Generation data timing sequence-based secure storage method

Abstract

The invention discloses a power generation data timing sequence secure storage-based method, which comprises the following steps of: generating a corresponding task description process based on a task requirement of a server terminal; judging whether the task description process is empty or not; if yes, the process is ended; otherwise, transmitting the task description process to the data acquisition end; based on the task description process, generating security data corresponding to the power generation data; and transmitting the security data to a server terminal. And by introducing a task description process and a security data generation mechanism, the original data is not directly transmitted to the server terminal any more, but only the processed result or abnormal data is transmitted, so that the security of the data is effectively guaranteed, and sensitive data leakage is prevented.

Description

Technical Field

[0001] The present invention relates to the field of data security storage, and more specifically, to a method for secure storage of power generation data in chronological order. Background Art

[0002] In the modern power generation field, with the wide application of intelligent and automated devices, the collection, storage, and processing of power generation data have become important means to improve power generation efficiency, optimize scheduling, and ensure equipment safety. Power generation data is usually collected in real time through various sensors and monitoring devices, covering multiple dimensions closely related to power production and equipment operation, including information such as power, voltage, current, frequency of generator output power, equipment temperature, wind speed / solar irradiance, etc. Since the data during the power generation process has chronological characteristics, it is usually collected at preset time intervals and forms chronological data.

[0003] Traditional power generation data storage methods usually directly transmit this chronological data to a server for storage and processing. However, with the continuous increase in data volume and the improvement of data security requirements, traditional data storage methods can no longer meet the complex requirements of the current power generation system, especially in terms of data security, privacy protection, and the application of intelligent analysis, facing a series of technical challenges.

[0004] During the storage, transmission, and processing of power generation data, different types of server terminals (such as modules for optimization scheduling, fault warning, and data storage, etc.) have different security level requirements. For example, the optimization scheduling module may only need to analyze and predict based on pre-processed power generation data; while the storage module requires complete original data for long-term storage. How to ensure the security and privacy of data during data transmission between different modules and avoid the leakage of original data is an important problem currently faced. Summary of the Invention

[0005] The purpose of the present invention is to solve the above-mentioned defects, and further propose a method for secure storage of power generation data in chronological order.

[0006] The present invention adopts the following technical solutions.

[0007] The first aspect of the present invention discloses a method for secure storage of power generation data in chronological order, including Step 1 to Step 4; Step 1, generate a corresponding task description process based on the task requirements of the server terminal; Step 2, determine whether the task description process is empty; if it is empty, end the process; otherwise, transmit the task description process to the data acquisition end; Step 3, generate secure data corresponding to the power generation data based on the task description process; Step 4, transfer the security data to the server terminal.

[0008] Further, Step 1 specifically includes Step 1.1 to Step 1.2; Step 1.1, create a template object, including: a first object and a second interface; generate an instance object of the template object based on the task requirements of the server terminal; Step 1.2, rewrite the second interface of the instance object and use it as the task description process.

[0009] Further, the data acquisition end creates a pointer to the template object to automatically adapt to the category of the instance object itself.

[0010] Further, Step 2 specifically includes Step 2.1 to Step 2.3 Step 2.1, judge the input parameters of the second interface. If the input parameter is a single power generation data, it is determined that the task description process is not empty, and the step ends; if the input parameter is not time-series power generation data, it is determined that the task description process is empty, and the step ends; Step 2.2, if the input parameter is time-series power generation data, perform sample expansion on the time-series power generation data to obtain multiple reference sample data; Step 2.3, compare the output result of the time-series power generation data passing through the second interface and the output results of multiple reference sample data passing through the second interface, and determine whether the task description process is empty.

[0011] Further, Step 2 specifically includes: for each element in a piece of time-series power generation data, perform addition, deletion, and modification on it to obtain a total of 3N + 1 pieces of reference sample data; where N is the length of the time-series power generation data; And Step 3 specifically includes: Step 3.1 to Step 3.3; Step 3.1, set the marking parameter k = 1; Step 3.2, compare the output result of the time-series power generation data passing through the second interface and the output results of multiple reference sample data passing through the second interface; if there are the same output results among all the above output results, let k = k + 1; Step 3.3, perform Steps 2 and 3.2 independently multiple times. If k = N, it is determined that the task description process is empty; otherwise, the task description process is not empty; where N is the number of executions.

[0012] Further, Step 2 specifically includes Step S21 to Step S22, and Step 3 includes Step S31 to Step S33; Step S21, use the time-series power generation data as the input and the output of the time-series power generation data passing through the second interface as the output to train the clustering algorithm model; Step S22: Determine the upper and lower limits of each element in the time - sequenced power generation data, and change each element to obtain a total of 2N pieces of reference sample data; Step S31: Use the output result of the time - sequenced power generation data and the 2N pieces of reference sample data through the second interface as the first output result, and again use the output result of the time - sequenced power generation data and the 2N pieces of reference sample data directly obtained via the server terminal as the second output result, and again use the output result of the time - sequenced power generation data and the 2N pieces of reference sample data directly obtained via the server terminal as the third output result; Step S32: Independently execute Steps 2 and S31 multiple times, and respectively obtain the first similarity and the second similarity; wherein, the first similarity is the similarity between the first output result and the second output result, and the second similarity is the similarity between the second output result and the third output result; Step S33: If the difference between the first similarity and the second similarity is greater than a preset threshold, it is determined that the task description process is empty; otherwise, the task description process is not empty.

[0013] Further, the preset threshold is 0.

