A method, device, equipment and storage medium for constructing a substation area topology

Abstract

The present application discloses a method, apparatus, device, and storage medium for constructing a substation area topology. The method includes: obtaining a voltage signal corresponding to the substation area to be constructed; discretizing the voltage signal and calculating the mean and variance of the discretized voltage signal; calculating the signal distance between voltage signals through the mean and variance; selecting initial reference samples and adjacent samples during clustering based on the signal distance; deleting abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain gravitational field samples; aggregating the initial reference samples and gravitational field samples according to the kernel component coefficient to obtain an initial topology structure; aggregating the initial topology structure according to the topology similarity to obtain a new topology structure; aggregating the new topology structure according to the new topology similarity until it is impossible to aggregate to obtain the substation area topology structure corresponding to the substation area to be constructed. It solves the technical problem of the low accuracy of the existing method for constructing the substation area topology.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular, to a method, device, equipment, and storage medium for constructing a distribution area topology. Background Art

[0002] Due to the lack of information systems in the early stage of construction in the distribution network area, the archive data is missing or incorrect, and further errors are caused during the relocation and maintenance processes, resulting in incorrect relationships between transformers, boxes, and households in the distribution area. This causes large errors in line loss analysis, and at the same time, it is impossible to accurately count the power outage scope and the number of power outage households, resulting in reliability and statistical errors, and the power outage plan arrangement cannot be optimized.

[0003] With the application of intelligent metering terminals, broadband carrier technology, and edge technology, the management system of the distribution network area gradually uses big data analysis technology to carry out a method for verifying network topology affiliation based on data, and constructs a distribution area topology for the operation and maintenance management of the distribution area.

[0004] At present, although the data-driven method can achieve certain effects when constructing the distribution area topology, it is sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect. Summary of the Invention

[0005] In view of this, the present application provides a method, device, equipment, and storage medium for constructing a distribution area topology, which solves the technical problem that the existing method for constructing the distribution area topology is sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect.

[0006] The first aspect of the present application provides a method for constructing a distribution area topology, including:

[0007] Obtain the voltage signal corresponding to the distribution area to be constructed;

[0008] After discretizing the voltage signal, calculate the mean and variance of the discretized voltage signal;

[0009] Calculate the signal distance between the voltage signals through the mean and variance;

[0010] Based on the signal distance, select the initial reference samples and adjacent samples during clustering;

[0011] Delete the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain gravitational field samples;

[0012] Aggregate the initial reference samples and the gravitational field samples according to the nuclear composition coefficients to obtain a number of initial topological structures;

[0013] Aggregate the initial topological structures according to the topological similarity to obtain new topological structures;

[0014] Aggregate the new topological structures according to the new topological similarity until no further aggregation is possible to obtain the substation area topological structure corresponding to the substation area to be constructed.

[0015] Optionally, the voltage signal includes: three-phase voltage of the substation area and user voltage;

[0016] After discretizing the voltage signal, calculate the mean and variance of the discretized voltage signal, specifically including:

[0017] Discretize the three-phase voltage of the substation area to obtain the discretized three-phase voltage of the substation area;

[0018] Discretize the user voltage to obtain the discretized user voltage;

[0019] Calculate the first mean and the first variance of the discretized three-phase voltage of the substation area;

[0020] Calculate the second mean and the second variance of the discretized user voltage.

[0021] Optionally, calculate the signal distance between the voltage signals through the mean and variance, specifically including:

[0022] Based on the voltage mean distance calculation formula, calculate the voltage mean distance between the three-phase voltage of the substation area and the user voltage according to the first mean and the second mean;

[0023] Based on the voltage variance distance calculation formula, calculate the voltage variance distance between the three-phase voltage of the substation area and the user voltage according to the first variance and the second variance;

[0024] Calculate the signal distance between the three-phase voltage of the substation area and the user voltage according to the voltage mean distance and the voltage variance distance.

