Intelligent Substation Operation and Distribution Data Acquisition and Fusion Method and System Based on Container Technology

Abstract

The present disclosure belongs to the field of power system and its automation, and provides a method and system for intelligent substation operation and distribution data acquisition and fusion based on container technology. The method includes the following steps: acquiring substation operation and distribution data; preprocessing the data by using a data parallel preprocessing method based on Spark; completing data fusion on the preprocessed data through a unified information model; placing the fused data in different containers with security isolation according to task identifiers, so as to achieve the comprehensiveness and efficiency of intelligent substation data acquisition considering multi-side perception requirements by breaking through the data barrier between the marketing and distribution business systems, reduce the user complaint rate, timely discover the hidden dangers of the distribution network safety, strengthen the power outage management, and improve the user service level and power supply safety reliability.

Description

Technical Field

[0001] The present invention belongs to the field of power system and its automation, and specifically relates to a method and system for collecting and integrating operation and distribution data of intelligent substations based on container technology. Background Technique

[0002] The statements in this part only provide background technical information related to the present disclosure, and do not necessarily constitute prior art.

[0003] With the development of the construction of intelligent distribution networks, intelligent substations will be an integral part of the smart grid, and are generally developing towards the overall direction and overall goal of having a reliable and efficient distribution network grid structure, a communication network with high reliability and high security, a high-penetration distributed power access, rapid simulation and self-healing control of the distribution system.

[0004] Although intelligent substations have good development prospects, there are also problems. The marketing and distribution business systems of the distribution network are relatively independent, lacking a data interaction mechanism and system interface between the systems, and the phenomenon of information islands is serious. The relevance and complementarity between marketing and distribution data have not been fully utilized, which is not conducive to integrating distribution network data resources and realizing rapid analysis of multi-source data of the distribution network. Moreover, with the increasing proportion of various networked energy supply and consumption devices such as electricity, gas, cold, heat networks, distributed photovoltaics, energy storage, electric vehicle charging piles, and smart home appliances in intelligent substations, the existing integrated marketing and distribution information system can no longer meet the requirements of holographic perception and status recognition of power distribution and consumption at the end of the substation, and problems such as incomplete data access types have emerged. Summary of the Invention

[0005] In order to solve the above problems, the present disclosure proposes a method and system for collecting and integrating operation and distribution data of intelligent substations based on container technology, which realizes the comprehensiveness and efficiency of data collection for intelligent substations considering multi-side perception requirements by breaking through the data barriers between marketing and distribution business systems, reduces the user complaint rate, discovers potential safety hazards in the distribution network in a timely manner, strengthens power outage management, and improves the user service level and power supply safety and reliability.

[0006] To achieve the above object, the present disclosure adopts the following technical solutions:

[0007] In a first aspect, a method for collecting and integrating operation and distribution data of an intelligent substation based on container technology includes the following steps:

[0008] Obtain the operation and distribution data of the substation;

[0009] Preprocess the operation and distribution data by using a data parallel preprocessing method based on Spark;

[0010] Complete data fusion for the preprocessed data through a unified information model;

[0011] The fused data is placed in different containers that are securely isolated according to the task identifier.

[0012] As a further qualification, the process of preprocessing the data includes:

[0013] Data dimension reduction and data removal / filling based on map and reduce functions;

[0014] Data denoising based on amplitude limiting and de-jittering filtering algorithm;

[0015] Screening and removal of data outlier records based on K-means clustering.

[0016] As a further limitation, the construction process of the unified information model includes the following steps:

[0017] Take the preprocessed data as input sample;

[0018] Introduce nonlinear mapping and kernel function of transformation, and classify samples by mapping them into high-dimensional space;

[0019] The sample classification formula is solved according to the KKT optimal condition and the least square method to obtain the weight vector and bias vector in the input sample set space, and the decision value is obtained according to the weight vector and bias vector;

[0020] The decision quantity is normalized to obtain the consistency coefficient.

