Transformer area load decomposition method based on user clustering and related device

Abstract

The application provides a user group-based transformer area load decomposition method and related device, the method comprises the following steps: obtaining the electricity consumption profile information of all users in a target transformer area, obtaining a plurality of electricity consumption profile information; classifying all users in the target transformer area according to the plurality of electricity consumption profile information, obtaining a plurality of classification groups; performing a preset first calculation operation on each classification group in the plurality of classification groups, obtaining a plurality of contribution weight coefficients; determining the optimization interval corresponding to each contribution weight coefficient in the plurality of contribution weight coefficients according to a preset numerical floating ratio, obtaining a plurality of optimization intervals; randomly generating a weight coefficient vector for each optimization interval in the plurality of optimization intervals, obtaining a plurality of initial weight coefficient vectors; performing a preset second calculation operation on each initial weight coefficient vector in the plurality of initial weight coefficient vectors, obtaining a plurality of optimal weight coefficient vectors. The reliability and accuracy of the transformer area load decomposition result can be improved.

Description

Technical Field

[0001] This application relates to the field of power grid planning technology, and in particular to a method and related apparatus for load decomposition of distribution areas based on user grouping. Background Technology

[0002] Currently, classifying users solely by electricity consumption category at each metering point and directly using the electricity consumption percentage of each category as the weighting coefficient is too simplistic and may lead to unreliable weighting coefficients during load decomposition. Furthermore, adjusting the weighting coefficients based on existing typical load curve feature libraries without restricting the range of their values ​​may cause the model to get stuck in local optima instead of reaching a better global optimum.

[0003] Therefore, improving the reliability and accuracy of load decomposition results for distribution areas is an urgent issue to be addressed. Summary of the Invention

[0004] This application provides a method and related apparatus for load decomposition of transformer substations based on user grouping. It can group users according to their electricity consumption information and optimize the weighting coefficients based on electricity consumption behavior data to improve the reliability and accuracy of the load decomposition results.

[0005] In a first aspect, embodiments of this application provide a method for load decomposition of distribution areas based on user grouping, the method comprising:

[0006] Obtain the electricity consumption records of all users in the target transformer area to obtain multiple electricity consumption record information; the multiple electricity consumption record information is used to characterize the transformer load of the target transformer area;

[0007] Based on the multiple electricity consumption records, all users in the target transformer area are classified into multiple category groups; the category groups include any one of the following: residential life, charging service, public service, and commercial operation;

[0008] For each of the multiple classification groups, a preset first calculation operation is performed to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient.

[0009] The optimization interval corresponding to each of the multiple contribution weight coefficients is determined according to the preset numerical fluctuation ratio, thus obtaining multiple optimization intervals;

[0010] Multiple initial weight coefficient vectors are obtained by randomly generating a weight coefficient vector for each of the multiple optimization intervals; each initial weight coefficient vector corresponds one-to-one with an optimization interval.

[0011] A preset second calculation operation is performed on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors.

[0012] Secondly, embodiments of this application provide a load decomposition device for transformer areas based on user grouping, the device comprising:

[0013] The acquisition module is used to acquire the electricity consumption records of all users in the target transformer area, resulting in multiple electricity consumption records; the multiple electricity consumption records are used to characterize the transformer load of the target transformer area.

[0014] The classification module is used to classify all users in the target transformer area according to the multiple electricity consumption records to obtain multiple classification groups; the classification groups include any one of the following: residential life, charging service, public service, and commercial operation;

[0015] The first calculation module is used to perform a preset first calculation operation for each of the multiple classification groups to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient.

[0016] The determination module is used to determine the optimization interval corresponding to each of the multiple contribution weight coefficients according to a preset numerical fluctuation ratio, thereby obtaining multiple optimization intervals;

[0017] The generation module is used to randomly generate a weight coefficient vector based on each of the plurality of optimization intervals to obtain a plurality of initial weight coefficient vectors; the initial weight coefficient vectors correspond one-to-one with the optimization intervals.

[0018] The second calculation module is used to perform a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors.

[0019] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0021] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0022] By implementing the embodiments of this application, users can be grouped according to the electricity consumption information of users in the distribution area, and weighting coefficients can be optimized according to electricity consumption behavior data, so as to improve the reliability and accuracy of the load decomposition results of the distribution area. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of a classification process for user groups in a transformer area, provided in an embodiment of this application.

[0025] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0026] Figure 3 This is a flowchart illustrating a method for load decomposition of transformer areas based on user grouping, provided in an embodiment of this application.

[0027] Figure 4 This is a functional module block diagram of a user-group-based load decomposition device for transformer areas provided in an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0029] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0030] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0031] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0032] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0033] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0034] The following is an explanation of the relevant terms used in this application:

[0035] A distribution area refers to a collection of electrical equipment and lines within a power supply service area, typically consisting of one or more distribution transformers and the users they supply.