[0025] Optionally, delete the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and the adjacent samples to obtain the gravitational field samples, specifically including:

[0026] Obtain the gravitational field range of the initial reference samples;

[0027] Calculate the gravitational density of the initial reference samples within the gravitational field range according to the gravitational density calculation formula;

[0028] Based on the gravitational coefficient calculation formula, calculate the abnormal gravitational coefficients of adjacent samples within the gravitational field according to the gravitational density.

[0029] Delete adjacent samples with abnormal gravitational coefficients greater than a preset threshold, and use the remaining adjacent samples as gravitational field samples.

[0030] Optionally, the gravitational density calculation formula is:

[0031]

[0032] In the formula, grt p is the gravitational density of the initial reference sample p, median() represents taking the median of a sequence of values, and |gr p | represents the number of samples within the gravitational field range gr p of the initial reference sample p, and grd pq represents the gravitational distance between the initial reference sample p and the adjacent sample q within the gravitational field range.

[0033] Optionally, the gravitational coefficient calculation formula is:

[0034]

[0035] In the formula, out p is the gravitational coefficient of the initial reference sample p, grta p is the average gravitational density of the initial reference sample p, and grta q is the average gravitational density of the initial reference sample q.

[0036] Optionally, according to the topological similarity, aggregate the initial topological structures to obtain a new topological structure, specifically including:

[0037] Calculate the topological similarity between the initial topological structures;

[0038] Aggregate the initial topological structures with topological similarity greater than a preset similarity threshold to obtain a new topological structure.

[0039] The second aspect of this application provides a device for constructing a substation area topology, including:

[0040] An acquisition unit for acquiring voltage signals corresponding to the substation area to be constructed;

[0041] A first calculation unit for calculating the mean and variance of the discretized voltage signals after discretizing the voltage signals;

[0042] A second calculation unit for calculating the signal distance between the voltage signals through the mean and variance;

[0043] A selection unit, configured to select an initial reference sample and adjacent samples during clustering based on the signal distance;

[0044] A deletion unit, configured to delete abnormal adjacent samples according to the gravitational field parameters of the initial reference sample and the adjacent samples, so as to obtain gravitational field samples;

[0045] A first aggregation unit, configured to aggregate the initial reference sample and the gravitational field samples according to the nuclear composition coefficient, so as to obtain a number of initial topological structures;

[0046] A second aggregation unit, configured to aggregate the initial topological structures according to the topological similarity, so as to obtain a new topological structure;

[0047] A third aggregation unit, configured to aggregate the new topological structures according to the new topological similarity until no further aggregation is possible, so as to obtain the topological structure of the substation area to be constructed.

[0048] A third aspect of the present application provides a device for constructing a substation area topology, including a processor and a memory;

[0049] The memory is configured to store program code and transmit the program code to the processor;

[0050] The processor is configured to execute the method for constructing a substation area topology according to any one of the first aspects according to the instructions in the program code.

[0051] A fourth aspect of the present application provides a storage medium, which is configured to store program code, and the program code is used to execute the method for constructing a substation area topology according to any one of the first aspects.

[0052] It can be seen from the above technical solutions that the present application has the following advantages:

[0053] The present application provides a method for constructing a substation area topology. First, the voltage signal corresponding to the substation area to be constructed is obtained, and then after discretizing the voltage signal, the mean and variance of the discretized voltage signal are calculated. Then, based on the mean and variance, the signal distance between voltage signals is calculated. Then, based on the signal distance, an initial reference sample and adjacent samples during clustering are selected. Next, according to the gravitational field parameters of the initial reference sample and the adjacent samples, abnormal adjacent samples are deleted to obtain gravitational field samples. Then, according to the nuclear composition coefficient, the initial reference sample and the gravitational field samples are aggregated to obtain a number of initial topological structures. Next, according to the topological similarity, the initial topological structures are aggregated to obtain a new topological structure. Finally, according to the new topological similarity, the new topological structures are aggregated until no further aggregation is possible, so as to obtain the topological structure of the substation area to be constructed.

