Data searching method and device for multi-energy complementary new energy digital power plant

Abstract

The application relates to the technical field of data management, and discloses a data searching method and device for a multi-energy complementary novel energy digital power station. First, a first physical quantity and a second physical quantity possibly having relevance are determined through clustering operation, and then whether the first physical quantity and the second physical quantity indeed have relevance is verified by using a logistic regression algorithm. If yes, a mapping relationship between the physical quantities can be constructed according to first to-be-processed data and second to-be-processed data. The physical quantities to which the to-be-searched data belong are divided into two sets, because there is relevance between part of the physical quantities, and one can be found by one, the application first searches for first to-be-searched data respectively corresponding to each physical quantity in the first set, and then the second to-be-searched data can be determined according to the first to-be-searched data and the mapping relationship. Compared with the previous data searching realized by sequentially traversing, the above-mentioned method is adopted to reduce the data searching amount, and the data searching efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data management, and particularly relates to a data searching method and device for a multi-energy complementary new energy digital power station. BACKGROUND

[0002] With the development of new energy power stations, the phenomenon of single new energy frequency and unstable load is gradually highlighted, and multi-energy complementary new energy power stations are developed. Since the data of large multi-energy complementary new energy power stations are huge and disordered, when searching for data, all data need to be read and identified to find the required data, which makes searching difficult and reduces searching efficiency.

[0003] Therefore, an efficient data searching method becomes inevitable to improve efficiency. SUMMARY

[0004] Therefore, the present application provides a data searching method and device for a multi-energy complementary new energy digital power station to solve the problem of current data searching difficulty.

[0005] In a first aspect, the present application provides a data searching method for a multi-energy complementary new energy digital power station, which comprises the following steps:

[0006] The pre-acquired to-be-processed data are clustered to obtain a clustering cluster, the clustering cluster including a first physical quantity to which the first to-be-processed data belong and a second physical quantity to which the second to-be-processed data belong, the to-be-processed data including the first to-be-processed data and the second to-be-processed data; when it is verified by a logistic regression algorithm that there is a correlation between the first physical quantity and the second physical quantity, a mapping relationship between the first physical quantity and the second physical quantity is determined based on the first to-be-processed data and the second to-be-processed data; when it is determined according to a searching instruction that the physical quantity to which the to-be-searched data belong includes multiple physical quantities and the multiple physical quantities include physical quantities having a correlation, the physical quantity to which the to-be-searched data belong is divided into a first set and a second set, the number of physical quantities in the first set is greater than or equal to the number of physical quantities in the second set, and the first set includes physical quantities having a correlation with any physical quantity in the second set; first to-be-searched data respectively corresponding to each physical quantity in the first set are searched; second to-be-searched data are determined based on the first to-be-searched data and the mapping relationship, the to-be-searched data including the first to-be-searched data and the second to-be-searched data.

[0007] The data searching method of the multi-energy complementary new energy digital power station provided by the embodiment firstly determines the first physical quantity and the second physical quantity that may have relevance through clustering operation, and then verifies whether the first physical quantity and the second physical quantity indeed have relevance through a logistic regression algorithm. If there is relevance, a mapping relationship between the first physical quantity and the second physical quantity can be constructed according to first to-be-processed data corresponding to the first physical quantity and second to-be-processed data corresponding to the second physical quantity. When a data searching instruction is received, if it is determined according to the data searching instruction that the physical quantity to which the to-be-searched data belongs includes multiple physical quantities and the multiple physical quantities include the physical quantity having relevance, the physical quantity to which the to-be-searched data belongs is divided into a first set and a second set. The reason for dividing the physical quantity into two sets is that there is relevance between part of the physical quantities, that is, one-to-one, therefore, the embodiment only needs to firstly search for the first to-be-searched data corresponding to each physical quantity in the first set, and then determines the second to-be-searched data according to the first to-be-searched data and the mapping relationship. Compared with the previous way of searching data by sequentially traversing, the embodiment reduces the amount of data searching by using the above way, and improves the efficiency of data searching.