[0021] As a further limitation, the security isolation method between the containers is to determine the division method of the object address space according to a security isolation policy rule set, and different subjects access different address spaces according to different permissions.

[0022] As a further limitation, the security isolation policy rule set includes Rule 1 and Rule 2; Rule 1 represents the address space that any container subject can read and operate, and Rule 2 represents the address space that any container subject can write.

[0023] As a further limitation, the method of dividing the object address space according to the security isolation policy rule set is: create a new container, allocate a container subject and an object address space to the container, the container subject performs any operation on the object within the address space range within the container, initiates a system call to the host subject, applies for access to the corresponding address space, and different subjects access different address spaces according to different permissions.

[0024] As a further limitation, the securely isolated containers are divided into different security levels, each different security level contains different containers, and each container has an information, and the containers are divided into corresponding security levels through container multi-level access control.

[0025] In a second aspect, a smart substation operation and distribution data acquisition and fusion system based on container technology is provided, including:

[0026] A data acquisition module, which is configured to: acquire operation and distribution data of the substation through a unified data interface;

[0027] A preprocessing module, which is configured to: preprocess the operation and distribution data by using a data parallel preprocessing method based on Spark;

[0028] A data fusion module, which is configured to: complete data fusion of the preprocessed data through a unified information model;

[0029] A data storage module, which is configured to: place the fused data in different containers with security isolation according to the task identifier.

[0030] In a third aspect, a computer-readable storage medium is provided, in which multiple instructions are stored, and the instructions are suitable for being loaded and executed by a processor of a terminal device to perform the steps of a smart substation operation and distribution data acquisition and fusion method based on container technology.

[0031] In a fourth aspect, a terminal device is provided, including a processor and a computer-readable storage medium. The processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded and executed by the processor to perform the steps of a smart substation operation and distribution data acquisition and fusion method based on container technology.

[0032] Compared with the prior art, the beneficial effects of the present disclosure are:

[0033] (1) The operation and distribution data acquisition and fusion method provided by the present invention can eliminate possible conflicts in data acquisition by each sensor. This method uniformly describes different data by constructing a unified information model, which can effectively avoid the problem of inconsistent data models and the workload of model conversion in data exchange. Since it is unified modeling and unified storage, there is no redundancy in data, and thus there is no need to perform data exchange, comparison, etc. in two sets of systems, greatly reducing the development and maintenance workload.

[0034] (2) Through container address space partitioning, the present invention can effectively isolate direct or indirect information exchange between containers, and no container entity can directly read the address space and content written by other container entities, ensuring data security.

[0035] (3) Through container multi-level access control, the present invention can effectively restrict the communication of unauthorized containers, enhance the security isolation between containers, prevent the running environment of the containers and the containers themselves from being tampered with and attacked, and ensure the legality of the internal operation of the containers. Brief Description of the Drawings

[0036] The accompanying drawings forming a part of this disclosure are used to provide a further understanding of the disclosure. The schematic embodiments and descriptions thereof of the disclosure are used to explain the disclosure and do not constitute an improper limitation of the disclosure.

[0037] Figure 1 It is a flowchart of the intelligent substation operation and distribution data acquisition and fusion method based on container technology for this embodiment;

[0038] Figure 2 It is the division relationship of the address space corresponding to the object in the fusion terminal for this embodiment;

[0039] Figure 3 It is the organizational chart of the container security level for this embodiment. Detailed Description of the Embodiments

[0040] The following further describes the disclosure in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanations of the disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this disclosure belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to this disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0043] Term Explanation:

[0044] Operation and distribution: "Operation" refers to marketing and operation, and "distribution" refers to power distribution and transmission.