[0036] Electricity consumption category at metering point: This refers to the electricity consumption category of a user or equipment, which can be divided and classified according to the user's electricity demand characteristics, usage purpose, and billing requirements.

[0037] Currently, classifying users solely by electricity consumption category at each metering point and directly using the electricity consumption percentage of each category as the weighting coefficient is overly simplistic and may lead to unreliable weighting coefficients during load decomposition. Furthermore, adjusting the weighting coefficients based on existing typical load curve feature libraries without limiting the range of their values ​​may cause the model to get stuck in local optima instead of reaching a better global optimum. Therefore, improving the reliability and accuracy of transformer area load decomposition results is an urgent issue that needs to be addressed.

[0038] To address the aforementioned issues, this application provides a method and related apparatus for load decomposition of transformer substations based on user grouping. First, electricity consumption profiles of all users in a target transformer substation are acquired, resulting in multiple electricity consumption profiles. These profiles characterize the load of the target substation. All users in the target substation are then categorized based on these profiles, resulting in multiple category groups. These category groups include any of the following: residential, charging services, public services, and commercial operations. Next, a preset first calculation operation is performed on each of the multiple category groups to obtain multiple contribution weight coefficients. Each category group corresponds to one contribution weight coefficient. An optimization interval is determined for each of the multiple contribution weight coefficients based on a preset numerical fluctuation ratio, resulting in multiple optimization intervals. A weight coefficient vector is randomly generated for each of the multiple optimization intervals, resulting in multiple initial weight coefficient vectors. Each initial weight coefficient vector corresponds one-to-one with an optimization interval. Finally, a preset second calculation operation is performed on each of the multiple initial weight coefficient vectors to obtain multiple optimal weight coefficient vectors. Users can be segmented based on their electricity consumption information, and weighting coefficients can be optimized based on electricity behavior data to improve the reliability and accuracy of load decomposition results for distribution areas.

[0039] The following is combined with Figure 1 This application describes a classification process for user groups in a transformer substation, as described in one embodiment. Figure 1 This is a schematic diagram of the classification process of user groups in a transformer substation according to an embodiment of this application. The user classification groups include residential life, charging service, public service, and shop operation.

[0040] This process involves acquiring electricity usage records for all users in the target transformer area. These records include the electricity usage category at the metering point and the user's address information, allowing for user classification based on these criteria. First, all users are initially classified according to the electricity usage category field, which indicates the user's electricity usage type. Specifically, users in the residential category are divided into a residential group, users in the commercial category into a shop operation group, and all other categories into a public service group. Then, the residential group is further classified based on the user's address information. Within the residential group, users whose addresses contain the keyword "public service" are classified into the public service group, and those whose addresses contain the keyword "charging service" are classified into the charging service group. Other users are left unclassified. Finally, all users in the target transformer area are categorized into four groups: residential, charging service, public service, and shop operation. This facilitates subsequent data collection from representative users within each group, reducing the cost and complexity of data collection.

[0041] It should be noted that public service keywords include, but are not limited to, lighting, elevators, fire protection, pumps, power distribution, passenger elevators, and security, while charging service keywords include, but are not limited to, charging piles and charging stations.

[0042] The characteristics of these four classification groups are shown in the table below:

[0043]

[0044] In one possible embodiment, the user's electricity consumption category is residential, but their electricity address information is "elevator in building xx, xxx, xxx, xxx Road, xx District, xx City, xx Province". Since the electricity address information contains the public service keyword "elevator", the user can be classified into the public service category group.

[0045] It is evident that segmenting users into groups facilitates subsequent data collection from representative users in each category, thereby significantly reducing the cost and complexity of data collection and providing a more comprehensive and accurate reflection of the electricity load characteristics of users in the target distribution area.

[0046] The following is combined with Figure 2 The electronic devices in the embodiments of this application will be described. Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 2 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0047] The processor is mainly used for:

[0048] Obtain the electricity consumption records of all users in the target transformer area to obtain multiple electricity consumption record information; these multiple electricity consumption record information are used to characterize the transformer load of the target transformer area.

[0049] Based on multiple electricity consumption records, all users in the target area are classified into multiple category groups; the category groups include any of the following: residential life, charging service, public service, and commercial operation;

[0050] For each of the multiple classification groups, a preset first calculation operation is performed to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient.

[0051] The optimization interval corresponding to each of the multiple contribution weight coefficients is determined according to the preset numerical fluctuation ratio, thus obtaining multiple optimization intervals;

[0052] Multiple initial weight coefficient vectors are obtained by randomly generating a weight coefficient vector for each of the multiple optimization intervals; each initial weight coefficient vector corresponds one-to-one with an optimization interval.

[0053] For each of the multiple initial weight coefficient vectors, a preset second calculation operation is performed to obtain multiple optimal weight coefficient vectors.

[0054] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0055] The processor can be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuitry, etc., and the storage unit can be a memory.