[0008] In an optional implementation, before clustering the pre-acquired to-be-processed data to obtain the clustering cluster, the method further includes:

[0009] acquiring a target label; and acquiring the to-be-processed data carrying the target label from a preset storage location.

[0010] In an optional implementation, before acquiring the target label, the method further includes:

[0011] acquiring to-be-stored data, the to-be-stored data including data in the digital power station; determining a category to which the to-be-stored data belongs as a label corresponding to the to-be-stored data according to a preset data division criterion; and storing the to-be-stored data carrying the label to a preset storage location.

[0012] In an optional implementation, the preset data division criterion includes:

[0013] a first criterion of dividing according to data types, a second criterion of dividing according to data dimensions, and a third criterion of dividing according to data weights and dynamic and static attributes.

[0014] In an optional implementation, storing the to-be-stored data carrying the label to the preset storage location includes:

[0015] storing the to-be-stored data carrying the label to the preset storage location in an array manner.

[0016] In an optional implementation, clustering the pre-acquired to-be-processed data to obtain the clustering cluster includes:

[0017] determining membership of the to-be-processed data to each cluster center, determining distance between the to-be-processed data and the cluster center based on the to-be-processed data, the membership and the cluster center, and determining a cluster corresponding to each cluster center based on the distance.

[0018] In an alternative embodiment, the distance between the to-be-processed data and the cluster center is determined based on the to-be-processed data, the membership and the cluster center by the following way:

[0019]

[0020] wherein J represents distance between the ith to-be-processed data x i and the jth cluster center C j , M represents total number of to-be-processed data, C represents total number of cluster centers, u ij represents membership of the ith to-be-processed data x i to the jth cluster center C j , and a represents a hyperparameter.

[0021] In a first aspect, the present application provides a data searching device of a multi-energy complementary novel energy digital power station, which comprises:

[0022] a clustering module configured to cluster pre-acquired to-be-processed data to obtain a cluster, the cluster comprising a first physical quantity to which the first to-be-processed data belongs and a second physical quantity to which the second to-be-processed data belongs, the to-be-processed data comprising the first to-be-processed data and the second to-be-processed data; a first determining module configured to determine a mapping relationship between the first physical quantity and the second physical quantity based on the first to-be-processed data and the second to-be-processed data when it is verified by a logistic regression algorithm that there is a correlation between the first physical quantity and the second physical quantity; a dividing module configured to divide the physical quantity to which the to-be-searched data belongs into a first set and a second set when it is determined according to a searching instruction that the physical quantity to which the to-be-searched data belongs comprises a plurality of physical quantities and the plurality of physical quantities contain physical quantities having a correlation, the number of physical quantities in the first set being greater than or equal to the number of physical quantities in the second set, and the first set comprising physical quantities having a correlation with any physical quantity in the second set; a searching module configured to search for first to-be-searched data corresponding to each physical quantity in the first set; and a second determining module configured to determine second to-be-searched data based on the first to-be-searched data and the mapping relationship, the to-be-searched data comprising the first to-be-searched data and the second to-be-searched data.

[0023] In an alternative embodiment, the device further comprises, before the clustering module:

[0024] a first acquiring module configured to acquire a target label, and a second acquiring module configured to acquire to-be-processed data carrying the target label from a preset storage location.

[0025] In an optional implementation, before the first obtaining module, the apparatus further comprises:

[0026] a third obtaining module, configured to obtain to-be-stored data, the to-be-stored data comprising data in a digital power station; a third determining module, configured to determine a category to which the to-be-stored data belongs as a label corresponding to the to-be-stored data according to a preset data division criterion; and a storage module, configured to store the to-be-stored data carrying the label to a preset storage location.

[0027] In an optional implementation, the preset data division criterion in the third determining module comprises:

[0028] a first criterion for division according to data types, a second criterion for division according to data dimensions, and a third criterion for division according to data weights and dynamic / static attributes.