[0045] Embodiment 1

[0046] Figure 1 It is a flowchart of the intelligent substation operation and distribution data acquisition and fusion method based on container technology for Embodiment 1. As Figure 1 shown, the intelligent substation operation and distribution data acquisition and fusion method based on container technology for Embodiment 1 includes the following steps:

[0047] S1: Collect the operation and distribution data of the substation through a unified data interface;

[0048] S2: Preprocess the data using a data parallel preprocessing method based on Spark;

[0049] There are problems of duplicate redundancy and data non-uniformity in the data collected from each system of marketing and power distribution. The present invention uses a data parallel preprocessing method based on Spark to solve the problems, and the main steps are as follows:

[0050] S201: Data dimensionality reduction, data empty / deficiency filling based on the map function and reduce;

[0051] Specifically, it includes the following steps:

[0052] (1) Import the original data into Spark to form a resilient distributed dataset for parallel computing;

[0053] (2) Remove the fields that are invalid for data analysis through feature selection;

[0054] (3) Use the transformer ID of the transformer substation area and the recorded date as the duplicate checking criterion of the map function, and mark the duplicate data records. Use the database operations provided by Spark SQL to merge the data according to the two key fields, and finally return the positions where the number of merged data records is greater than 1. Use the reduce function to delete the corresponding rows in the original array to obtain a new dataset with duplicate data removed.

[0055] (4) Use the map function to calculate the missing ratio of the attributes in a single record, remove the empty records with a missing ratio greater than 30%, and fill in the records with a missing ratio less than 30% through the Lagrange interpolation method.

[0056] S202: Data denoising based on the amplitude-limiting and jitter-eliminating filtering algorithm;

[0057] Specifically, it includes the following steps:

[0058] Determine the maximum allowable deviation value for two samplings of the load data. By comparing the difference between two data in consecutive time slices and judging whether the data error is within the maximum deviation value range. If not, the data in the subsequent time slice needs to be replaced with a reasonable value, which can be a copy of the value at the previous time point or the statistical result of the data record;

[0059] The specific approach in combination with Spark is to first use the map function to check each data record one by one, and then use the reduce function to replace the data records that are greater than the deviation value according to the result of the most recent sampling.

[0060] Among them, the maximum allowable deviation value for two samplings of the load data is determined based on expert experience.

[0061] S203: Screening and removing the outlier records based on K-means clustering;

[0062] Specifically, it includes the following steps:

[0063] (1) Convert the data into a structured DataFrame for easy API calculation;

[0064] (2) Import the Spark MLlib algorithm library and implement the clustering of the load by calling the KMeans function; the hyperparameters of the clustering algorithm are set based on expert experience;

[0065] (3) Delete the unclassified data records according to the clustering results using the drop function.

[0066] Since the Spark ecosystem provides a machine learning algorithm library, the data can be directly analyzed by calling functions provided by Spark through the API without implementing a complex load clustering algorithm through a large amount of code.

[0067] S3: Complete data fusion for the preprocessed data through a unified information model; among them, the construction process of the unified information model is as follows:

[0068] Let the processed data set be X = {x1, x2, x3,..., x n}, and a certain data x k can be expressed as:

[0069] T = {(x1, y1),..., (x k , y k )} ∈ (R n ×y) (1)

[0070] where x i ∈ R n is the input sample, y i ∈ y = R is the output sample, i = 1, 2,..., n to find the real-valued decision quantity g i , and the decision quantity is the regression equation for inferring y from x:

[0071] y = g i = (w·x) + b (2)

[0072] In the formula, w is the weight vector in the R n space; b is the bias vector;

[0073] After introducing the nonlinear mapping of the transformation x = Φ(x) and the kernel function K(x, x') = (Φ(x)·Φ(x')), classification is performed by mapping to a high-dimensional space, and the classification formula can be expressed as:

[0074]

[0075] s.t. y i (w·Φ(xi )) + b + η i , i = 1, 2, …, l (4)

[0076] Where η = [η1, η2, …, η l is the error variable; C is the penalty coefficient. According to the Lagrangian function, we can get:

[0077]

[0078] Where α = [α1, α2, …, α i , …, α l T represents the Lagrange multiplier. According to the KKT optimality conditions, the above formula is differentiated to obtain:

[0079]

[0080] Find a and b according to the least squares method. Let be any solution to the above problem. Then the solution (w * , b * ) can be calculated according to the following formula:

[0081]

[0082]

[0083]

[0084] Normalize the decision-making quantity:

[0085]

[0086]

[0087] Where q i is the consistency coefficient.