[0056] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0057] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device can be used to perform functions such as... Figure 1 The classification process described above.

[0058] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 3 This application describes a method for load decomposition of transformer areas based on user grouping in its embodiments. Figure 3 A flowchart illustrating a user-group-based transformer area load decomposition method provided in this application embodiment specifically includes the following steps:

[0059] Step S301: Obtain the electricity consumption records of all users in the target distribution area to obtain multiple electricity consumption records.

[0060] The multiple electricity consumption records are used to characterize the load of the target transformer area.

[0061] Specifically, electricity consumption records for all users in the target distribution area can be obtained from the power company or grid management system, resulting in multiple electricity consumption records. These records include the electricity consumption category at the metering point and the electricity address information. The metering point electricity consumption category includes residential, commercial, and other categories, while the electricity address information includes the user's specific electricity address, which can be used to identify each user's location and electricity consumption characteristics. These multiple electricity consumption records not only characterize the load situation of the target distribution area but also provide necessary data support and decision-making basis for the grid operation and management of the target distribution area.

[0062] Step S302: Classify all users in the target distribution area according to the multiple electricity consumption records to obtain multiple classification groups.

[0063] The classification groups include any of the following: residential life, charging services, public services, and shop operations.

[0064] Specifically, users whose electricity consumption is categorized as "Residential" can be further divided into "Residential," "Commercial" into "Shop Operation," and all other categories into "Public Services." Within the "Residential" category, users whose address information contains the keyword "Public Services" are classified as "Public Services," and those whose address information contains the keyword "Charging Services" are classified as "Charging Services." Other users are left unclassified. Thus, all users in the target transformer area can be divided into multiple categories, each including any of the following: Residential, Charging Services, Public Services, and Shop Operation.

[0065] Step S303: Perform a preset first calculation operation for each of the multiple classification groups to obtain multiple contribution weight coefficients.

[0066] Specifically, each classification group corresponds to a contribution weight coefficient. The step of performing a preset first calculation operation on each of the multiple classification groups to obtain multiple contribution weight coefficients includes: selecting p typical users in the first classification group and collecting load data from the p typical users according to a preset collection strategy to obtain a load dataset; p is a positive integer; the first classification group is any one of the multiple classification groups; calculating the load dataset according to a preset clustering algorithm to obtain a first typical load curve; the horizontal axis of the first typical load curve represents time, and the vertical axis represents load data; and determining the contribution weight coefficient of the first classification group based on the first typical load curve.

[0067] The specific steps of selecting p typical users in the first classification group and collecting load data from the p typical users according to a preset collection strategy to obtain a load dataset include: obtaining the daily frozen electricity of each user in the first classification group to obtain multiple first-day frozen electricity values; sorting the users in the first classification group according to the daily frozen electricity values ​​from largest to smallest based on the multiple first-day frozen electricity values ​​to obtain a first user sorting list; summing the daily frozen electricity values ​​of the first p-1 users and the first p users in the first user sorting list to obtain the second-day frozen electricity value and the third-day frozen electricity value; determining half of the total daily frozen electricity value of the first classification group as a reference electricity value threshold; if the second-day frozen electricity value is less than the reference electricity value threshold and the third-day frozen electricity value is greater than or equal to the reference electricity value threshold, then selecting the p users as the p typical users; and collecting data from the p typical users according to a preset collection frequency and collection duration to obtain the load dataset.

[0068] Specifically, firstly, the daily frozen electricity consumption of each user in the first category group is collected, resulting in multiple first-day frozen electricity consumption figures, representing each user's daily electricity consumption. Then, users are sorted from largest to smallest daily frozen electricity consumption, forming a first-user ranking list. The daily frozen electricity consumption of the first p-1 users in the first-user ranking list is summed to obtain the second-day frozen electricity consumption. The daily frozen electricity consumption of the first p users is then summed to obtain the third-day frozen electricity consumption. To select representative users in the first category group, the total daily frozen electricity consumption of this category group is obtained, and 50% of this total daily frozen electricity consumption is used as a reference electricity consumption threshold. If the second-day frozen electricity consumption is less than the reference electricity consumption threshold, and the third-day frozen electricity consumption is greater than or equal to the reference electricity consumption threshold, then these p users are identified as p typical users in the first category group. Finally, data is collected from these p typical users according to a preset collection frequency and duration to obtain a load dataset. The collection frequency can be once every 15 minutes, and the collection duration can be one day (24 hours), without specific limitations. It should be noted that there are 24 hours in a day, and four 15-minute time intervals in an hour. Therefore, each user corresponds to 96 data points in a day.

[0069] The load dataset comprises p load data subsets; the step of calculating the first typical load curve based on a preset clustering algorithm includes:

[0070] A1. Determine p load curves based on the p load data sets;

[0071] The load dataset consists of p load data subsets, each corresponding to a typical user. Based on these p load data subsets, p load curves are generated for each typical user, with each load curve representing the electricity consumption of that user. It should be noted that the load curves are curves formed by the load data of a typical user at 96 time points throughout the day. The horizontal axis of the curve represents the time of day, and the vertical axis represents the load at each time point.