[0029] In an optional implementation, the storage module comprises:

[0030] a storage submodule, configured to store the to-be-stored data carrying the label to the preset storage location in an array manner.

[0031] In an optional implementation, the clustering module comprises:

[0032] a first determining submodule, configured to determine a membership degree of the to-be-processed data to each clustering center; a second determining submodule, configured to determine a distance between the to-be-processed data and the clustering center based on the to-be-processed data, the membership degree, and the clustering center; and a third determining submodule, configured to determine a clustering cluster corresponding to each clustering center based on the distance.

[0033] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, which are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the data searching method of the multi-energy complementary new energy digital power station according to the first aspect or any of the corresponding embodiments thereof.

[0034] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the data searching method of the multi-energy complementary new energy digital power station according to the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0036] Figure 1 FIG. 1 is a flowchart of a data searching method of a multi-energy complementary new energy digital power station according to an embodiment of the present application;

[0037] Figure 2 FIG. 1 is a flowchart of a data searching method of a multi-energy complementary new energy digital power station according to an embodiment of the present application;

[0038] Figure 3 FIG. 1 is a flowchart of a data searching method of a multi-energy complementary new energy digital power station according to an embodiment of the present application;

[0039] Figure 4 FIG. 1 is a flowchart of a data searching method of a multi-energy complementary new energy digital power station according to an embodiment of the present application; DETAILED DESCRIPTION

[0040] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0041] In order to avoid the problem of low efficiency of current data searching, the embodiment of the present application provides a data searching method of a multi-energy complementary new energy digital power station, which takes the mapping relationship between two related physical quantities as a searching bridge, and determines the data to be searched by using the mapping relationship and the physical quantity related to the physical quantity to which the data to be searched belongs. Through the above-mentioned manner, the data to be searched can be quickly and accurately searched, thereby improving the searching efficiency.

[0042] According to the embodiment of the present application, a data searching method of a multi-energy complementary new energy digital power station is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0043] The application provides a data searching method of a multi-energy complementary new energy digital power station, which can be used for a computer device, Figure 1 The application provides a data searching method of a multi-energy complementary new energy digital power station, which can be used for a computer device, Figure 1 The application provides a data searching method of a multi-energy complementary new energy digital power station, which can be used for a computer device,

[0044] Step S101, clustering the pre-acquired to-be-processed data to obtain a clustering cluster, and the clustering cluster includes a first physical quantity to which the first to-be-processed data belongs and a second physical quantity to which the second to-be-processed data belongs.

[0045] Specifically, the to-be-processed data includes the first to-be-processed data and the second to-be-processed data.

[0046] Specifically, the to-be-processed data includes data corresponding to at least two physical quantities. For example, the pre-acquired to-be-processed data includes temperature data corresponding to temperature, power data corresponding to power generation power, structure data corresponding to a fan structure, and position data corresponding to a fan position, wherein the temperature, the power generation power, the fan structure and the fan position are physical quantities. After obtaining the to-be-processed data, all the to-be-processed data are subjected to clustering processing to obtain at least one clustering cluster. Since in the clustering process, the to-be-processed data corresponding to two physical quantities which may have a correlation relationship are clustered into one cluster, the clustering cluster includes two types of data, i.e., the first to-be-processed data corresponding to the first physical quantity and the second to-be-processed data corresponding to the second physical quantity.

[0047] Step S102, when it is verified by a logistic regression algorithm that there is a correlation between the first physical quantity and the second physical quantity, determining a mapping relationship between the first physical quantity and the second physical quantity based on the first to-be-processed data and the second to-be-processed data.

[0048] Specifically, the mapping relationship function and a hypothesis function in the logistic regression algorithm are used to determine a probability that the first physical quantity and the second physical quantity have a correlation relationship. When the probability value is greater than 0.5, it is indicated that there is a correlation relationship between the first physical quantity and the second physical quantity, and otherwise, there is no correlation relationship.