[0054] In this application, the signal distance is calculated through the mean and variance between voltage signals. Based on the gravitational field parameters, data outliers (i.e., adjacent samples) are excluded, and autonomous community structure aggregation is carried out to realize the construction of the substation area topology, thus solving the technical problem that the existing methods for constructing the substation area topology are sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a schematic flowchart of the first embodiment of a method for constructing a substation area topology in an embodiment of the present application;

[0057] Figure 2 It is a schematic flowchart of the second embodiment of a method for constructing a substation area topology in an embodiment of the present application;

[0058] Figure 3 It is a schematic structural diagram of a device for constructing a substation area topology in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The embodiments of the present application provide a method, device, equipment and storage medium for constructing a substation area topology, which solves the technical problem that the existing methods for constructing the substation area topology are sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect.

[0060] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all of them. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0061] The first aspect of the embodiments of the present application provides an embodiment of a method for constructing a substation area topology.

[0062] Please refer to Figure 1 , a schematic flowchart of the first embodiment of a method for constructing a substation area topology in an embodiment of the present application.

[0063] The method for constructing the substation area topology in this embodiment includes:

[0064] Step 101, obtain the voltage signal corresponding to the substation area to be constructed.

[0065] After discretizing the voltage signal, calculate the mean and variance of the discretized voltage signal.

[0066] Calculate the signal distance between the voltage signals through the mean and variance.

[0067] Based on the signal distance, select the initial reference samples and adjacent samples during clustering.

[0068] It can be understood that the initial reference samples can be arbitrarily selected, and the selection objects can be transformers, users, etc. within the substation area to be constructed. This embodiment does not make specific limitations on this.

[0069] According to the gravitational field parameters of the initial reference samples and adjacent samples, delete the abnormal adjacent samples to obtain the gravitational field samples.

[0070] According to the nuclear composition coefficient, aggregate the initial reference samples and the gravitational field samples to obtain several initial topological structures.

[0071] According to the topological similarity, aggregate the initial topological structures to obtain a new topological structure.

[0072] According to the new topological similarity, aggregate the new topological structures until no aggregation can be performed to obtain the substation area topology structure corresponding to the substation area to be constructed.

[0073] It can be understood that the aggregation is performed according to the topological similarity. The topological similarity values corresponding to the topologies that can be aggregated are relatively close, that is, the topological similarity is greater than the preset value. When the topological similarity is less than this preset value, it means that no aggregation can be performed.

[0074] In this embodiment, first, the voltage signal corresponding to the to-be-constructed substation area is obtained. Then, after discretizing the voltage signal, the mean and variance of the discretized voltage signal are calculated. Next, based on the mean and variance, the signal distance between voltage signals is calculated. Then, based on the signal distance, the initial reference samples and adjacent samples for clustering are selected. Subsequently, according to the gravitational field parameters of the initial reference samples and adjacent samples, the abnormal adjacent samples are deleted to obtain gravitational field samples. Then, according to the kernel component coefficient, the initial reference samples and gravitational field samples are aggregated to obtain several initial topological structures. Next, according to the topological similarity, the initial topological structures are aggregated to obtain new topological structures. Finally, according to the new topological similarity, the new topological structures are aggregated until no further aggregation is possible, obtaining the substation area topological structure corresponding to the to-be-constructed substation area. In this application, the signal distance is calculated through the mean and variance between voltage signals. Based on the gravitational field parameters, data outliers (i.e., adjacent samples) are excluded, and autonomous community structure aggregation is carried out to realize the construction of the substation area topology, thus solving the technical problem that the existing methods for constructing the substation area topology are sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect.

[0075] The above is Embodiment 1 of a method for constructing a substation area topology provided by an embodiment of this application. The following is Embodiment 2 of a method for constructing a substation area topology provided by an embodiment of this application.

[0076] Please refer to Figure 2 , the flow schematic diagram of Embodiment 2 of a method for constructing a substation area topology in an embodiment of this application.

[0077] The method for constructing a substation area topology in this embodiment includes:

[0078] Step 201: Obtain the three-phase voltage of the substation area and the user voltage corresponding to the to-be-constructed substation area.

