Virtual power plant flexible resource aggregation method based on deep clustering and electronic equipment
By using deep clustering methods to reconstruct and feature extraction of flexible resources in virtual power plants, the problem of poor aggregation effect of flexible resources in the prior art is solved, and more efficient resource utilization and regulation are achieved.
Patent Information
- Application Number
- CN202411893890.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-04-08
AI Technical Summary
In the prior art, the aggregation effect of the flexible resource aggregation method of virtual power plants is poor, and the uncertainty factors and potential of various resources cannot be fully considered, resulting in low resource utilization.
The deep clustering method is adopted to obtain flexible resource data in the virtual power plant, and data reconstruction is carried out based on information entropy. The spatial features are extracted using a deep self-encoder, and the spatial features are aggregated through the deep clustering algorithm to improve the aggregation effect of resources.
Through the application of deep clustering algorithm, flexible resources in virtual power plants can be more effectively aggregated, resource utilization rate can be improved, and resource regulation flexibility and efficiency can be enhanced.
Smart Images
Figure CN119784064A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of virtual power plants, and in particular to a flexible resource aggregation method and electronic equipment for virtual power plants based on deep clustering. Background Art
[0002] With the continuous development of new power systems and the gradual construction of the power market, the penetration rate of distributed resources in the power grid is getting higher and higher. Usually, the internal resources of virtual power plants are composed of a variety of flexible resources such as new energy units, energy storage, distributed power sources, flexible loads and electric vehicles.
[0003] At present, in the existing technology, the resource aggregation method of virtual power plants mainly considers the output characteristics of different types of resources and their complementary characteristics, such as the resource aggregation plan established with the goal of minimizing the power generation cost of virtual power plants and the optimization model with the goal of maximizing load response.
[0004] However, the aggregation effect of the flexible resource aggregation method in the prior art is relatively poor. Therefore, how to improve the aggregation effect of flexible resources has become a problem to be solved. Summary of the invention
[0005] The purpose of this application is to provide a flexible resource aggregation method for a virtual power plant based on deep clustering, which can solve the problem of poor aggregation effect of flexible resource aggregation methods in the prior art.
[0006] In a first aspect, an embodiment of the present application provides a method for aggregating flexible resources of a virtual power plant based on deep clustering, the method comprising: Obtain flexible resource data in virtual power plants; Reconstructing the flexible resource data based on information entropy to obtain reconstructed flexible resource data; Based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features; A deep clustering algorithm is used to aggregate spatial features to obtain flexible resource aggregation results.
[0007] In a possible implementation of the first aspect, the matrix of flexible resource data is expressed as follows:
[0008] in, represents the flexible resource data matrix, ~ Represents flexible resource data, N Indicates the number of flexible resource data. M Indicates the number of time series samples collected; The calculation formula of information entropy is as follows:
[0009]
[0010] in, Indicates n The flexible resource data is in m The data value collected at each moment, Indicates n Time series load data of flexible resource data, Represents the normalized n The flexible resource data is in m The data value collected at each moment, Indicates n The information entropy of flexible resource data, n and m Indicates ordinal number, Represents the base 10 logarithm.
[0011] In a possible implementation of the first aspect, reconstructing the flexible resource data based on information entropy includes: Based on information entropy, the reconstruction coefficient of flexible resource data is calculated. The specific calculation formula is as follows:
[0012] in, represents the reconstruction coefficient; The expression of the reconstructed flexible resource data is as follows:
[0013] in, Represents the reconstructed flexible resource dataset, ~ Indicates the 1st~ n The reconstruction coefficients, ~ Indicates the 1st~ n The time series load data of flexible resource data.
[0014] In a possible implementation of the first aspect, the deep autoencoder includes: an encoder and a decoder; based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features, including: Based on the encoder, the original flexible resource data is embedded in the low-dimensional space, and the features of the original flexible resource data are extracted to obtain the intermediate layer features. The specific expression is as follows:
[0015] in, represents the middle layer features, represents the activation function of the encoding process, represents the weight of the encoding layer, represents the flexible resource data matrix, represents the bias of the coding layer; Based on the decoder, the intermediate layer features are restored to obtain spatial features. The specific expression is as follows:
[0016] in, represents the spatial feature matrix, represents the activation function of the decoding process, represents the weight of the decoding layer, Represents the bias of the decoding layer.
[0017] In a possible implementation manner of the first aspect, the method further includes: Train the deep autoencoder based on the optimization objective function; Among them, the expression of the optimization objective function is as follows:
[0018] in, represents the optimization objective function, Indicates The value of the variable at its minimum.