[0088] The advantage of the above solution is that the operation and distribution data acquisition and fusion method provided by the present invention can eliminate possible conflicts in data acquisition by each sensor. This method constructs a unified information model to uniformly describe different data, which can effectively avoid the problem of inconsistent data models and the workload of model conversion in data exchange. Since it is unified modeling and unified storage, there is no redundancy in data, and thus there is no need to perform data exchange, comparison, etc. in two sets of systems, greatly reducing the development and maintenance workload.

[0089] S4: Place the fused data in different containers that have been safely isolated according to the task identifier;

[0090] ​Among them, each container has an independent task identification mechanism. When mapping to the integrated terminal kernel, a complete task identification is formed by combining the container identification and the task identification. The operation and maintenance data integration terminal isolates the business software from the operating system through container technology, improving the system security while isolating the power distribution service APP and the power consumption information acquisition service APP.

[0091] Furthermore, the security isolation method between the containers is as follows: construct a set of security isolation policy rules, determine the partitioning method of the object address space according to the set of security isolation policy rules, and different subjects access different address spaces according to different permissions.

[0092] For j, 1 ≤ i ≤ n, 1 ≤ j ≤ n, i ≠ j, there is R(Co i ) ∩ W(Co i ) = φ.

[0093] In the formula, R: S → 2 L represents the object address space where the subject S can perform read operations; W: S → 2 L represents the object address space where the subject S can perform write operations; Co i (1 ≤ i ≤ n) represents the container i subject.

[0094] Among them, according to the set of security isolation policy rules, determine the partitioning method of the object address space;

[0095] The rule set includes:

[0096] Rule 1:

[0097] Rule 2:

[0098] In the formula, H represents the address space corresponding to the objects that the host subject can operate on arbitrarily. Let H x represent the first type of address space in H, H ro represent the second type of address space in H, and H ic (1 ≤ i ≤ n) represent the third type of address space in H.

[0099] Among them, Rule 1 means that the address space where any container i (1 ≤ i ≤ n) subject can perform read operations includes the container address space C i (1 ≤ i ≤ n) corresponding to all objects within the container i, the address space H ro corresponding to the objects that all subjects in H can only perform read operations on, and the object address space H ic (1 ≤ i ≤ n) corresponding to the container i subject in H where reading and writing can be performed.

[0100] Rule 2 states that the address space that the body of any container i (1 ≤ i ≤ n) can write to includes the container address space C corresponding to all the objects within container i i (1 ≤ i ≤ n), and the object address space H in H that only the body of container i can read and write ic (1 ≤ i ≤ n).

[0101] This application proposes an address space partitioning method that meets the restrictive conditions in Rule 1 and Rule 2, that is, different subjects access different address spaces according to different permissions, and it is ensured that all containers in the converged terminal are securely isolated from each other.

[0102] That is, for j, 1 ≤ i ≤ n, 1 ≤ j ≤ n, i ≠ j, there is R(Co i ) ∩ W(Co i ) = (C i ∪H ro ∪H ic ) = (C j ∪H jc ) = φ.

[0103] The method for determining the partitioning of the object address space according to the set of security isolation policy rules is as Figure 2 shown. Create a new container, allocate a container body and a certain range of object address space for the container. The container body can perform any operation on the objects within this address space range in the container, and can initiate a system call to the body according to needs to apply for access to the corresponding address space, and different subjects access different address spaces according to different permissions. Q represents the address space corresponding to all objects. According to the set of security isolation policy rules, the address space corresponding to all objects can be regarded as an (n + 1)-tuple, where n represents the number of containers among the subjects, that is, Q = {H, C1, C2, …, C n}, and the object address space that the subject can operate on arbitrarily can be regarded as an (n + 2)-tuple, that is, H = {H x , H ro , H 1c , H 2c , …, H nc}.