[0072] A2. Randomly select k load curves from the p load curves, and use the k load curves as the k first center points of k clusters respectively; k is a positive integer;

[0073] Specifically, k load curves are randomly selected from the p load curves, and k clusters are created. Each load curve is used as the center point of each cluster, resulting in k first center points. It should be noted that the profile coefficient can be used as an evaluation index for the k value, and it is calculated according to a preset profile coefficient calculation formula to determine the optimal k value. The profile coefficient calculation formula is as follows:

[0074]

[0075] Where s(i) is the profile coefficient corresponding to load curve i, a(i) is the average distance between load curve i and other load curves in its cluster, and b(i) is the minimum average distance between load curve i and all load curves in other clusters.

[0076] Specifically, the silhouette coefficient s(i) ranges from -1 to 1. If s(i) is close to 1, it indicates that the load curve i is correctly clustered, and its distance from other load curves within the same cluster is much smaller than its distance from load curves within other clusters. If s(i) is close to -1, it indicates that the load curve i may have been incorrectly clustered into an adjacent cluster. If s(i) is close to 0, it indicates that the load curve i is at the boundary between two clusters. Then, the average silhouette coefficient is obtained by averaging the silhouette coefficients of all load curves. This average silhouette coefficient is used to represent the overall clustering quality evaluation index. The closer the average silhouette coefficient is to 1, the more ideal the clustering result. Therefore, the average silhouette coefficient corresponding to different k values ​​can be calculated, and the k value that makes the average silhouette coefficient closest to 1 can be selected as the optimal k value.

[0077] A3. Calculate the distance between each of the p load curves and the k first center points, and assign it to the cluster corresponding to the nearest first center point;

[0078] This involves calculating the distance between each of the p load curves and each first center point, and then assigning each load curve to the cluster corresponding to the nearest first center point. In other words, each load curve is assigned to the nearest cluster. It should be noted that each load curve corresponds to load data collected at 96 time points, which can be viewed as a 96-dimensional vector. Similarly, each center point can also be considered a 96-dimensional vector. Therefore, the distance between the load curve and the first center point can be calculated using the Euclidean distance formula.

[0079] A4. After the p load curves are evenly distributed, the average value of all load curves in each of the k clusters is taken to obtain k second center points; the k second center points correspond one-to-one with the k clusters.

[0080] After all p load curves are assigned to the nearest cluster, the average value of all load curves within each cluster is taken to obtain the second center point corresponding to each cluster, i.e., the k second center points corresponding to k clusters.

[0081] A5. Repeat steps A3 and A4 until the center point of each of the k clusters no longer changes, then proceed to step A6.

[0082] In this process, steps A3 and A4 are repeated to determine the optimal center point for each cluster. When the center point of each of the k clusters no longer changes, it is determined that the clustering results of each cluster have converged to a stable state.

[0083] A6. Determine the center point of the cluster with the most load curves among the k clusters as the first typical load curve.

[0084] Among them, the cluster with the most load curves among the k clusters is the most representative, and its center point is taken as the first typical load curve corresponding to the first classification group.

[0085] It should be noted that typical load curves for each classification group can be aggregated using the k-means clustering algorithm, or hierarchical clustering, DBSCAN, and other clustering algorithms can be used; no specific limitation is made here.

[0086] The specific steps of determining the contribution weight coefficient of the first classification group based on the first typical load curve include:

[0087] The contribution weight coefficient is obtained by calculating the first typical load curve according to the preset first calculation formula; the first typical load curve is [α1, α2, α3, ..., α n ];

[0088] The first calculation formula is as follows:

[0089]

[0090] Where, d α The total daily frozen electricity for the first category group; ω α The contribution weight coefficient for the first classification group; α n The load data is collected at the nth time point in the first typical load curve; n is an integer greater than 1, and c is a positive integer.

[0091] In one possible embodiment, n can be 96, then c is 4. α1+α2+α3+…+α n This represents the sum of load data collected every 15 minutes, i.e., 4 load data collections per hour. When calculating the total daily frozen electricity for the first category group, the total daily frozen electricity d can be obtained by collecting and summing the load data for the first category group over a 24-hour period. α This data collection process requires 96 data acquisitions, with electricity measured in kilowatt-hours (kWh) and load measured in kilowatts (kW). Therefore, dividing the sum of the load data from these 96 acquisitions by 4 yields the corresponding electricity data for 24 hours. It can be seen that the total daily frozen electricity d for the first category group... α The data is obtained through actual collection, and the only unknown in the first calculation formula is ω. α Therefore, the contribution weight coefficient ω of the first classification group can be calculated using this first calculation formula. α .