[0049] Exemplarily, the hypothesis function in the logistic regression algorithm is a polynomial, which is a hyperplane function, and is used to determine whether the first physical quantity and the second physical quantity have a correlation relationship based on the first to-be-processed data and the second to-be-processed data. The hypothesis function is as follows:

[0050] h θ (x)=θ0+θ1x1+Λ+θ n x n =θ T x

[0051] wherein θ0, θ1, …, θ nare coefficients in the hypothesis function (i.e., the polynomial function), x1, …, x n are variables in the hypothesis function.

[0052] When the result determined according to the hypothesis function is that the correlation between the first physical quantity and the second physical quantity can be determined according to the first to-be-processed data and the second to-be-processed data, it is determined whether the correlation between the first physical quantity and the second physical quantity exists by using the mapping relationship function. The mapping relationship function is as follows:

[0053]

[0054] g(θ T x) is an output result of the mapping relationship function, and takes a value between 0 and 1. g(θ T x) is used to determine whether the correlation between the first variable and the second variable exists.

[0055] Specifically, when the correlation between the first physical quantity and the second physical quantity exists, the first to-be-processed data and the second to-be-processed data are fitted to obtain the mapping relationship between the first physical quantity and the second physical quantity, which can be a functional relationship, etc.

[0056] Exemplarily, if n clusters are obtained after the clustering operation, after verification by the logistic regression algorithm, there are at most 5 groups of variables with correlation.

[0057] In step S103, when it is determined according to the search instruction that the physical quantity to which the to-be-searched data belongs includes multiple physical quantities, and the multiple physical quantities include the physical quantity with correlation, the physical quantity to which the to-be-searched data belongs is divided into a first set and a second set.

[0058] Specifically, the number of physical quantities in the first set is greater than or equal to the number of physical quantities in the second set, and the first set includes the physical quantity with correlation with any physical quantity in the second set.

[0059] Exemplarily, the to-be-searched data is determined based on the received computer instruction. The computer instruction can include the time interval to be searched, the space interval to be searched, and the physical quantity to which the to-be-searched data belongs, such as the data of the output power, the temperature, and the output voltage of the fan in a certain region in a certain time period.

[0060] Therefore, when the search instruction is received, the to-be-searched physical quantity (i.e., the physical quantity to which the to-be-searched data belongs) needs to be determined first; for example, the to-be-searched physical quantity includes A, B, a, c, C, and d.

[0061] Secondly, the physical quantity with correlation and the independent physical quantity are determined from the to-be-searched physical quantity; the physical quantity with correlation, such as A and a, and C and c; the independent physical quantity, such as B and d.

[0062] Again, the physical quantities with relevance are respectively stored into two sets, such as A and C are classified into one set, and a and c are classified into another set, i.e. P={A, C}; Q={a, c}.

[0063] Finally, all independent physical quantities are divided into any one of the above sets, and the set in which the independent physical quantity is located is defined as the first set, and the other set is defined as the second set. For example, P={A, C, B, d}; Q={a, c}, set P is the first set, and set Q is the second set.

[0064] In step S104, the first to-be-searched data corresponding to each physical quantity in the first set is searched.

[0065] Specifically, the first to-be-searched data is searched from a preset storage location, the first to-be-searched data is a collective term of the to-be-searched data corresponding to each physical quantity in the first set, and the preset storage location is used to store all data of the digital power station.

[0066] For example, still taking the example in step S103, the to-be-searched data corresponding to physical quantity A, the to-be-searched data corresponding to physical quantity C, the to-be-searched data corresponding to physical quantity B and the to-be-searched data corresponding to physical quantity d in the first set (i.e. set P) are searched respectively.

[0067] In step S105, the second to-be-searched data is determined based on the first to-be-searched data and the mapping relationship.

[0068] Specifically, the to-be-searched data includes the first to-be-searched data and the second to-be-searched data.