[0019] In a possible implementation of the first aspect, the deep clustering algorithm includes a K-means algorithm; and the deep clustering algorithm is used to aggregate spatial features, including: The K-means algorithm is used to aggregate spatial features into K categories according to the dual-scale distance, and the flexible resource aggregation result is K-category flexible resource data.
[0020] In a possible implementation manner of the first aspect, the method further includes: The Euclidean distance between each flexible resource data is calculated according to the following calculation formula:
[0021] in, represents the Euclidean distance, Indicates ordinal number, Represents the characteristic dimension of flexible resource data, and Indicates Dimensional flexible resource data; The dynamic time warping distance between each flexible resource data is calculated according to the following calculation formula:
[0022] in, represents the dynamic time warping distance, Indicates taking the minimum value, and Indicates Dimensional flexible resource data; The dual-scale distance is calculated based on the Euclidean distance and the dynamic time warping distance. The specific calculation formula is as follows:
[0023] in, represents the dual-scale distance, represents the weight of the Euclidean distance, Represents the weight of the dynamic time warping distance.
[0024] In a possible implementation manner of the first aspect, the method further includes: The flexible resource aggregation results are evaluated based on the response time, response capacity and daily load fluctuation rate of various flexible resource data.
[0025] In a possible implementation of the first aspect, a calculation formula for the response time of each type of flexible resource data is as follows:
[0026] in, Indicates the response time of various flexible resource data. Indicates taking the maximum value, Indicates the response time of photovoltaic data, Indicates the response time of wind power data, Indicates the response time of the flexible load data, Indicates the response time of energy storage data; The calculation formula for the response capacity of various types of flexible resource data is as follows:
[0027] in, Indicates the response capacity of various types of flexible resource data, represents the response capacity of photovoltaic data, represents the response capacity of wind power data, Indicates the response capacity of the flexible load data, Indicates the response capacity of energy storage data; The calculation formula for daily load fluctuation rate of various flexible resource data is as follows:
[0028] in, Represents the daily load fluctuation rate of various flexible resource data, represents the mean, represents the daily load fluctuation rate of photovoltaic data, represents the daily load fluctuation rate of wind power data, represents the daily load fluctuation rate of the flexible load data, Represents the daily load fluctuation rate of energy storage data.
[0029] In a second aspect, an embodiment of the present application provides a virtual power plant flexible resource aggregation device based on deep clustering, the device comprising: An acquisition unit, used for acquiring flexible resource data in a virtual power plant; A reconstruction unit, used for reconstructing the flexible resource data based on information entropy to obtain reconstructed flexible resource data; A feature extraction unit, used for extracting features from the reconstructed flexible resource data based on the trained deep autoencoder to obtain spatial features; The aggregation unit is used to aggregate spatial features using a deep clustering algorithm to obtain flexible resource aggregation results.
[0030] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for flexible resource aggregation of a virtual power plant based on deep clustering according to any one of the above-mentioned first aspects is implemented.
[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the virtual power plant flexible resource aggregation method based on deep clustering according to any one of the above-mentioned first aspects.
[0032] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device executes the virtual power plant flexible resource aggregation method based on deep clustering according to any one of the above-mentioned first aspects.
[0033] The application scheme first obtains the flexible resource data in the virtual power plant, and then reconstructs the flexible resource data based on information entropy. Then, based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features. Finally, a deep clustering algorithm is used to aggregate the spatial features, which can improve the aggregation effect of flexible resources and has strong ease of use and practicality.
[0034] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0036] Figure 1 It is a schematic diagram of the steps of a virtual power plant flexible resource aggregation method based on deep clustering provided in an embodiment of the present application; Figure 2 is a schematic diagram of the deep autoencoder process provided by an embodiment of the present application; Figure 3 It is a structural schematic diagram of a virtual power plant flexible resource aggregation device based on deep clustering provided in an embodiment of the present application; Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0037] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0038] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or photovoltaic components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, photovoltaic components and / or combinations thereof.
[0039] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0040] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0041] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.
[0042] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0043] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0044] With the continuous development of new power systems and the gradual construction of the power market, the penetration rate of distributed resources in the power grid is getting higher and higher. Virtual power plants participate in the coordinated management of the power market and power grid operation as a special power plant through the aggregation and coordination of distributed power sources, controllable loads and energy storage units, and realize flexible allocation of resources. Usually, the internal resources of virtual power plants are composed of a variety of flexible resources such as new energy units, energy storage, distributed power sources, flexible loads and electric vehicles.