[0092] Step S304: Determine the optimization interval corresponding to each of the multiple contribution weight coefficients according to the preset numerical fluctuation ratio, thereby obtaining multiple optimization intervals.

[0093] The numerical fluctuation ratio can be 10%, without specific limitation. Therefore, each contribution weight coefficient can be fluctuated by 10% before and after, and this fluctuation can be used as the optimization interval corresponding to that contribution weight coefficient, resulting in multiple optimization intervals. For example, if the contribution weight coefficient is 0.8, after fluctuating it by 10% before and after, its corresponding optimization interval can be [0.72, 0.88].

[0094] Step S305: Randomly generate a weight coefficient vector for each of the multiple optimization intervals to obtain multiple initial weight coefficient vectors.

[0095] The initial weight coefficient vector corresponds one-to-one with the optimization interval. For each optimization interval, a weight coefficient vector is randomly generated, resulting in multiple initial weight coefficient vectors, all of which are 96-dimensional vectors.

[0096] Step S306: Perform a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors.

[0097] Specifically, the step of performing a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors includes:

[0098] B1. Calculate the first weight coefficient vector w according to the preset second calculation formula to obtain the reference root mean square error value; the first weight coefficient vector w is any one of the plurality of initial weight coefficient vectors; the first weight coefficient vector w is [ω1, ω2, ω3, ..., ω n ];

[0099] The second calculation formula is as follows:

[0100]

[0101] Where L(w) is the reference root mean square error value; h(x) i The reference transformer load curve is obtained by weighted summation based on the weighting coefficient vector and the typical load curve; x i The typical load curves for the multiple taxonomic groups on day i; y i The load curve of the transformer substation on the i-th day is the actual data collected; m is the total number of days in the sample; i is a positive integer;

[0102] It should be noted that the reference transformer load curve h(x) can be calculated according to the preset weighted calculation formula. i The weighted calculation formula is as follows:

[0103] A*X=h(x i )

[0104] Where A = [w1, w2, w3, ..., w N ] is used to represent the weight coefficient vector corresponding to the typical load curves of M classification groups, and w M Let X be the weight coefficient vector corresponding to the typical load curve of the Mth classification group; X = [X1, X2, X3, ..., X...]. M ] T A matrix representing the typical load curves of M taxonomic groups, where X N This is the typical load curve for the Mth taxonomic group; h(x) i )=[β1,β2,β3,…,β 96 ] T To represent the load curve of a reference station area recorded at 15-minute intervals, β 96This represents the load data for the transformer substation corresponding to the 96th time point, with a 15-minute interval between any two time points. Here, M is a positive integer.

[0105] Where m represents the total number of days in the sample, meaning that one or more days of transformer load data can be used as the sample; no specific limitation is made here. x i For the typical load curves of multiple taxonomic groups on day i, i.e., x i Let y be the typical load curves for M taxonomic groups on day i, and y be the typical load curves for M taxonomic groups on day i. i This represents the actual data of the load curve of the transformer substation on the i-th day.

[0106] B2. Calculate the first gradient of the first weight coefficient vector w, and iteratively update the first weight coefficient vector w based on the first gradient;

[0107] B3. Repeat step B2 until L(w) no longer decreases after 5 consecutive iterations. Then stop updating the first weight coefficient vector w and obtain the optimal weight coefficient vector.

[0108] In this process, step B2 is repeatedly executed, with each iteration updating L(w) to a smaller value, until the convergence condition for iterative updates is met. At this point, the update of the first weight coefficient vector w stops, and the latest first weight coefficient vector w is determined to be the optimal weight coefficient vector. It should be noted that the convergence condition is that the weight coefficient vector after five consecutive iterations cannot obtain a smaller L(w), meaning that L(w) no longer decreases after five consecutive iterations, and the algorithm is considered to have converged. Finally, a preset second calculation operation is performed on each initial weight coefficient vector to obtain multiple optimal weight coefficient vectors, and these multiple optimal weight coefficient vectors represent the load decomposition results for the transformer area.

[0109] The specific steps of calculating the first gradient of the first weight coefficient vector w and iteratively updating the first weight coefficient vector w based on the first gradient include:

[0110] The first gradient of the first weight coefficient vector w is calculated according to a preset gradient calculation formula; the gradient calculation formula is as follows:

[0111]

[0112] Wherein, ΔL(w) is the first gradient obtained by differentiating the reference root mean square error value with respect to the first weight coefficient vector w; x is the gradient value corresponding to the j-th weight coefficient value in the first weight coefficient vector w; ij For the j-th load data in the typical load curve of the multiple classification groups on day i;

[0113] The first weight coefficient vector w is iteratively updated according to a preset weight coefficient update formula; the weight coefficient update formula is as follows:

[0114]

[0115] Where, ω j ε is the j-th weight coefficient value in the first weight coefficient vector w; ε is the step size for iterative updates.