[0069] For example, the to-be-searched data corresponding to physical quantity a can be obtained according to the to-be-searched data corresponding to physical quantity A searched in step S104 and the mapping relationship between physical quantity A and physical quantity a. Similarly, the to-be-searched data corresponding to physical quantity c can be obtained according to the to-be-searched data corresponding to physical quantity C and the mapping relationship between physical quantity C and physical quantity c.

[0070] In the prior art, when the to-be-searched physical quantity is 6 (such as A, B, a, c, C, d), 6 searches are required respectively, but if the searching method disclosed in the embodiment is used, only 4 searches are required, so the data searching method disclosed in the embodiment is more efficient.

[0071] The data searching method of the multi-energy complementary new energy digital power station provided by the embodiment firstly determines the first physical quantity and the second physical quantity that may have relevance through clustering operation, and then verifies whether the first physical quantity and the second physical quantity indeed have relevance through a logistic regression algorithm. If there is relevance, a mapping relationship between the first physical quantity and the second physical quantity can be constructed according to first to-be-processed data corresponding to the first physical quantity and second to-be-processed data corresponding to the second physical quantity. When a data searching instruction is received, if it is determined that the physical quantity to which the data to be searched belongs includes multiple physical quantities and the multiple physical quantities include the physical quantity having relevance based on the data searching instruction, the physical quantity to which the data to be searched belongs is divided into a first set and a second set. The reason for dividing the physical quantity into two sets is that there is relevance between part of the physical quantities, that is, one seeks one, therefore, the embodiment only needs to firstly search for the first to-be-searched data corresponding to each physical quantity in the first set, and then determines the second to-be-searched data according to the first to-be-searched data and the mapping relationship. Compared with the previous way of searching data by sequentially traversing, the above way is adopted to reduce the amount of data searching, thereby improving the efficiency of data searching.

[0072] In an optional embodiment, before step S101, the method further includes:

[0073] Step a1, acquiring to-be-stored data.

[0074] Specifically, the to-be-stored data includes data in the digital power station.

[0075] Step a2, determining a category to which the to-be-stored data belongs as a label corresponding to the to-be-stored data according to a preset data division criterion.

[0076] Specifically, the preset data division criterion includes a first criterion of division according to data types, a second criterion of division according to data dimensions, and a third criterion of division according to data weights and dynamic and static attributes. The data types include but are not limited to structural data, operation data, and environmental data, etc.; the data dimensions include one-dimensional point data, two-dimensional surface data, and three-dimensional body data; the data weight is used to measure the importance of the data, and the important weight is set by a person skilled in the art based on the influence of the physical quantity to which the data belongs on the unit operation; the dynamic and static attributes are dynamic attributes and static attributes, the dynamic attribute is a quantity that changes according to changes of other factors, and the static attribute is a quantity that does not change. It should be noted that the more data division criteria, the more concrete the data, and the number and types of data division criteria are not limited here, and a person skilled in the art can set them according to actual conditions.

[0077] Exemplarily, after obtaining a data M to be stored, firstly, it is judged according to the first criterion that the M data belongs to which data type, for example, the M data belongs to running data, then the running data is determined as the first label of the M data; then, the dimension of the M data is judged according to the second criterion, for example, the M data belongs to two-dimensional surface data, then the two-dimensional surface data is determined as the second label of the M data; finally, the weight and dynamic and static properties of the M data are judged according to the third criterion, for example, the third label of the M data is determined as two static data, and the data level increases with the importance.

[0078] Step a3, storing the data to be stored carrying the label to a preset storage location.

[0079] Specifically, after the above operation, the A data carrying three labels is stored to the preset storage location.

[0080] Specifically, the data to be stored carrying the label can be stored to the preset storage location in an array manner. The form of data storage is not specifically limited in the embodiment, and can be selected by the person skilled in the art.

[0081] Step a4, obtaining a target label.