[0104] The advantage of the above solution is that through the partitioning of the container address space, the present invention can effectively isolate the containers so that there is no direct or indirect information exchange between them, and the address space and content written by any other container body cannot be directly read by any one container body, ensuring the security of the data.

[0105] S5: Classify the containers into different security levels, denoted as L.

[0106] To avoid unauthorized communication between containers, the present invention classifies containers into different security levels, where L = {L1, L2, L3, L4, L5, L6, L7}, and the relationships between the levels are as Figure 3 shown:

[0107] In container multi-level access control, each different security level L i contains different containers L i C i , and L i C is denoted as the set of containers included in the L i security level. Then

[0108] L i C = {L i C1, L i C2,..., L i C n} (12)

[0109] And each container has an information L i C i m i . L i C i M is denoted as the set of container information. Then

[0110] L i C i M = {L i C1m1, L i C2m2,..., L i C n m n} (13)

[0111] For each container, the administrator can classify the container into the corresponding security level according to his own needs.

[0112] The subject L i can encrypt the information m through the following relational expression to obtain the ciphertext c:

[0113] c = m e modN i (14)

[0114] If L j is an ancestor of L i , the subject L j can parse the ciphertext c through the following relational expression to obtain the information m:

[0115]

[0116] To ensure data security, for any piece of information m, it is encrypted using K = <e, N>, denoted as [m, K], and defined as:

[0117] [m, <e, N>] = m e mod N (16)

[0118] The encryption key K = <e, N>, and the decryption key K -1 is represented by the ordered pair <d, N> and satisfies ed = 1 mod φ(N).

[0119] For the decryption key K -1 = <d, N>, given the ciphertext c, the plaintext m can be obtained through the following relationship, denoted as [c, K -1 :

[0120] m = [c, K -1 = c d mod N (17)

[0121] For any piece of information m, when K = <e, N> and K -1 = <d, N>, there is

[0122] [[m, K], K -1 = m (18)

[0123] In the multi-level relationship of the container, it is possible to encrypt the information m using the encryption key K provided by the hierarchy, and it is also possible to use the provided decryption key K -1 to decrypt the encrypted information and restore it to the information m.

[0124] Each container has an independent network environment. The tasks within the container communicate with the outside through the network. The container has its own ports, IP addresses, sockets, etc., and can achieve the docking of the marketing and power distribution dual master stations through remote communication methods such as optical fiber or 4G.

[0125] Example Two

[0126] In this example, a smart substation marketing and distribution data acquisition and fusion system based on container technology is disclosed, including:

[0127] A data acquisition module, which is configured to: collect marketing and distribution data of the substation through a unified data interface;

[0128] A preprocessing module, which is configured to: preprocess the data using a data parallel preprocessing method based on Spark;

[0129] A data fusion module, which is configured to: complete data fusion of the preprocessed data through a unified information model;

[0130] A data storage module, which is configured to: place the fused data into different containers that have been securely isolated according to the task identifier respectively.

[0131] Embodiment III

[0132] In this embodiment, a computer-readable storage medium is disclosed, in which multiple instructions are stored. The instructions are suitable for being loaded and executed by a processor of a terminal device to perform the steps of the intelligent substation operation and distribution data acquisition and fusion method based on container technology disclosed in Embodiment I.

[0133] Embodiment IV

[0134] In this embodiment, a terminal device is disclosed, including a processor and a computer-readable storage medium. The processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions. The instructions are suitable for being loaded and executed by the processor to perform the steps of the intelligent substation operation and distribution data acquisition and fusion method based on container technology described in Embodiment I.

[0135] Through container multi-level access control, the present invention can effectively restrict the communication of unauthorized containers, enhance the security isolation between containers, prevent the operating environment of the containers and the containers themselves from being tampered with and attacked, and ensure the legality of the operations inside the containers.

