Industrial control system database backup method and related device

Through machine learning model optimization, select the backup method of industrial control system database, combined with full backup, incremental backup and differential backup, the problem of difficult to balance backup time and recovery time in the existing technology is solved, and efficient database backup and rapid recovery are achieved. Improves database availability and recoverability.

CN119065897APending Publication Date: 2024-12-03XIAN THERMAL POWER RES INST CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411101402.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing industrial control system database backup method is difficult to find a balance between backup time and recovery time, resulting in low backup efficiency and recovery efficiency, and cannot meet the needs of efficient backup and rapid recovery of large-scale wind farm databases.

Method used

Using a machine learning-based backup method decision model, by obtaining the impact factor of data backup, calling the preset backup method decision model, optimizing the selection of backup method, with the goal of minimum total backup and recovery time, combining full backup, incremental backup and Differential backup and other methods to achieve optimal backup and recovery strategies.

Benefits of technology

It effectively improves the high availability and disaster recovery of the database, shortens the backup and recovery time, and improves the overall efficiency and reliability of the database.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065897A_ABST
    Figure CN119065897A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of data processing, and discloses an industrial control system database backup method and related device.The industrial control system database backup method comprises the steps that data backup influence factors of an industrial control system database in the current time period are obtained; according to the data backup influence factor, calling a preset backup mode decision model to obtain a backup mode of the industrial control system database in the current time period; performing industrial control system database backup in the current time period of the industrial control system database according to the backup mode in the current time period of the industrial control system database; wherein the backup mode decision model takes the minimum sum of backup time and recovery time as an optimization target, takes the data backup influence factor as input and takes the backup mode as output, and is obtained based on machine learning model training. Through the preset backup mode decision model, the backup mode of the industrial control system database in the current time period is optimized and determined, the sum of the backup time and the recovery time is optimal, and the high availability and disaster recoverability of the database are effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the field of data processing and relates to an industrial control system database backup method and related devices. Background Art

[0002] With the growing global demand for renewable energy, wind power technology has developed rapidly, and the scale of wind farm construction has also been expanding. As a key system in wind farm operation and management, the SCADA (Supervisory Control And Data Acquisition) system is responsible for real-time monitoring of the operating status of wind farms, collecting and processing various operating data of wind turbines, and is an important basis for wind farms to achieve efficient and stable operation. However, the database of the SCADA system is often faced with various risks, such as hardware failures, software errors, and network attacks. These risk factors may cause the database data of the SCADA system to be lost or damaged, which will have a serious impact on the normal operation of the wind farm.

[0003] Database backup is usually used to overcome the above problems. Existing database backup methods mainly include full backup, incremental backup and differential backup. Among them, full backup is a method of completely backing up the entire database. This method can ensure the integrity and recoverability of the backup data, but when the amount of data is large, the time and storage space required for backup are large. Incremental backup only backs up the data that has changed since the last backup. This method can save backup time and storage space, but it needs to combine multiple backup files when restoring data, and the recovery process is relatively complicated. Differential backup backs up the data that has changed since the last full backup. This method combines the characteristics of full backup and incremental backup, which can improve backup efficiency while ensuring data integrity.

[0004] However, in practical applications, a single backup method is often difficult to meet the backup needs of the system. On the one hand, the amount of data in the database is usually large, and an efficient data backup strategy is required to ensure timely backup and storage of data; on the other hand, the database also has high requirements for data recovery time. Once the data is lost or damaged, the data needs to be restored as soon as possible. Therefore, a backup method that combines two backups is usually adopted. Among them, the backup strategy that combines full backup with differential backup is characterized by a shorter time to restore data, but a longer backup time is required. The backup strategy that combines full backup with incremental backup is characterized by a shorter time required for backup, but a longer time required for restoring data. Therefore, designing an industrial control system database backup method that can optimize the overall backup and restore time has become an urgent problem to be solved. Summary of the invention

[0005] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide an industrial control system database backup method and related devices.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides an industrial control system database backup method, comprising:

[0008] Obtain the data backup impact factor of the industrial control system database in the current time period;

[0009] According to the data backup influencing factors, the preset backup method decision model is called to obtain the backup method of the industrial control system database in the current time period;

[0010] Backing up the industrial control system database in the current time period of the industrial control system database according to the backup method of the industrial control system database in the current time period;

[0011] Among them, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as input, and takes the backup method as output, and is trained based on the machine learning model.

[0012] Optionally, the data backup influencing factors include one or more of the following:

[0013] Data increment size, data difference change rate, total data volume, and system resource utilization.