[0079] Step 202: Discretize the three-phase voltage of the substation area to obtain the discretized three-phase voltage of the substation area.

[0080] It can be understood that the implementation steps of discretization may include: first, perform discrete wavelet transform on the three-phase voltage of the substation area, then select the three-phase voltage within the frequency band range for discrete wavelet reconstruction, then perform time-domain transformation using short-time Fourier transform, and finally output the discrete time-domain signal (i.e., the discretized three-phase voltage of the substation area).

[0081] Step 203: Discretize the user voltage to obtain the discretized user voltage.

[0082] It can be understood that the implementation steps of discretization may include: first, performing discrete wavelet transform on the user voltage, then selecting the user voltage within the frequency band range for discrete wavelet reconstruction, then performing time-domain transform using short-time Fourier transform, and finally outputting the discrete time-domain signal (i.e., the discretized user voltage).

[0083] Step 204: Calculate the first mean and the first variance of the three-phase voltage of the substation area after discretization.

[0084] It can be understood that the first mean The calculation formula is:[[]]END]]

[0085]

[0086] In the formula, k represents the discrete signal number; x v (k) represents the three-phase voltage value of the kth substation area; w(k) is the sampling function corresponding to the three-phase voltage of the kth substation area; K represents the total number of discrete signals.

[0087] The first variance The calculation formula is:[[]]END]]

[0088]

[0089] It can be understood that when calculating the signal distance through the mean and variance, it is also necessary to calculate the corresponding auxiliary coefficient of the three-phase voltage of the substation area

[0090] In one implementation, the auxiliary coefficient The calculation formula is:[[]]END]]

[0091]

[0092] Step 205: Calculate the second mean and the second variance of the discretized user voltage.

[0093] Use the same method as in step 204 above to calculate the mean variance and the auxiliary coefficient

[0094] Step 206: Based on the voltage mean distance calculation formula, calculate the voltage mean distance between the three-phase voltage of the substation area and the user voltage according to the first mean and the second mean.

[0095] Among them, the calculation formula of the voltage mean distance d1 is:[[]]END]]

[0096]

[0097] Step 207: Based on the voltage variance distance calculation formula, calculate the voltage variance distance between the three-phase voltage of the power distribution area and the user voltage according to the first variance and the second variance.

[0098] In this embodiment, the calculation formula of the voltage variance distance d2 is:

[0099]

[0100] Step 208: Calculate the signal distance between the three-phase voltage of the power distribution area and the user voltage according to the voltage mean distance and the voltage variance distance.

[0101] In one implementation manner, the calculation formula of the signal distance d vj is:

[0102] d vj = d1 * d2.

[0103] Step 209: Based on the signal distance, select the initial reference samples and adjacent samples during clustering.

[0104] It can be understood that in this application, referring to the gravitational field concept of physical celestial bodies, several adjacent samples closest to the initial reference samples are screened out to form a stable region. Analyze the gravity between the initial reference samples and adjacent samples. If a certain gravity is too large, it indicates that this point is an abnormal point and does not belong to this stable region. If a certain gravity is too small, this point will be quickly pulled closer and swallowed.

[0105] Step 210: Delete the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain the gravitational field samples.

[0106] It can be understood that in one implementation manner, deleting the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain the gravitational field samples specifically includes:

[0107] Obtain the gravitational field range of the initial reference samples;

[0108] According to the gravitational density calculation formula, calculate the gravitational density of the initial reference samples within the gravitational field range;

[0109] Based on the gravitational coefficient calculation formula, calculate the abnormal gravitational coefficients of each adjacent sample within the gravitational field range according to the gravitational density;

[0110] Delete the adjacent samples with abnormal gravitational coefficients greater than the preset threshold, and use the remaining adjacent samples as the gravitational field samples.

[0111] It can be understood that for the gravitational field range gr pis established according to the k-distance to determine the gravitational field range gr of the initial reference sample p p .