[0116] It should be noted that ε is the step size of the iterative update, meaning the learning rate ε can be 0.001. This learning rate ε is a parameter that controls the step size during the iterative update process. It can be used to adjust the size of each update, ensuring that the parameters are not updated too large during the update process, thus avoiding missing the optimal solution. Furthermore, iterative convergence can be achieved using the gradient descent optimization algorithm, or other optimization algorithms such as least squares, Newton's method, or maximum likelihood estimation can be used; no specific limitations are specified here.

[0117] As can be seen, the above method allows for user grouping based on electricity consumption information within a transformer substation. Representative users are then selected from each substation group to collect their electricity consumption behavior data, i.e., load curve data, effectively reducing data collection costs. Analyzing the load curve data using clustering algorithms yields typical load curves for each substation group. These typical load curves provide a more comprehensive and accurate description of the load characteristics of the users in that substation, improving the reliability and accuracy of load decomposition. Randomly generating weight coefficient vectors within the optimization interval allows for faster and more accurate identification of the optimal weight coefficients, while also reducing the cost of iterative convergence. Iteratively adjusting the weight coefficient vectors using gradient descent helps minimize the error between the predicted and actual load curves, improving the accuracy and reliability of load decomposition.

[0118] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0120] When dividing each function into modules according to its corresponding function. Figure 4 This application provides a functional module block diagram of a user-group-based transformer area load splitting device 400, comprising:

[0121] The acquisition module 410 is used to acquire the electricity consumption record information of all users in the target transformer area, and obtain multiple electricity consumption record information; the multiple electricity consumption record information is used to characterize the transformer area load of the target transformer area;

[0122] The classification module 420 is used to classify all users in the target transformer area according to the multiple electricity consumption records to obtain multiple classification groups; the classification groups include any one of the following: residential life, charging service, public service, and shop operation;

[0123] The first calculation module 430 is used to perform a preset first calculation operation for each of the multiple classification groups to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient.

[0124] The determination module 440 is used to determine the optimization interval corresponding to each of the multiple contribution weight coefficients according to the preset numerical fluctuation ratio, so as to obtain multiple optimization intervals;

[0125] The generation module 450 is used to randomly generate a weight coefficient vector according to each of the plurality of optimization intervals to obtain a plurality of initial weight coefficient vectors; the initial weight coefficient vectors correspond one-to-one with the optimization intervals.

[0126] The second calculation module 460 is used to perform a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors.

[0127] Optionally, in performing a preset first calculation operation for each of the plurality of classification groups to obtain multiple contribution weight coefficients, the first calculation module 430 is specifically used for:

[0128] Select p typical users from the first classification group, and collect load data of the p typical users according to the preset collection strategy to obtain a load dataset; p is a positive integer; the first classification group is any one of the multiple classification groups;

[0129] The load dataset is calculated according to a preset clustering algorithm to obtain a first typical load curve; the horizontal axis of the first typical load curve is time, and the vertical axis is load data.

[0130] The contribution weight coefficient of the first classification group is determined based on the first typical load curve.

[0131] Optionally, regarding the step of selecting p typical users from the first classification group and collecting load data from the p typical users according to a preset collection strategy to obtain a load dataset, the first calculation module 430 is further specifically used for:

[0132] Obtain the daily frozen electricity consumption for each user in the first category group to obtain multiple first-day frozen electricity consumption figures;

[0133] Based on the multiple first-day frozen electricity amounts, the users in the first category group are sorted from largest to smallest according to the amount of frozen electricity amount, resulting in a first user sorting list;

[0134] The daily frozen electricity of the first p-1 users and the first p users in the first user sorting list is summed to obtain the frozen electricity of the second day and the frozen electricity of the third day.

[0135] Half of the total daily frozen electricity volume of the first category group is determined as the reference electricity volume threshold;

[0136] If the frozen electricity on the second day is less than the reference electricity threshold, and the frozen electricity on the third day is greater than or equal to the reference electricity threshold, then the p users are selected as the p typical users;

[0137] The load dataset is obtained by collecting data from the p typical users according to the preset collection frequency and collection duration.

[0138] Optionally, in the load dataset comprising p load data subsets; regarding the step of calculating the load dataset according to a preset clustering algorithm to obtain a first typical load curve, the first calculation module 430 is further specifically used for:

[0139] A1. Determine p load curves based on the p load data sets;

[0140] A2. Randomly select k load curves from the p load curves, and use the k load curves as the k first center points of k clusters respectively; k is a positive integer;

[0141] A3. Calculate the distance between each of the p load curves and the k first center points, and assign it to the cluster corresponding to the nearest first center point;

[0142] A4. After the p load curves are evenly distributed, the average value of all load curves in each of the k clusters is taken to obtain k second center points; the k second center points correspond one-to-one with the k clusters.

[0143] A5. Repeat steps A3 and A4 until the center point of each of the k clusters no longer changes, then proceed to step A6.