[0045] At present, in the existing technology, the resource aggregation method of the current virtual power plant mainly considers the output characteristics of different types of resources and their complementary characteristics to construct a resource aggregation method, such as a resource aggregation plan established with the goal of minimizing the power generation cost of the virtual power plant and an optimization model with the goal of maximizing the load response. This method has fewer types of resource aggregation, the constructed indicators are relatively simple, and less consideration is given to the uncertainty in the operation of the internal resource system.
[0046] Virtual power plants contain a large number of distributed power generation resources, electric vehicle resources, energy storage resources and controllable load resources. The operating characteristics of these resources are different and have certain uncertainties and randomness. The current methods cannot fully consider the uncertainties of various resources, and have not fully tapped the potential of various resources to improve resource utilization.
[0047] The current virtual power plant resource aggregation method usually focuses on the single optimization goal of power generation cost, and lacks consideration of the complementary characteristics of source-load-storage in internal resources. Therefore, in the virtual power plant resource aggregation, it is necessary to give full play to the advantages of the output characteristics of various resources and aggregate them into a resource entity with good output characteristics and convenient and flexible regulation.
[0048] Commonly used traditional clustering algorithms are simple, efficient and flexible, but they are sensitive to noise and outliers, have high computational complexity, are prone to local optimality, and are not suitable for large-scale data sets. Due to the wide variety of resources, different characteristics, and uneven distribution in virtual power plants, traditional clustering algorithms cannot effectively mine the output characteristics of various resources and achieve complementary advantages of resources.
[0049] The aggregation effect of the flexible resource aggregation method in the prior art is relatively poor. Therefore, how to improve the aggregation effect of flexible resources has become a problem to be solved.
[0050] In response to the above-mentioned defects, an embodiment of the present application provides a method for aggregating flexible resources of a virtual power plant based on deep clustering. First, the flexible resource data in the virtual power plant is acquired. Secondly, the flexible resource data is reconstructed based on information entropy. Then, feature extraction is performed on the reconstructed flexible resource data based on the trained deep autoencoder to obtain spatial features. Finally, a deep clustering algorithm is used to aggregate the spatial features, which can improve the aggregation effect of flexible resources and has strong ease of use and practicality.
[0051] The specific process implemented by this application is introduced below through specific embodiments.
[0052] See also Figure 1 , Figure 1 Schematic diagram of the steps of the virtual power plant flexible resource aggregation method based on deep clustering provided in the embodiment of the present application. Figure 1 As shown, the method may include the following steps: S101, obtaining flexible resource data in the virtual power plant.
[0053] In one embodiment, the flexible resource data set of the virtual power plant is obtained in combination with the cyber-physical network, including data on photovoltaics, wind power, flexible loads, and energy storage.
[0054] S102, reconstructing the flexible resource data based on information entropy to obtain reconstructed flexible resource data.
[0055] It should be noted that in a virtual power plant, various resources have different characteristics and distributions. Using conventional normalization methods to standardize data will destroy the differences between the original data forms. In one embodiment, the complexity of data is measured by information entropy. The larger the entropy value, the more complex the data.
[0056] S103, based on the trained deep autoencoder, extract features from the reconstructed flexible resource data to obtain spatial features.
[0057] S104, using a deep clustering algorithm to aggregate spatial features to obtain flexible resource aggregation results.
[0058] According to an implementation manner of the present application, the matrix expression of the flexible resource data is as follows:
[0059] in, represents the flexible resource data matrix, ~ Represents flexible resource data, N Indicates the number of flexible resource data. M Indicates the number of time series samples collected; The calculation formula of information entropy is as follows:
[0060]
[0061] in, Indicates n The flexible resource data is in m The data value collected at each moment, Indicates n Time series load data of flexible resource data, Represents the normalized n The flexible resource data is in m The data value collected at each moment, Indicates n The information entropy of flexible resource data, n and m Indicates ordinal number, Represents the base 10 logarithm.
[0062] According to an implementation of the present application, data reconstruction of flexible resource data based on information entropy includes: Based on information entropy, the reconstruction coefficient of flexible resource data is calculated. The specific calculation formula is as follows:
[0063] in, represents the reconstruction coefficient; The expression of the reconstructed flexible resource data is as follows:
[0064] in, Represents the reconstructed flexible resource dataset, ~ Indicates the 1st~ n The reconstruction coefficients, ~ Indicates the 1st~ n The time series load data of flexible resource data.