[0112] Among them, the gravitational density calculation formula is:

[0113]

[0114] In the formula, grt p is the gravitational density of the initial reference sample p, median() represents taking the median of the numerical sequence, |gr p | represents the number of samples within the gravitational field range gr of the initial reference sample p p , grd pq represents the gravitational distance between the initial reference sample p and the adjacent sample q within the gravitational field range.

[0115] Specifically, the gravitational coefficient calculation formula is:

[0116]

[0117] In the formula, out p is the gravitational coefficient of the initial reference sample p, grta p is the average gravitational density of the initial reference sample p, grta q is the average gravitational density of the initial reference sample q.

[0118] It can be understood that the calculation formula of the average gravitational density grta p is:

[0119]

[0120] In the formula, r represents the number of the adjacent sample within the gravitational field range, grt r is the gravitational density of the adjacent sample r.

[0121] Step 211: Aggregate the initial reference sample and the gravitational field samples according to the nuclear composition coefficient to obtain a number of initial topological structures.

[0122] The sample point core with the highest matching degree among the adjacent samples is aggregated with the adjacent samples within the gravitational field range to form a number of initial topological structures. Analyze the difference between the initial reference sample and the gravitational field samples, that is, the nuclear composition coefficient nhp i , and the corresponding calculation formula of the nuclear composition coefficient nhp i is:

[0123]

[0124] In the formula, J represents the total number of samples, sim ijIndicates calculating the similarity sim between the three-phase voltage and the user voltage ij , and its corresponding calculation formula is:

[0125]

[0126] Step 212: Aggregate the initial topological structure according to the topological similarity to obtain a new topological structure.

[0127] It can be understood that in one implementation, aggregating the initial topological structure according to the topological similarity to obtain a new topological structure specifically includes:

[0128] Calculate the topological similarity between the initial topological structures;

[0129] Aggregate the initial topological structures with topological similarity greater than the preset similarity threshold to obtain a new topological structure.

[0130] Among them, the topological similarity sdp i The calculation formula is:

[0131]

[0132] In the formula, nm represents the number of samples in the initial topological structure.

[0133] When the topological similarity is greater than the preset similarity threshold δ, aggregate the initial topological structures, and then recalculate the similarity between the topological structures. It is like rolling a snowball until no more aggregation is possible. Each topological structure represents a physical relationship between a station line and a user.

[0134] Step 213: Aggregate the new topological structure according to the new topological similarity until no more aggregation is possible to obtain the topological structure of the corresponding substation area to be constructed.

[0135] Compared with the prior art, this embodiment has the following advantages:

[0136] 1). Using the variance and mean of time-series data to measure the similarity between samples, it does not require two samples to be of equal length, has fewer constraints, and can handle data missing problems caused by acquisition equipment failures and communication failures in actual analysis.

[0137] 2). Using the concept of gravitational field to construct an outlier filtering model, which can screen out obviously incorrect data points before aggregating the topological structure

[0138] 3). Analyze the differences between data samples and neighboring samples, that is, the kernel component coefficients, construct the initial topological structure, and then aggregate based on the similarity between topological structures without the need to specify the number of clusters in advance.

[0139] In this embodiment, first, the voltage signal corresponding to the substation area to be constructed is obtained. Then, after discretizing the voltage signal, the mean and variance of the discretized voltage signal are calculated. Next, based on the mean and variance, the signal distance between the voltage signals is calculated. Then, based on the signal distance, the initial reference samples and adjacent samples for clustering are selected. Subsequently, according to the gravitational field parameters of the initial reference samples and adjacent samples, the abnormal adjacent samples are deleted to obtain the gravitational field samples. Then, according to the nuclear component coefficient, the initial reference samples and the gravitational field samples are aggregated to obtain several initial topological structures. Next, according to the topological similarity, the initial topological structures are aggregated to obtain a new topological structure. Finally, according to the new topological similarity, the new topological structures are aggregated until no further aggregation is possible, and the substation area topological structure corresponding to the substation area to be constructed is obtained. In this application, the signal distance is calculated based on the mean and variance between voltage signals. Based on the gravitational field parameters, data outliers (i.e., adjacent samples) are excluded, and autonomous community structure aggregation is carried out to realize the construction of the substation area topology, thereby solving the technical problem that the existing methods for constructing the substation area topology are sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect.