[0144] A6. Determine the center point of the cluster with the most load curves among the k clusters as the first typical load curve.

[0145] Optionally, in determining the contribution weight coefficient of the first classification group based on the first typical load curve, the first calculation module 430 is further specifically used for:

[0146] The contribution weight coefficient is obtained by calculating the first typical load curve according to the preset first calculation formula; the first typical load curve is [α1, α2, α3, ..., α n ];

[0147] The first calculation formula is as follows:

[0148]

[0149] Where, d α The total daily frozen electricity for the first category group; ω α The contribution weight coefficient for the first classification group; α n The load data is collected at the nth time point in the first typical load curve; n is an integer greater than 1, and c is a positive integer.

[0150] Optionally, in performing a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors, the second calculation module 460 is specifically used for:

[0151] B1. Calculate the first weight coefficient vector w according to the preset second calculation formula to obtain the reference root mean square error value; the first weight coefficient vector w is any one of the plurality of initial weight coefficient vectors; the first weight coefficient vector w is [ω1, ω2, ω3, ..., ω n ];

[0152] The second calculation formula is as follows:

[0153]

[0154] Where L(w) is the reference root mean square error value; h(x) i The reference transformer load curve is obtained by weighted summation based on the weighting coefficient vector and the typical load curve; x i The typical load curves for the multiple taxonomic groups on day i; y i The load curve of the transformer substation on the i-th day is the actual data collected; m is the total number of days in the sample; i is a positive integer;

[0155] B2. Calculate the first gradient of the first weight coefficient vector w, and iteratively update the first weight coefficient vector w based on the first gradient;

[0156] B3. Repeat step B2 until L(w) no longer decreases after 5 consecutive iterations. Then stop updating the first weight coefficient vector w and obtain the optimal weight coefficient vector.

[0157] Optionally, in calculating the first gradient of the first weight coefficient vector w and iteratively updating the first weight coefficient vector w based on the first gradient, the second calculation module 460 is further specifically configured to:

[0158] The first gradient of the first weight coefficient vector w is calculated according to a preset gradient calculation formula; the gradient calculation formula is as follows:

[0159]

[0160] Wherein, ΔL(w) is the first gradient obtained by differentiating the reference root mean square error value with respect to the first weight coefficient vector w; x is the gradient value corresponding to the j-th weight coefficient value in the first weight coefficient vector w; ij For the j-th load data in the typical load curve of the multiple classification groups on day i;

[0161] The first weight coefficient vector w is iteratively updated according to a preset weight coefficient update formula; the weight coefficient update formula is as follows:

[0162]

[0163] Where, ω j ε is the j-th weight coefficient value in the first weight coefficient vector w; ε is the step size for iterative updates.

[0164] It is evident that segmenting users based on their electricity consumption information and optimizing weighting coefficients based on electricity behavior data can improve the reliability and accuracy of load decomposition results for distribution areas.

[0165] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The user grouping-based area load decomposition device 400 can be used to execute the above method embodiments of this application, and will not be described again here.

[0166] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0167] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0168] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0169] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0170] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0171] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0172] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0173] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on a processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented using a software program that runs on a processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0174] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for load decomposition of distribution areas based on user grouping, characterized in that, include: Obtain electricity consumption records for all users in the target transformer area, resulting in multiple electricity consumption records. The multiple electricity consumption records are used to characterize the load of the target transformer area; Based on the multiple electricity consumption records, all users in the target transformer area are classified into multiple category groups; the category groups include any one of the following: residential life, charging service, public service, and commercial operation; For each of the multiple classification groups, a preset first calculation operation is performed to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient. The optimization interval corresponding to each of the multiple contribution weight coefficients is determined according to the preset numerical fluctuation ratio, thus obtaining multiple optimization intervals; Multiple initial weight coefficient vectors are obtained by randomly generating a weight coefficient vector for each of the multiple optimization intervals; each initial weight coefficient vector corresponds one-to-one with an optimization interval. For each of the plurality of initial weight coefficient vectors, a preset second calculation operation is performed to obtain a plurality of optimal weight coefficient vectors; Specifically, the step of performing a preset first calculation operation on each of the plurality of classification groups to obtain multiple contribution weight coefficients includes: Select p typical users from the first classification group, and collect load data of the p typical users according to the preset collection strategy to obtain the load dataset; p is a positive integer; the first classification group is any one of the multiple classification groups; The load dataset is calculated according to a preset clustering algorithm to obtain a first typical load curve; the horizontal axis of the first typical load curve is time, and the vertical axis is load data. The contribution weight coefficient of the first classification group is determined based on the first typical load curve; The step of selecting p typical users from the first classification group and collecting load data from the p typical users according to a preset collection strategy to obtain a load dataset includes: Obtain the daily frozen electricity consumption for each user in the first category group to obtain multiple first-day frozen electricity consumption figures; Based on the multiple first-day frozen electricity amounts, the users in the first category group are sorted from largest to smallest according to the amount of daily frozen electricity, resulting in a first user sorting list; The daily frozen electricity of the first p-1 users and the first p users in the first user sorting list is summed to obtain the frozen electricity of the second day and the frozen electricity of the third day. Half of the total daily frozen electricity volume of the first category group is determined as the reference electricity volume threshold; If the frozen electricity on the second day is less than the reference electricity threshold, and the frozen electricity on the third day is greater than or equal to the reference electricity threshold, then the p users are selected as the p typical users; The load dataset is obtained by collecting data from the p typical users according to the preset collection frequency and collection duration. The step of performing a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors includes: B1. Calculate the first weight coefficient vector w according to the preset second calculation formula to obtain the reference root mean square error value; the first weight coefficient vector w is any one of the plurality of initial weight coefficient vectors; the first weight coefficient vector w is... ; The second calculation formula is as follows: in, The reference root mean square error value; The reference transformer load curve is obtained by weighted summation based on the weighting coefficient vector and the typical load curve. The typical load curves for the multiple classification groups on day i; The actual load curve of the transformer substation on day i is collected. Let i be the total number of days in the sample; i is a positive integer; B2. Calculate the first gradient of the first weight coefficient vector w, and iteratively update the first weight coefficient vector w based on the first gradient; B3. Repeat step B2 until the result of 5 consecutive iterations is updated. If none of the weights decrease, then stop updating the first weight coefficient vector w and obtain the optimal weight coefficient vector.