[0065] In some embodiments, the greater the information entropy, the more complex the flexible resource sequence is, the greater the reconstruction coefficient allocated, and the more original data features are retained. Reconstructing the flexible resource data based on the reconstruction coefficient obtained by the information entropy can highlight the timing characteristics of the flexible resource while ensuring that the original information is not lost.
[0066] See also Figure 2 , Figure 2 Schematic diagram of the deep autoencoder process provided by the embodiment of the present application. According to one embodiment of the present application, the deep autoencoder includes: an encoder and a decoder; based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features, including: Based on the encoder, the original flexible resource data is embedded in the low-dimensional space, and the features of the original flexible resource data are extracted to obtain the intermediate layer features. The specific expression is as follows:
[0067] in, represents the middle layer features, represents the activation function of the encoding process, represents the weight of the encoding layer, represents the flexible resource data matrix, represents the bias of the coding layer; Based on the decoder, the intermediate layer features are restored to obtain spatial features. The specific expression is as follows:
[0068] in, represents the spatial feature matrix, represents the activation function of the decoding process, represents the weight of the decoding layer, Represents the bias of the decoding layer.
[0069] In some embodiments, since the dimension of the flexible resource data is large and contains noise, a deep autoencoder is used to extract effective features from complex data. The deep autoencoder includes: an encoder and a decoder. The encoder embeds the original data into a low-dimensional space, extracts important features of the original data, and realizes low-dimensional expression. The decoder restores the features of the low-dimensional space to realize the reconstruction of the original data.
[0070] According to one embodiment of the present application, the method further includes: Train the deep autoencoder based on the optimization objective function; Among them, the expression of the optimization objective function is as follows:
[0071] in, represents the optimization objective function, Indicates The value of the variable at its minimum.
[0072] In one embodiment, the deep autoencoder is trained by optimizing the objective function to minimize the error between the input flexible resource data and the output reconstructed data.
[0073] According to an implementation of the present application, the deep clustering algorithm includes a K-means algorithm; the deep clustering algorithm is used to aggregate spatial features, including: The K-means algorithm is used to aggregate spatial features into K categories according to the dual-scale distance, and the flexible resource aggregation result is K-category flexible resource data.
[0074] In some embodiments, a dual-scale distance based on Euclidean distance and Dynamic Time Warping (DTW) distance is used to measure the similarity between flexible resource features and is used as input data for a clustering algorithm. A K-means algorithm is used to aggregate the flexible resource data into K categories.
[0075] According to one embodiment of the present application, the method further includes: The Euclidean distance between each flexible resource data (such as flexible resource data A and B) is calculated according to the following calculation formula:
[0076] in, represents the Euclidean distance, Indicates ordinal number, Represents the characteristic dimension of flexible resource data, and Indicates Dimensional flexible resource data; The dynamic time warping distance between each flexible resource data is calculated according to the following calculation formula:
[0077] in, represents the dynamic time warping distance, Indicates taking the minimum value, and Indicates Dimensional flexible resource data; The dual-scale distance is calculated based on the Euclidean distance and the dynamic time warping distance. The specific calculation formula is as follows:
[0078] in, represents the dual-scale distance, represents the weight of the Euclidean distance, represents the weight of the dynamic time warping distance. In one embodiment, .
[0079] According to one embodiment of the present application, the method further includes: The flexible resource aggregation results are evaluated based on the response time, response capacity and daily load fluctuation rate of various flexible resource data.
[0080] In some embodiments, after obtaining various clusters of flexible resources aggregated from virtual power plants, the aggregation results of various flexible resource data are evaluated by response time, response capacity, and daily load fluctuation rate, and the grid operation and electricity market participation plans are further determined based on various indicators.
[0081] According to an implementation of the present application, the calculation formula for the response time of various types of flexible resource data is as follows:
[0082] in, Indicates the response time of various flexible resource data. Indicates taking the maximum value, Indicates the response time of photovoltaic data, Indicates the response time of wind power data, Indicates the response time of the flexible load data, Indicates the response time of energy storage data; The calculation formula for the response capacity of various types of flexible resource data is as follows:
[0083] in, Indicates the response capacity of various types of flexible resource data, represents the response capacity of photovoltaic data, represents the response capacity of wind power data, Indicates the response capacity of the flexible load data, Indicates the response capacity of energy storage data; The calculation formula for daily load fluctuation rate of various flexible resource data is as follows:
[0084] in, Represents the daily load fluctuation rate of various flexible resource data, represents the mean, represents the daily load fluctuation rate of photovoltaic data, represents the daily load fluctuation rate of wind power data, represents the daily load fluctuation rate of the flexible load data, Represents the daily load fluctuation rate of energy storage data.