[0140] The second aspect of the embodiment of the present application provides an embodiment of a device for constructing a substation area topology.

[0141] Please refer to Figure 3 , the structural schematic diagram of a device for constructing a substation area topology in the embodiment of the present application.

[0142] A device for constructing a substation area topology in this embodiment includes:

[0143] An acquisition unit, configured to acquire the voltage signal corresponding to the substation area to be constructed;

[0144] A first calculation unit, configured to calculate the mean and variance of the discretized voltage signal after discretizing the voltage signal;

[0145] A second calculation unit, configured to calculate the signal distance between the voltage signals based on the mean and variance;

[0146] A selection unit, configured to select the initial reference samples and adjacent samples for clustering based on the signal distance;

[0147] A deletion unit, configured to delete the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain the gravitational field samples;

[0148] A first aggregation unit, configured to aggregate the initial reference samples and the gravitational field samples according to the nuclear component coefficient to obtain several initial topological structures;

[0149] The second aggregation unit is configured to aggregate the initial topological structure according to the topological similarity to obtain a new topological structure;

[0150] The third aggregation unit is configured to aggregate the new topological structure according to the new topological similarity until no further aggregation is possible, to obtain the substation area topological structure corresponding to the to-be-constructed substation area.

[0151] Further, the voltage signal includes: three-phase substation area voltage and user voltage;

[0152] The first calculation unit specifically includes:

[0153] The first discretization subunit is configured to discretize the three-phase substation area voltage to obtain the discretized three-phase substation area voltage;

[0154] The second discretization subunit is configured to discretize the user voltage to obtain the discretized user voltage;

[0155] The first calculation subunit is configured to calculate the first mean value and the first variance of the discretized three-phase substation area voltage;

[0156] The second calculation subunit is configured to calculate the second mean value and the second variance of the discretized user voltage.

[0157] Specifically, the second calculation unit specifically includes:

[0158] The third calculation subunit is configured to calculate the voltage mean distance between the three-phase substation area voltage and the user voltage based on the voltage mean distance calculation formula according to the first mean value and the second mean value;

[0159] The fourth calculation subunit is configured to calculate the voltage variance distance between the three-phase substation area voltage and the user voltage based on the voltage variance distance calculation formula according to the first variance and the second variance;

[0160] The fifth calculation subunit is configured to calculate the signal distance between the three-phase substation area voltage and the user voltage according to the voltage mean distance and the voltage variance distance.

[0161] Further, the deletion unit specifically includes:

[0162] The acquisition subunit is configured to acquire the gravitational field range of the initial reference sample;

[0163] The sixth calculation subunit is configured to calculate the gravitational density of the initial reference sample within the gravitational field range according to the gravitational density calculation formula;

[0164] The seventh calculation subunit is used to calculate the abnormal gravitational coefficients of adjacent samples within the gravitational field according to the gravitational coefficient calculation formula based on the gravitational density;

[0165] The deletion subunit is used to delete adjacent samples with abnormal gravitational coefficients greater than a preset threshold, and use the remaining adjacent samples as gravitational field samples.

[0166] Optionally, the gravitational density calculation formula is:

[0167]

[0168] In the formula, grt p is the gravitational density of the initial reference sample p, median() represents taking the median of a numerical sequence, |gr p | represents the number of samples within the gravitational field range gr p of the initial reference sample p, and grd pq represents the gravitational distance between the initial reference sample p and the adjacent sample q within the gravitational field range.

[0169] Furthermore, the gravitational coefficient calculation formula is:

[0170]

[0171] In the formula, out p is the gravitational coefficient of the initial reference sample p, grta p is the average gravitational density of the initial reference sample p, and grta q is the average gravitational density of the initial reference sample q.