[0082] Specifically, the target label is a label corresponding to the pre-acquired data to be processed, and the target label can be embodied by a search instruction.

[0083] Step a5, obtaining the data to be processed carrying the target label from the preset storage location.

[0084] In the embodiment, the data to be processed is obtained from the preset storage location by taking the target label as an index, so that the efficiency of data acquisition is improved.

[0085] In the embodiment, a data search method of a multi-energy complementary new energy digital power station is provided, which can be used for a computer device, Figure 2 is a flowchart of the data search method of the multi-energy complementary new energy digital power station according to the embodiment of the application, as shown in the figure, the flowchart comprises the following steps: Figure 2

[0086] Step S201, clustering the pre-acquired data to be processed to obtain a clustering cluster, the clustering cluster comprising a first physical quantity to which the first data to be processed belongs and a second physical quantity to which the second data to be processed belongs, the data to be processed comprising the first data to be processed and the second data to be processed.

[0087] Specifically, the above step S201 comprises:

[0088] Step S2011, determining the membership degree of the data to be processed to each clustering center.

[0089] Exemplarily, the determination method of the membership degree is as follows: ​

[0090]

[0091] Where M is the dataset, C is the number of cluster centers, and u ij Let be the membership degree of the i-th data point to the j-th centroid, and 0. ij <1.

[0092] Step S2012: Determine the distance between the data to be processed and the cluster centers based on the data to be processed, membership degree, and cluster centers.

[0093] For example, the distance between the data to be processed and the cluster center is achieved in the following way:

[0094]

[0095] Where J represents the i-th data to be processed x i With the j-th cluster center C j The distance between them, where M represents the total number of data to be processed, and C represents the total number of cluster centers. middleu ij This represents the i-th data to be processed, x. i For the j-th cluster center C j The membership degree, where α represents the hyperparameter.

[0096] Step S2013: Determine the cluster corresponding to each cluster center based on distance.

[0097] Specifically, the distances between the data to be processed and each cluster center are sorted. The minimum distance is selected from the sorted distances, and the cluster corresponding to the cluster center with the minimum distance is determined as the cluster to which the data to be processed belongs. After performing the above processing on all the data to be processed, the cluster corresponding to each cluster center can be obtained.

[0098] Step S202: When the correlation between the first physical quantity and the second physical quantity is verified using the logistic regression algorithm, the mapping relationship between the first physical quantity and the second physical quantity is determined based on the first and second data to be processed. For details, please refer to... Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0099] Step S203: If, according to the search instruction, the physical quantity to which the data to be searched belongs includes multiple physical quantities, and these multiple physical quantities contain related physical quantities, then the physical quantities to which the data to be searched belongs are divided into a first set and a second set. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0100] ​Step S204: Locate the first data to be searched for for each physical quantity in the first set. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0101] Step S205: Determine the second data to be searched based on the first data to be searched and the mapping relationship. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0102] This embodiment also provides a data retrieval device for a novel multi-energy complementary digital power station. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0103] This embodiment provides a data retrieval device for a novel multi-energy complementary digital power station, such as... Figure 3 As shown, it includes:

[0104] Clustering module 301 is used to cluster the pre-acquired data to be processed to obtain clusters. The clusters include a first physical quantity to which the first data to be processed belongs and a second physical quantity to which the second data to be processed belongs. The data to be processed includes the first data to be processed and the second data to be processed.

[0105] The first determining module 302 is used to determine the mapping relationship between the first physical quantity and the second physical quantity based on the first data to be processed and the second data to be processed when the correlation between the first physical quantity and the second physical quantity is verified by using a logistic regression algorithm.

[0106] The partitioning module 303 is used to partition the physical quantities to which the data to be searched belongs into a first set and a second set when the physical quantities to which the data to be searched belongs include multiple physical quantities and the multiple physical quantities include physical quantities that are related. The number of physical quantities in the first set is greater than or equal to the number of physical quantities in the second set, and the first set includes physical quantities that are related to any physical quantity in the second set.