2. The method as described in claim 1, characterized in that, The load dataset includes p load data subsets; the step of calculating the first typical load curve based on the load dataset using a preset clustering algorithm includes: A1. Determine p load curves based on the p load data sets; A2. Randomly select k load curves from the p load curves, and use the k load curves as the k first center points of k clusters respectively; k is a positive integer; A3. Calculate the distance between each of the p load curves and the k first center points, and assign it to the cluster corresponding to the nearest first center point; A4. After the p load curves are evenly distributed, the average value of all load curves in each of the k clusters is taken to obtain k second center points; the k second center points correspond one-to-one with the k clusters. A5. Repeat steps A3 and A4 until the center point of each of the k clusters no longer changes, then proceed to step A6. A6. Determine the center point of the cluster with the most load curves among the k clusters as the first typical load curve.

3. The method as described in claim 1, characterized in that, The step of determining the contribution weight coefficient of the first classification group based on the first typical load curve includes: The contribution weight coefficient is obtained by calculating the first typical load curve according to the preset first calculation formula; the first typical load curve is [ ]; The first calculation formula is as follows: in, This represents the total daily frozen electricity consumption for the first category group; The contribution weight coefficient for the first classification group; The load data is collected at the nth time point in the first typical load curve; n is an integer greater than 1, and c is a positive integer.

4. The method as described in claim 1, characterized in that, The step of calculating the first gradient of the first weight coefficient vector w and iteratively updating the first weight coefficient vector w based on the first gradient includes: The first gradient of the first weight coefficient vector w is calculated according to a preset gradient calculation formula; the gradient calculation formula is as follows: in, The reference root mean square error value is used to adjust the first weight coefficient vector. The first gradient obtained after differentiation; The gradient value corresponding to the j-th weight coefficient value in the first weight coefficient vector w; For the j-th load data in the typical load curve of the multiple classification groups on day i; The first weight coefficient vector w is iteratively updated according to a preset weight coefficient update formula; the weight coefficient update formula is as follows: in, This refers to the j-th weight coefficient value in the first weight coefficient vector w; This is the step size for iterative updates.

5. A user-group-based transformer area load decomposition device, used to perform the method as described in any one of claims 1-4, characterized in that, It includes an acquisition module, a classification module, a first calculation module, a determination module, a generation module, and a second calculation module, wherein: The acquisition module is used to acquire the electricity consumption records of all users in the target transformer area, resulting in multiple electricity consumption records; the multiple electricity consumption records are used to characterize the transformer load of the target transformer area. The classification module is used to classify all users in the target transformer area according to the multiple electricity consumption records to obtain multiple classification groups; the classification groups include any one of the following: residential life, charging service, public service, and commercial operation; The first calculation module is used to perform a preset first calculation operation for each of the multiple classification groups to obtain multiple contribution weight coefficients; each classification group corresponds to one contribution weight coefficient. The determining module is used to determine the optimization interval corresponding to each of the multiple contribution weight coefficients according to a preset numerical fluctuation ratio, thereby obtaining multiple optimization intervals. The generation module is used to randomly generate a weight coefficient vector according to each of the plurality of optimization intervals to obtain a plurality of initial weight coefficient vectors; the initial weight coefficient vectors correspond one-to-one with the optimization intervals. The second calculation module is used to perform a preset second calculation operation on each of the plurality of initial weight coefficient vectors to obtain a plurality of optimal weight coefficient vectors.

6. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-4.

Images