[0014] Optionally, the backup mode is a full backup, an incremental backup, a differential backup, a backup mode combining a full backup and a differential backup, or a backup mode combining a full backup and an incremental backup.

[0015] Optionally, the backup mode decision model is trained in the following manner:

[0016] Obtain several training data samples and build a KPCA-SVM decision model;

[0017] A number of training data samples are used to train the KPCA-SVM decision model to obtain a backup mode decision model;

[0018] The training data samples include data backup influencing factors, backup time, recovery time and backup method within a preset time period of the industrial control system database.

[0019] Optionally, the adopting of a plurality of training data samples to train the KPCA-SVM decision model includes:

[0020] After data preprocessing, several training data samples are divided into training data set and test data set;

[0021] Training step: using the training data set to train the KPCA-SVM decision model, and using a cross-validation method to obtain the test effect of the trained KPCA-SVM decision model on the test data set; and modifying the model parameters of the trained KPCA-SVM decision model according to the test effect;

[0022] Repeat the above training steps until the test results meet the preset requirements.

[0023] Optionally, the model parameters include one or more of the following: the kernel function type of the KPCA model, the kernel function coefficient of the KPCA model, the number of eigenvectors of the KPCA model, the error penalty coefficient of the SVM model, the kernel function type of the SVM model, and the kernel function coefficient of the SVM model.

[0024] A second aspect of the present invention provides an industrial control system database backup system, comprising:

[0025] A data acquisition module is used to obtain the data backup influencing factors of the industrial control system database in the current time period;

[0026] The model processing module is used to call the preset backup mode decision model according to the data backup influencing factor to obtain the backup mode of the industrial control system database in the current time period;

[0027] A data backup module, used to back up the industrial control system database in the current time period of the industrial control system database according to the backup method of the industrial control system database in the current time period;

[0028] Among them, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as input, and takes the backup method as output, and is trained based on the machine learning model.

[0029] Optionally, the data backup influencing factors include one or more of the following:

[0030] Data increment size, data difference change rate, total data volume, and system resource utilization.

[0031] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned industrial control system database backup method when executing the computer program.

[0032] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned industrial control system database backup method are implemented.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The industrial control system database backup method of the present invention is based on the data backup influencing factors of the industrial control system database in the current time period, and through a preset backup mode decision model, optimizes and determines the backup mode of the industrial control system database in the current time period. The backup mode decision model takes the minimum sum of backup time and recovery time as the optimization goal, takes the data backup influencing factors as input, takes the backup mode as output, and is obtained based on machine learning model training, thereby achieving the optimal sum of backup time and recovery time, and then backs up the industrial control system database in the current time period of the industrial control system database according to the backup mode of the industrial control system database in the current time period, thereby effectively improving the high availability and disaster recoverability of the database. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The following is a flow chart of a method for backing up a database of an industrial control system according to an embodiment of the present invention.

[0036] Figure 2 The following is a structural block diagram of an industrial control system database backup system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0040] See also Figure 1In one embodiment of the present invention, a method for backing up a database of an industrial control system is provided, which rationally combines three traditional backup methods so that both the backup time and the recovery time can achieve optimal results.

[0041] Specifically, the industrial control system database backup method of the present invention includes the following steps:

[0042] S1: Obtain the data backup impact factor of the industrial control system database in the current time period.

[0043] S2: According to the data backup influencing factors, the preset backup method decision model is called to obtain the backup method of the industrial control system database in the current time period.

[0044] S3: backing up the industrial control system database in the current time period according to the backup method of the industrial control system database in the current time period.

[0045] Among them, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as input, and takes the backup method as output, and is trained based on the machine learning model.

[0046] The industrial control system database backup method of the present invention is based on the data backup influencing factors of the industrial control system database in the current time period, and through a preset backup mode decision model, optimizes and determines the backup mode of the industrial control system database in the current time period. The backup mode decision model takes the minimum sum of backup time and recovery time as the optimization goal, takes the data backup influencing factors as input, takes the backup mode as output, and is obtained based on machine learning model training, thereby achieving the optimal sum of backup time and recovery time, and then backs up the industrial control system database in the current time period of the industrial control system database according to the backup mode of the industrial control system database in the current time period, thereby effectively improving the high availability and disaster recoverability of the database.

[0047] In a possible implementation manner, the data backup influencing factors include one or more of the following: data increment size, data difference change rate, total data volume, and system resource utilization.