[0172] Furthermore, the second aggregation unit specifically includes:

[0173] The eighth calculation subunit is used to calculate the topological similarity between the initial topologies;

[0174] The first aggregation subunit is used to aggregate the initial topologies with the topological similarity greater than a preset similarity threshold to obtain a new topology.

[0175] In this embodiment, first, the voltage signal corresponding to the substation area to be constructed is obtained. Then, after discretizing the voltage signal, the mean and variance of the discretized voltage signal are calculated. Next, based on the mean and variance, the signal distance between voltage signals is calculated. Then, based on the signal distance, the initial reference samples and adjacent samples for clustering are selected. Subsequently, according to the gravitational field parameters of the initial reference samples and adjacent samples, the abnormal adjacent samples are deleted to obtain the gravitational field samples. Then, according to the kernel component coefficient, the initial reference samples and gravitational field samples are aggregated to obtain several initial topological structures. Next, according to the topological similarity, the initial topological structures are aggregated to obtain a new topological structure. Finally, according to the new topological similarity, the new topological structures are aggregated until no further aggregation is possible, obtaining the substation area topological structure corresponding to the substation area to be constructed. In this application, the signal distance is calculated through the mean and variance between voltage signals. Based on the gravitational field parameters, data outliers (i.e., adjacent samples) are excluded, and autonomous community structure aggregation is carried out to realize the construction of the substation area topology, thereby solving the technical problem that the existing methods for constructing the substation area topology are sensitive to outliers. When the value of a certain sample in a certain dimension is particularly large, the clustering center tends to the outlier, resulting in a low accuracy of the clustering effect.

[0176] The third aspect of the embodiment of this application provides an embodiment of a device for constructing a substation area topology.

[0177] A device for constructing a substation area topology includes a processor and a memory; the memory is used to store program code and transmit the program code to the processor; the processor is used to execute the method for constructing the substation area topology in the first aspect according to the instructions in the program code.

[0178] The fourth aspect of the embodiment of this application provides an embodiment of a storage medium.

[0179] A storage medium is used to store program code, and the program code is used to execute the method for constructing the substation area topology in the first aspect.

[0180] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0181] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another power grid network to be installed, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0182] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0183] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0184] If the above-mentioned integrated 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 technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0185] As described above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for constructing a substation area topology, characterized in that Including: Obtain the voltage signal corresponding to the substation area to be constructed; After discretizing the voltage signal, calculate the mean and variance of the discretized voltage signal; Calculate the signal distance between the voltage signals through the mean and variance; Based on the signal distance, select the initial reference samples and adjacent samples during clustering; Delete the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain the gravitational field samples; Aggregate the initial reference samples and the gravitational field samples according to the nuclear composition coefficient to obtain a number of initial topological structures; Aggregate the initial topological structures according to the topological similarity to obtain a new topological structure; Aggregate the new topological structures according to the new topological similarity until no aggregation is possible to obtain the substation area topological structure corresponding to the substation area to be constructed; Among them, deleting the abnormal adjacent samples according to the gravitational field parameters of the initial reference samples and adjacent samples to obtain the gravitational field samples specifically includes: Obtain the gravitational field range of the initial reference samples; Calculate the gravitational density of the initial reference samples within the gravitational field range according to the gravitational density calculation formula; Based on the gravitational coefficient calculation formula, calculate the abnormal gravitational coefficient of each adjacent sample within the gravitational field range according to the gravitational density; Delete the adjacent samples with abnormal gravitational coefficients greater than the preset threshold, and use the remaining adjacent samples as the gravitational field samples; The gravitational density calculation formula is: ； In the formula, is the gravitational density of the initial reference sample p, represents taking the median of the numerical sequence, represents the range of the gravitational field of the initial reference sample p the number of samples within, represents the gravitational distance between the initial reference sample p and the adjacent sample q within the gravitational field range; The gravitational coefficient calculation formula is: ； In the formula, is the gravitational coefficient of the initial reference sample p, is the average gravitational density of the initial reference sample p, is the average gravitational density of the initial reference sample q.

