue vectors, perform the following steps respectively: The distance between the vector and each primary cluster center point is determined according to the second formula, wherein the second formula is: In the formula, d(m, r) is the distance between the vector and the center point of the primary cluster. is the nth element of the vector, is the nth element of a cluster center, and nmax is the total number of vector elements; Add the vector to the class where the nearest cluster center point is located.

6. The voltage sag control method according to claim 4, characterized in that: The verifying the rationality of the initial number of clusters includes: The reasonable indication value of the initial number of clusters is obtained by verifying the third formula, wherein the third formula is: In the formula, S(C) is a reasonable indicator value of the number of clusters C, num(C k ) is the number of vectors in the kth class, b(i) is the distance between the i-th vector in the class and the class center, a(i) is the average distance between the i-th vector in the class and other vectors in the class, and max() is the maximum value function; If S(C)>S(C+1) and S(C)>S(C-1), then the initial number of clusters is reasonable; Otherwise, the initial number of clusters is unreasonable.

7. The voltage sag control method according to any one of claims 1 to 6, characterized in that: The determining of a plurality of power sag intervals according to the plurality of power sag classes, and determining a plurality of protection schemes according to the load capacities of the plurality of class centers and the plurality of power sag intervals, includes: For each power reduction class, perform the following steps: Get the maximum power sag depth, minimum power sag depth, maximum power sag duration, and minimum power sag duration in the class; Get the load capacity of the class center; Determining a maximum protection scheme according to the load capacity of the class center, the maximum power sag depth, and the maximum power sag duration; A minimum protection scheme is determined according to the load capacity of the class center, the minimum power sag depth, and the minimum power sag duration.

8. A voltage sag control device, characterized in that: Used to implement the voltage sag control method according to any one of claims 1 to 7, the voltage sag control device comprises: A data acquisition module, used to acquire a plurality of power sag data sets, wherein the power sag data sets represent the fluctuation of load capacity over time when a voltage sag occurs; A feature vector extraction module is used to normalize each temporary power sag data set, and perform sliding window processing on each normalized temporary power sag data set to obtain multiple power feature value vectors, wherein each power feature value vector corresponds to a temporary power sag data set; A power sag classification module, used for clustering the multiple power eigenvalue vectors to obtain multiple power sag classes; as well as, A protection scheme determination module is used to determine multiple power sag intervals according to the multiple power sag classes, and to determine multiple protection schemes according to the load capacity of multiple class centers and the multiple power sag intervals, wherein the power sag interval includes the power sag depth and the power sag duration.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images