[0136] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0137] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0138] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0140] Although the specific embodiments of the present disclosure have been described above in conjunction with the accompanying drawings, they are not intended to limit the scope of protection of the present disclosure. Those skilled in the art should understand that, based on the technical solutions of the present disclosure, various modifications or variations that can be made without creative efforts by those skilled in the art are still within the scope of protection of the present disclosure.

Claims

1. A method for collecting and integrating operation and distribution data of intelligent substations based on container technology, characterized in that: The following steps are involved: Obtain the distribution data of the substation area; The Spark-based data parallel preprocessing method is used to preprocess the distribution data of the substation area; The preprocessed data is fused through a unified information model; the construction process of the unified information model includes the following steps: the preprocessed data is used as an input sample; the nonlinear mapping and kernel function of the transformation are introduced, and classification is performed by mapping to a high-dimensional space; the sample classification formula is solved according to the KKT optimal condition and the least squares method to obtain the weight vector and the bias vector in the input sample set space, and the decision amount is obtained according to the weight vector and the bias vector; the decision amount is normalized to obtain the consistency coefficient, and the normalization process is: ； ； Among them, represents the consistency coefficient; The fused data is placed in different containers that are securely isolated according to the task identifier.

2. The intelligent substation operation and distribution data acquisition and fusion method based on container technology according to claim 1, wherein: The process of preprocessing data includes: Data dimension reduction and data removal / filling based on map and reduce functions; Data denoising based on amplitude limiting and de-jittering filtering algorithm; Screening and removal of data outlier records based on K-means clustering.

3. The intelligent substation operation and distribution data acquisition and fusion method based on container technology according to claim 1, characterized in that: The security isolation method between containers is to determine the division method of the object address space according to the security isolation policy rule set, and different subjects access different address spaces according to different permissions.

4. The intelligent substation operation and distribution data acquisition and fusion method based on container technology according to claim 1, characterized in that: The security isolation policy rule set includes rule 1 and rule 2; rule 1 represents the address space that any container subject can read and operate, and rule 2 represents the address space that any container subject can write.

5. The intelligent substation operation and distribution data acquisition and fusion method based on container technology according to claim 3, characterized in that: The method of dividing the object address space according to the security isolation policy rule set is as follows: a new container is created, a container subject and an object address space are allocated to the container, the container subject performs any operation on the object within the address space range within the container, initiates a system call to the host subject, applies for access to the corresponding address space, and different subjects access different address spaces according to different permissions.

6. The intelligent substation operation and distribution data acquisition and fusion method based on container technology according to claim 1, characterized in that: The securely isolated containers are divided into different security levels. Each different security level contains different containers, and each container has a piece of information. The containers are divided into corresponding security levels through container multi-level access control.

7. The intelligent substation operation and distribution data acquisition and fusion system based on container technology is characterized in that include: A data acquisition module is configured to: acquire station area distribution data; The preprocessing module is configured to: preprocess the substation distribution data using a Spark-based data parallel preprocessing method; The data fusion module is configured to: complete data fusion of the preprocessed data through a unified information model; the construction process of the unified information model includes the following steps: taking the preprocessed data as input samples; introducing the nonlinear mapping and kernel function of the transformation, and classifying by mapping to a high-dimensional space; solving the sample classification formula according to the KKT optimal condition and the least squares method to obtain the weight vector and the bias vector in the input sample set space, and obtaining the decision amount according to the weight vector and the bias vector; normalizing the decision amount to obtain the consistency coefficient, and the normalization process is: ； ； Among them, represents the consistency coefficient; The data storage module is configured to place the fused data in different containers that are securely isolated according to the task identifiers.

8. A computer-readable storage medium, characterized in that it stores There are multiple instructions, and the instructions are adapted to be loaded and executed by a processor of a terminal device for the steps of the intelligent substation operation and distribution data acquisition and fusion method based on container technology according to any one of claims 1-6.

9. A terminal device, characterized in that: It includes a processor and a computer-readable storage medium. The processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor for the steps of the intelligent substation operation and distribution data acquisition and fusion method based on container technology according to any one of claims 1-6.

Images