[0048] Specifically, the factors affecting data backup refer to factors that affect data backup time and recovery time, generally including data increment size, data difference change rate, total data volume, and system resource utilization. Among them, data increment size refers to how much data increases or decreases within a certain period of time. The larger the data increment, the longer the backup time is usually required, because more data changes need to be processed, and a larger data increment may also increase the size of the backup file, which in turn affects storage and transmission efficiency. The data difference change rate refers to the percentage of data that has changed within a certain period of time to the total data volume. A higher data difference change rate means that more data changes need to be processed during the backup process, which may increase the backup time. In addition, differential backup may be more effective in this case. The total data volume refers to the size of the overall data in the database. The total data volume directly affects the scale of backup and recovery. A larger total data volume usually means longer backup and recovery time. System resource utilization refers to the resource utilization rate used by the system during backup and restore, such as CPU and memory. System resource utilization has a crucial impact on the performance of backup and recovery. High resource utilization will slow down the backup and recovery operations, thereby extending the backup and recovery time.

[0049] In a possible implementation, the backup mode is a full backup, an incremental backup, a differential backup, a backup mode combining a full backup and a differential backup, or a backup mode combining a full backup and an incremental backup.

[0050] Specifically, when selecting the backup method, not only a single backup method is considered, but also a combination of two backup methods is considered, which can fully provide the most suitable backup method for the industrial control system database data in different situations, so as to achieve the optimization of minimizing the total backup time and recovery time.

[0051] In a possible implementation, the backup mode decision model is trained in the following manner: obtaining a number of training data samples and constructing a KPCA-SVM decision model; using a number of training data samples to train the KPCA-SVM decision model to obtain a backup mode decision model; wherein the training data samples include data backup influencing factors, backup time, recovery time and backup methods within a preset time period of the industrial control system database.

[0052] Specifically, the KPCA-SVM decision model is a prediction or classification model that combines a kernel principal component analysis (KPCA) model and a support vector machine (SVM) model.

[0053] The KPCA-SVM decision model first uses the KPCA model to extract nonlinear features from the original data, and then uses these extracted features as input variables of the SVM model to establish a prediction or classification model. The KPCA model uses nonlinear dimensionality reduction technology, which maps data to a high-dimensional feature space so that the original data presents linearly separable characteristics in the new space. Through the KPCA model, nonlinear feature information in the original data can be extracted, which is crucial for subsequent SVM model processing. The SVM model is a supervised learning algorithm model used for classification and regression problems. In the KPCA-SVM decision model, the SVM model is used to process the features extracted by the KPCA model for prediction or classification.

[0054] In this implementation, when the industrial control system database runs smoothly, the time period is one month, and the industrial control system database is backed up and restored in two ways every day. The backup time and recovery time of each backup method are recorded respectively to collect training data samples.

[0055] The training data samples include the daily data backup influencing factors, backup time, recovery time and backup method of the industrial control system database. Among them, the data backup influencing factors are used as input data, and the backup time, recovery time and backup method are used as label determination data to determine the labels of the training data samples. Specifically, the backup method with the shortest total backup time and recovery time is selected as the label of the corresponding data backup influencing factors.

[0056] Optionally, training data sample A1i = {Δi, ψi, Si, ηi, Tci1, Tci2, Tri1, Tri2, B1 or B2}; wherein Δi is the data increment size, ψi is the data difference change rate, Si is the total data amount, ηi is the system resource utilization rate, Tci1 is the backup time of B1, Tci2 is the backup time of B2, Tri1 is the recovery time of B1, Tri2 is the recovery time of B2, B1 is the first backup method, and B2 is the second backup method.

[0057] Optionally, after collecting a number of training data samples, the training data samples are divided into a training data set and a test data set after data preprocessing; training step: using the training data set to train the KPCA-SVM decision model, and using a cross-validation method to obtain the test effect of the trained KPCA-SVM decision model on the test data set; and correcting the model parameters of the trained KPCA-SVM decision model according to the test effect; repeating the above training steps until the test effect meets the preset requirements.

[0058] Among them, data preprocessing generally includes data cleaning, feature value extraction and outlier processing.

[0059] Specifically, each training data sample in the training data set is processed by dimensionality reduction using the KPCA model, mapped to a low-dimensional space, and then the SVM model is used to classify the reduced-dimensional training data samples to determine their corresponding prediction labels. Next, the trained KPCA-SVM decision model is tested and evaluated using a cross-validation method based on the test data set to determine whether the test effect meets the preset requirements, and if the test effect does not meet the preset requirements, the model parameters are modified according to the test effect.