2. The method for constructing the topological structure of the power distribution area according to claim 1, wherein The voltage signal includes: three-phase voltage of the substation area and user voltage; After discretizing the voltage signal, calculating the mean and variance of the discretized voltage signal specifically includes: Discretize the three-phase voltage of the substation area to obtain the discretized three-phase voltage of the substation area; Discretize the user voltage to obtain the discretized user voltage; Calculate the first mean and the first variance of the discretized three-phase voltage of the substation area; Calculate the second mean and the second variance of the discretized user voltage.

3. The method for constructing the substation area topology according to claim 2, wherein Calculating the signal distance between the voltage signals through the mean and variance specifically includes: Based on the voltage mean distance calculation formula, calculate the voltage mean distance between the three-phase voltage of the substation area and the user voltage according to the first mean and the second mean; Based on the voltage variance distance calculation formula, calculate the voltage variance distance between the three-phase voltage of the substation area and the user voltage according to the first variance and the second variance; Calculate the signal distance between the three-phase voltage of the substation area and the user voltage according to the voltage mean distance and the voltage variance distance.

4. The method for constructing the substation area topology according to claim 1, wherein Aggregating the initial topological structures according to the topological similarity to obtain a new topological structure specifically includes: Calculate the topological similarity between the initial topological structures; Aggregate the initial topological structures with the topological similarity greater than the preset similarity threshold to obtain a new topological structure.

5. A device for constructing a substation area topology, characterized in that Including: An acquisition unit for acquiring the voltage signal corresponding to the substation area to be constructed; A first calculation unit for calculating the mean and variance of the discretized voltage signal after discretizing the voltage signal; A second calculation unit, configured to calculate a signal distance between the voltage signals based on the mean value and variance; A selection unit, configured to select an initial reference sample and adjacent samples during clustering based on the signal distance; A deletion unit, configured to delete abnormal adjacent samples according to the gravitational field parameters of the initial reference sample and the adjacent samples, so as to obtain gravitational field samples; A first aggregation unit, configured to aggregate the initial reference sample and the gravitational field samples according to a kernel component coefficient, so as to obtain a plurality of initial topological structures; A second aggregation unit, configured to aggregate the initial topological structures according to topological similarity, so as to obtain a new topological structure; A third aggregation unit, configured to aggregate the new topological structures according to a new topological similarity until no further aggregation is possible, so as to obtain a substation area topological structure corresponding to the to-be-constructed substation area; Wherein, deleting the abnormal adjacent samples according to the gravitational field parameters of the initial reference sample and the adjacent samples to obtain gravitational field samples specifically includes: Obtaining a gravitational field range of the initial reference sample; Calculating a gravitational density of the initial reference sample within the gravitational field range according to a gravitational density calculation formula; Calculating an abnormal gravitational coefficient of each adjacent sample within the gravitational field range based on a gravitational coefficient calculation formula according to the gravitational density; Deleting adjacent samples with an abnormal gravitational coefficient greater than a preset threshold, and using the remaining adjacent samples as gravitational field samples; The gravitational density calculation formula is: ； In the formula, is the gravitational density of the initial reference sample p, represents taking the median of the numerical sequence, represents the range of the gravitational field of the initial reference sample p the number of samples within, represents the gravitational distance between the initial reference sample p and the adjacent sample q within the gravitational field range; The gravitational coefficient calculation formula is: ； In the formula, is the gravitational coefficient of the initial reference sample p, is the average gravitational density of the initial reference sample p, is the average gravitational density of the initial reference sample q.

6. A device for constructing a substation area topology, characterized in that Comprising a processor and a memory; The memory is configured to store program code and transmit the program code to the processor; The processor is configured to execute the method for constructing a substation area topology according to any one of claims 1 to 4 according to instructions in the program code.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium is configured to store program code, and the program code is used to execute the method for constructing a substation area topology according to any one of claims 1 to 4.

Images