[0107] The lookup module 304 is used to look up the first data to be searched for corresponding to each physical quantity in the first set.

[0108] The second determining module 305 is used to determine the second search data based on the first search data and the mapping relationship. The search data includes the first search data and the second search data.

[0109] In some alternative implementations, the following is included before clustering module 301:

[0110] The first acquisition module is used to acquire the target tag.

[0111] The second acquisition module is used to acquire the data to be processed carrying the target tag from a preset storage location.

[0112] In some alternative implementations, the module prior to the first acquisition module includes:

[0113] The third acquisition module is used to acquire data to be stored, including data from the digital power plant.

[0114] The third determination module is used to determine the category to which the data to be stored belongs as the corresponding label according to the preset data classification criteria.

[0115] The storage module is used to store the data to be stored, which carries the tag, to a preset storage location.

[0116] In some optional implementations, the preset data partitioning criteria in the third determining module include:

[0117] The first criterion for classification is based on data type, the second criterion is based on data dimension, and the third criterion is based on data weight and static / dynamic attributes.

[0118] In some alternative implementations, the storage module includes:

[0119] The storage submodule is used to store the data to be stored, carrying tags, in an array format to a preset storage location.

[0120] In some alternative implementations, clustering module 301 includes:

[0121] The first determination submodule is used to determine the membership degree between the data to be processed and each cluster center.

[0122] The second determination submodule is used to determine the distance between the data to be processed and the cluster centers based on the data to be processed, membership degree, and cluster centers.

[0123] The third determination submodule is used to determine the cluster corresponding to each cluster center based on distance.

[0124] In some alternative implementations, the second determining submodule is implemented in the following manner:

[0125]

[0126] Where J represents the i-th data to be processed x i With the j-th cluster center C jThe distance between them, where M represents the total number of data to be processed, and C represents the total number of cluster centers. middleu ij This represents the i-th data to be processed, x. i For the j-th cluster center C j The membership degree, where α represents the hyperparameter.

[0127] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0128] In this embodiment, the data retrieval device for a novel multi-energy complementary digital power station is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0129] This invention also provides a computer device having the above-described features. Figure 3 The data retrieval device shown is for a new type of digital power station with multi-energy complementarity.

[0130] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0131] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0132] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0133] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0134] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0135] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0136] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0137] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A data retrieval method for a new type of multi-energy complementary digital power station, characterized in that, The method includes: Clustering is performed on the pre-acquired data to be processed to obtain clusters. The clusters include a first physical quantity to which the first data to be processed belongs and a second physical quantity to which the second data to be processed belongs. The data to be processed includes the first data to be processed and the second data to be processed. When using logistic regression algorithm to verify the correlation between the first physical quantity and the second physical quantity, the mapping relationship between the first physical quantity and the second physical quantity is determined based on the first data to be processed and the second data to be processed. When the physical quantity to which the data to be searched belongs is determined according to the search instruction, and the physical quantity to which the data to be searched belongs includes multiple physical quantities, and the multiple physical quantities include physical quantities that are related, the physical quantity to which the data to be searched belongs is divided into a first set and a second set. The number of physical quantities in the first set is greater than or equal to the number of physical quantities in the second set, and the first set includes physical quantities that are related to any physical quantity in the second set. Find the first data to be searched for for each physical quantity in the first set; The second data to be searched is determined based on the first data to be searched and the mapping relationship, wherein the data to be searched includes the first data to be searched and the second data to be searched.

2. The method according to claim 1, characterized in that, Before clustering the pre-acquired data to be processed to obtain clusters, the method further includes: Obtain the target tag; The data to be processed, carrying the target tag, is retrieved from a preset storage location.

3. The method according to claim 2, characterized in that, Prior to obtaining the target label, the method further includes: Acquire the data to be stored, which includes data from the digital power plant; According to the preset data classification criteria, the category to which the data to be stored belongs is determined as the tag corresponding to the data to be stored; The data to be stored, carrying the tag, is stored in the preset storage location.