[0060] In this embodiment, the model parameters to be adjusted include the kernel function type of the KPCA model, the kernel function coefficient of the KPCA model, the number of eigenvectors of the KPCA model, the error penalty coefficient of the SVM model, the kernel function type of the SVM model, and the kernel function coefficient of the SVM model, etc. By adjusting the model parameters, the decision performance of the backup mode decision model can be further improved.

[0061] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0062] See also Figure 2 In another embodiment of the present invention, an industrial control system database backup system is provided, which can be used to implement the above-mentioned industrial control system database backup method. Specifically, the industrial control system database backup system includes a data acquisition module, a model processing module and a data backup module.

[0063] Among them, the data acquisition module is used to obtain the data backup influencing factor of the industrial control system database in the current time period; the model processing module is used to call the preset backup method decision model according to the data backup influencing factor to obtain the backup method of the industrial control system database in the current time period; the data backup module is used to back up the industrial control system database in the current time period according to the backup method of the industrial control system database in the current time period; wherein, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as the input, and takes the backup method as the output, and is obtained based on machine learning model training.

[0064] In a possible implementation manner, the data backup influencing factors include one or more of the following: data increment size, data difference change rate, total data volume, and system resource utilization.

[0065] All relevant contents of each step involved in the aforementioned embodiment of the industrial control system database backup method can be referred to the functional description of the functional module corresponding to the industrial control system database backup system in the embodiment of the present invention, and will not be repeated here.

[0066] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0067] In another embodiment of the present invention, a computer device is provided, the computer device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor 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 gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the industrial control system database backup method.

[0068] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the computer device and the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the industrial control system database backup method in the above embodiment.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for backing up a database of an industrial control system, characterized in that: include: Obtain the data backup impact factor of the industrial control system database in the current time period; According to the data backup influencing factors, the preset backup method decision model is called to obtain the backup method of the industrial control system database in the current time period; Backing up the industrial control system database in the current time period of the industrial control system database according to the backup method of the industrial control system database in the current time period; Among them, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as input, and takes the backup method as output, and is trained based on the machine learning model.

2. The industrial control system database backup method according to claim 1, characterized in that: The data backup influencing factors include one or more of the following: Data increment size, data difference change rate, total data volume, and system resource utilization.

3. The industrial control system database backup method according to claim 1, characterized in that: The backup mode is a full backup, an incremental backup, a differential backup, a backup mode combining a full backup and a differential backup, or a backup mode combining a full backup and an incremental backup.

4. The industrial control system database backup method according to claim 1, characterized in that: The backup mode decision model is trained in the following way: Obtain several training data samples and build a KPCA-SVM decision model; A number of training data samples are used to train the KPCA-SVM decision model to obtain a backup mode decision model; The training data samples include data backup influencing factors, backup time, recovery time and backup method within a preset time period of the industrial control system database.

5. The industrial control system database backup method according to claim 4, characterized in that: The use of a plurality of training data samples to train the KPCA-SVM decision model comprises: After data preprocessing, several training data samples are divided into training data set and test data set; Training step: using the training data set to train the KPCA-SVM decision model, and using a cross-validation method to obtain the test effect of the trained KPCA-SVM decision model on the test data set; and modifying the model parameters of the trained KPCA-SVM decision model according to the test effect; Repeat the above training steps until the test results meet the preset requirements.

6. The industrial control system database backup method according to claim 5, characterized in that: The model parameters include one or more of the following: a kernel function type of a KPCA model, a kernel function coefficient of a KPCA model, the number of eigenvectors of a KPCA model, an error penalty coefficient of an SVM model, a kernel function type of an SVM model, and a kernel function coefficient of an SVM model.

7. An industrial control system database backup system, characterized in that: include: A data acquisition module is used to obtain the data backup influencing factors of the industrial control system database in the current time period; The model processing module is used to call the preset backup mode decision model according to the data backup influencing factor to obtain the backup mode of the industrial control system database in the current time period; A data backup module, used to back up the industrial control system database in the current time period of the industrial control system database according to the backup method of the industrial control system database in the current time period; Among them, the backup method decision model takes the minimization of the sum of backup time and recovery time as the optimization goal, takes the data backup influencing factor as input, and takes the backup method as output, and is trained based on the machine learning model.

8. The industrial control system database backup system according to claim 7, characterized in that: The data backup influencing factors include one or more of the following: Data increment size, data difference change rate, total data volume, and system resource utilization.

9. A computer 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, the steps of the industrial control system database backup method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the industrial control system database backup method according to any one of claims 1 to 6 are implemented.