[0085] The virtual power plant flexible resource aggregation method based on deep clustering provided in the embodiment of the present application first obtains the flexible resource data in the virtual power plant, then reconstructs the flexible resource data based on information entropy, and then extracts features of the reconstructed flexible resource data based on the trained deep autoencoder to obtain spatial features. Finally, a deep clustering algorithm is used to aggregate the spatial features, which can improve the aggregation effect of flexible resources and has strong ease of use and practicality.
[0086] This application scheme adopts a deep clustering algorithm to analyze and consider the uncertainty of internal resources and the output characteristics of various resources to realize an optimized aggregation model of multiple resources in a virtual power plant. This method is scientific, reasonable and has engineering application value.
[0087] This application scheme introduces deep learning into the clustering algorithm to solve the problems of data dimensionality reduction and feature representation of large-scale data sets, uses deep learning to mine the representation information between various resources, and realizes the effective aggregation of various resources in the virtual power plant.
[0088] Since there are many types of resources in virtual power plants and their distribution is uneven, it is difficult to achieve ideal resource aggregation effects by directly using traditional clustering algorithms. This application scheme reduces the dimension and extracts features of various flexible resources by reconstructing data based on information entropy and building a deep autoencoder model, thereby improving the accuracy and efficiency of virtual power plant resource aggregation.
[0089] Distance measurement methods play a very important role in clustering algorithms. This application scheme uses a dual-scale distance measurement method to calculate the similarity of various flexible resources. Compared with Euclidean distance, dynamic time warping distance can overcome the impact of data deformation and improve the quality of clustering results.
[0090] The response time, response capacity and daily load fluctuation rate are used to evaluate the aggregation results of various flexible resource data and characterize the response characteristics of the aggregated resources, which is conducive to the optimization and decision-making of virtual power plant resources participating in the power market.
[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0092] Corresponding to the method of the above embodiment, Figure 3 1 is a schematic diagram of the structure of a flexible resource aggregation device for a virtual power plant based on deep clustering provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown.
[0093] Reference Figure 3 , the device comprises: An acquisition unit 301 is used to acquire flexible resource data in a virtual power plant; A reconstruction unit 302, configured to reconstruct the flexible resource data based on information entropy to obtain reconstructed flexible resource data; A feature extraction unit 303 is used to extract features from the reconstructed flexible resource data based on the trained deep autoencoder to obtain spatial features; The aggregation unit 304 is used to aggregate the spatial features using a deep clustering algorithm to obtain a flexible resource aggregation result.
[0094] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0095] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0096] Figure 4 Schematic diagram of the structure of the electronic device 4 provided in the embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: at least one processor 401 ( Figure 4 Only one is shown in the figure), a memory 403, and a computer program 402 stored in the memory 403 and executable on at least one processor 401, wherein the processor 401 implements the steps in the above method embodiment when executing the computer program 402.
[0097] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a mobile phone. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 403. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation on the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.
[0098] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware photovoltaic modules, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0099] In some embodiments, the memory 403 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. In other embodiments, the memory 403 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital card (SecureDigital, SD), a flash card (Flash Card), etc. equipped on the electronic device 4. Further, the memory 403 may also include both an internal storage unit of the electronic device 4 and an external storage device. The memory 403 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as program codes of a computer program, etc. The memory 403 may also be used to temporarily store data that has been output or is to be output.
[0100] 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, when the present application implements all or part of the processes in the above-mentioned embodiment method, it can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps applied to the above-mentioned method embodiment. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may at least include: any entity or device that can carry the computer program code to the computing device / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, such as USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electric carrier signals and telecommunication signals.
[0101] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0102] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps in the above-mentioned method embodiments.
[0103] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0104] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0105] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. The device / electronic device embodiments described above are merely schematic, and the division of the above modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or photovoltaic components can be combined or integrated into another system, and some features can be ignored and not executed. Another point is that the indirect coupling, direct coupling or communication connection between each other shown or discussed can be an indirect coupling, direct coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0106] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0107] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A virtual power plant flexible resource aggregation method based on deep clustering, characterized in that: The method comprises: Obtain flexible resource data in virtual power plants; Reconstructing the flexible resource data based on information entropy to obtain reconstructed flexible resource data; Based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features; A deep clustering algorithm is used to aggregate the spatial features to obtain flexible resource aggregation results.
2. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 1 is characterized in that: The matrix expression of the flexible resource data is as follows: in, represents the flexible resource data matrix, ~ Represents flexible resource data, N Indicates the number of flexible resource data. M Indicates the number of time series samples collected; The calculation formula of the information entropy is as follows: in, Indicates n The flexible resource data is in m The data value collected at each moment, Indicates n Time series load data of flexible resource data, Represents the normalized n The flexible resource data is in m The data value collected at each moment, Indicates n The information entropy of flexible resource data, n and m Indicates ordinal number, Represents the base 10 logarithm.
3. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 2 is characterized in that: Reconstructing the flexible resource data based on information entropy includes: Based on the information entropy, the reconstruction coefficient of the flexible resource data is calculated. The specific calculation formula is as follows: in, represents the reconstruction coefficient; The expression of the reconstructed flexible resource data is as follows: in, Represents the reconstructed flexible resource dataset, ~ Indicates the 1st~ n The reconstruction coefficients, ~ Indicates the 1st~ n The time series load data of flexible resource data.
4. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 1 is characterized in that: The deep autoencoder includes: an encoder and a decoder; based on the trained deep autoencoder, feature extraction is performed on the reconstructed flexible resource data to obtain spatial features, including: Based on the encoder, the original flexible resource data is embedded in the low-dimensional space, and the feature extraction is performed on the original flexible resource data to obtain the intermediate layer feature. The specific expression is as follows: in, represents the middle layer features, represents the activation function of the encoding process, represents the weight of the encoding layer, represents the flexible resource data matrix, represents the bias of the coding layer; The intermediate layer features are restored based on the decoder to obtain the spatial features. The specific expression is as follows: in, represents the spatial feature matrix, represents the activation function of the decoding process, represents the weight of the decoding layer, Represents the bias of the decoding layer.
5. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 1 is characterized in that: The method further comprises: Training the deep autoencoder based on an optimization objective function; The expression of the optimization objective function is as follows: in, represents the optimization objective function, Indicates The value of the variable at its minimum.
6. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 1, characterized in that: The deep clustering algorithm includes a K-means algorithm; the deep clustering algorithm is used to aggregate the spatial features, including: The K-means algorithm is used to aggregate the spatial features into K categories according to the dual-scale distance, and the flexible resource aggregation result is K-category flexible resource data.
7. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 6 is characterized in that: The method further comprises: The Euclidean distance between each flexible resource data is calculated according to the following calculation formula: in, represents the Euclidean distance, Indicates ordinal number, Represents the characteristic dimension of flexible resource data, and Indicates Dimensional flexible resource data; The dynamic time warping distance between each flexible resource data is calculated according to the following calculation formula: in, represents the dynamic time warping distance, Indicates taking the minimum value, and Indicates Dimensional flexible resource data; The dual-scale distance is calculated according to the Euclidean distance and the dynamic time warping distance. The specific calculation formula is as follows: in, represents the dual-scale distance, represents the weight of the Euclidean distance, Represents the weight of the dynamic time warping distance.
8. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 6 is characterized in that: The method further comprises: The flexible resource aggregation result is evaluated according to the response time, response capacity and daily load fluctuation rate of various flexible resource data.
9. The method for flexible resource aggregation of virtual power plants based on deep clustering according to claim 8, characterized in that: The calculation formula for the response time of various flexible resource data is as follows: in, Indicates the response time of various flexible resource data. Indicates taking the maximum value, Indicates the response time of photovoltaic data, Indicates the response time of wind power data, Indicates the response time of the flexible load data, Indicates the response time of energy storage data; The calculation formula for the response capacity of various types of flexible resource data is as follows: in, Indicates the response capacity of various types of flexible resource data, represents the response capacity of photovoltaic data, represents the response capacity of wind power data, Indicates the response capacity of the flexible load data, Indicates the response capacity of energy storage data; The calculation formula for daily load fluctuation rate of various flexible resource data is as follows: in, Represents the daily load fluctuation rate of various flexible resource data, represents the mean, represents the daily load fluctuation rate of photovoltaic data, represents the daily load fluctuation rate of wind power data, represents the daily load fluctuation rate of the flexible load data, Represents the daily load fluctuation rate of energy storage data.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the virtual power plant flexible resource aggregation method based on deep clustering described in any one of claims 1-9.
11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the virtual power plant flexible resource aggregation method based on deep clustering as described in any one of claims 1-9.