4. The method according to claim 3, characterized in that, The preset data partitioning criteria include: The first criterion for classification is based on data type, the second criterion is based on data dimension, and the third criterion is based on data weight and static / dynamic attributes.

5. The method according to claim 3, characterized in that, The step of storing the data to be stored, carrying the tag, to the preset storage location includes: The data to be stored, carrying the tag, is stored in an array at the preset storage location.

6. The method according to claim 1, characterized in that, The process of clustering the pre-acquired data to be processed to obtain clusters includes: Determine the membership degree between the data to be processed and each cluster center; The distance between the data to be processed and the cluster center is determined based on the data to be processed, the membership degree, and the cluster center. The cluster corresponding to each of the cluster centers is determined based on the distance.

7. The method according to claim 6, characterized in that, The determination of the distance between the data to be processed and the cluster center based on the data to be processed, the membership degree, and the cluster center is achieved in the following way: Where J represents the i-th data to be processed x i With the j-th cluster center C j The distance between them, where M represents the total number of data to be processed, and C represents the total number of cluster centers. middleu ij This represents the i-th data to be processed, x. i For the j-th cluster center C j The membership degree, where α represents the hyperparameter.

8. A data retrieval device for a new type of multi-energy complementary digital power station, characterized in that, The device includes: The clustering module is used to cluster the pre-acquired data to be processed to obtain clusters. The clusters include a first physical quantity to which the first data to be processed belongs and a second physical quantity to which the second data to be processed belongs. The data to be processed includes the first data to be processed and the second data to be processed. The first determining module is used to determine the mapping relationship between the first physical quantity and the second physical quantity based on the first data to be processed and the second data to be processed when the correlation between the first physical quantity and the second physical quantity is verified by using a logistic regression algorithm. The partitioning module is used to divide the physical quantity to which the data to be searched belongs into a first set and a second set when the physical quantity to which the data to be searched belongs includes multiple physical quantities and the multiple physical quantities include related physical quantities. The number of physical quantities in the first set is greater than or equal to the number of physical quantities in the second set, and the first set includes physical quantities that are related to any physical quantity in the second set. The search module is used to search for the first data to be searched corresponding to each physical quantity in the first set; The second determining module is used to determine the second search data based on the first search data and the mapping relationship, wherein the search data includes the first search data and the second search data.

9. The apparatus according to claim 8, characterized in that, Prior to the clustering module, the apparatus further includes: The first acquisition module is used to acquire the target tag; The second acquisition module is used to acquire the data to be processed carrying the target tag from a preset storage location.

10. The apparatus according to claim 9, characterized in that, Prior to the first acquisition module, the device further includes: The third acquisition module is used to acquire data to be stored, including data from the digital power plant. The third determining module is used to determine the category to which the data to be stored belongs as the tag corresponding to the data to be stored according to a preset data classification criterion; A storage module is used to store the data to be stored, which carries the tag, to the preset storage location.

11. The apparatus according to claim 10, characterized in that, The preset data partitioning criteria in the third determining module include: The first criterion for classification is based on data type, the second criterion is based on data dimension, and the third criterion is based on data weight and static / dynamic attributes.

12. The apparatus according to claim 10, characterized in that, The storage module includes: The storage submodule is used to store the data to be stored, carrying the tag, in an array format to the preset storage location.

13. The apparatus according to claim 8, characterized in that, The clustering module includes: The first determination submodule is used to determine the membership degree between the data to be processed and each cluster center; The second determining submodule is used to determine the distance between the data to be processed and the cluster center based on the data to be processed, the membership degree, and the cluster center; The third determining submodule is used to determine the cluster corresponding to each of the cluster centers based on the distance.

14. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the data search method for a multi-energy complementary new energy digital power station as described in any one of claims 1 to 7.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the data search method for a multi-energy complementary new energy digital power station as described in any one of claims 1 to 7.

Images