[0014] The second aspect of the present invention discloses a system for secure storage based on time - sequencing of power generation data, which is applied to the method described in the first aspect. The system includes: a server terminal and a data acquisition terminal; The server terminal is used to generate a corresponding task description process based on task requirements; and determine whether the task description process is empty; if it is empty, end the process; otherwise, transmit the task description process to the data acquisition terminal; The data acquisition terminal is used to generate secure data corresponding to the power generation data based on the task description process; and transmit the secure data to the server terminal.

[0015] The third aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0016] The fourth aspect of the present invention discloses a computer - readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the steps of the method described in the first aspect.

[0017] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention has the following advantages: (1) Improve data security: By introducing a task description process and a secure data generation mechanism, the original data is no longer directly transmitted to the server terminal. Instead, only the processed results or abnormal data are transmitted, thus effectively ensuring data security and preventing the leakage of sensitive data.

[0018] (2) Implement differential data permission control: Since the task requirements of the server terminals are different, the system will generate corresponding data transmission schemes according to the specific tasks of each module. This enables each server terminal to only access the data it needs, avoiding unnecessary permission leakage.

[0019] (3) Improve data processing efficiency: By screening and preprocessing power generation data, only the useful secure data is transmitted to the server terminal, reducing the transmission of useless data and improving data processing and storage efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a flowchart of the method for time-sequential secure storage of power generation data according to an embodiment of the present invention.

[0022] Figure 2 It is a flowchart of the first transmission of power generation data according to an embodiment of the present invention.

[0023] Figure 3 It is a flowchart of the second transmission of power generation data according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0025] Power generation data refers to various data related to power production and equipment operation collected during the power generation process. These data are usually collected in real time by sensors or monitoring devices and cover multiple aspects such as power, equipment status, electrical parameters, etc. Common power generation data includes but is not limited to the following: power generation power, voltage, current, frequency of the generator output power, equipment temperature, wind speed / solar irradiance, and so on. Sequentialization means that these power generation data will be recorded in a time series. Usually, the sensors for collecting power generation data will collect data once at a preset time interval t. When a certain amount of data is collected, it will be packaged together by the data acquisition end and sent to the server terminal.

[0026] It can be understood that the data acquisition ends are often distributed on different devices, and the number of server terminals can also be multiple according to their functions. Different server terminals should be understood as serving different project requirements, and their security permissions for power generation data are also different. For example: If server terminal 1 is a storage module, then its security permission is the highest and it is used to store the most original power generation data; if server terminal 2 is an optimization scheduling module, then its security level is the second. The optimization scheduling module is based on the serialized power generation data and combines specific deep learning algorithms or machine learning algorithms to output relevant conclusions; if server terminal 3 is a fault warning module, then its security level is the lowest. Usually, after preliminary screening by the data acquisition end, only the abnormal power generation data is sent to the server terminal for storage for subsequent abnormal data troubleshooting work. It can be understood that this is completely different from the conventional method of sequential storage of power generation data (directly transmitting power generation data from the data acquisition end to the server terminal).

[0027] Based on this, the present invention discloses a method for secure storage based on the sequentialization of power generation data, as Figure 1 shown, including Step 1 to Step 4; Step 1, generate a corresponding task description process based on the task requirements of the server terminal.

[0028] Step 2, determine whether the task description process is empty; if it is empty, end the process; otherwise, transmit the task description process to the data acquisition end.

[0029] Step 3, generate secure data corresponding to the power generation data based on the task description process.

[0030] Step 4, transfer the secure data to the server terminal.

[0031] In Embodiment A, if the task requirement of the server terminal is optimization scheduling, for example, its core code is as follows: # Dataset partitioning X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42); # Initialize the model: Random Forest Regressor model = RandomForestRegressor(n_estimators=100, random_state=42); # Train the model model.fit(X_train, y_train); # Predict the scheduling results y_pred = model.predict(X_test); # Evaluate the model performance mse = mean_squared_error(y_test, y_pred); It is understandable that the essence of optimizing the scheduling is actually to first divide the power generation data (e.g., variable X) into data sets, then train the model, and finally obtain the predicted scheduling results (e.g., y_pred). For the security consideration of the original power generation data, only the final scheduling results need to be sent to the server terminal to achieve the encryption protection of the original power generation data.

[0032] In Embodiment B, if the task requirement of the server terminal is fault warning, for example, its core code is as follows: # Define simple fault warning logic: Trigger a warning if any sensor data exceeds the threshold int check_fault(X) { d, pressure = X; if d>temperature_threshold or pressure>pressure_threshold: return 1; # Fault else: return 0; # Normal } result = check_fault(data); warning = 'Fault Detected' if result == 1 else 'Normal'; print(f"Sensor : {warning}; Understandably, the essence of the fault warning is actually to perform numerical detection on the power generation data (e.g., variable X) (e.g., threshold judgment), and based on the detection output, the final judgment result is formed, and the final warning information (e.g., warning) is generated.

[0033] In order to conveniently generate the corresponding task description process from the task requirements of the server terminal, it is necessary that the design of each task requirement follows the corresponding template, so that the server terminal can automatically analyze its corresponding task description process. Based on this, step 1 specifically includes steps 1.1 to 1.2.

[0034] Step 1.1: Create a template object, including: a first object and a second interface; based on the task requirements of the server terminal, generate an instance object of the template object.

[0035] Understandably, the template object can be as shown in the following code: template<typename Ti, To> class TaskDesp { private: Ti X public: To GetData(Ti) { … return y; } } Step 1.2: Rewrite the second interface of the instance object and use it as the task description process.

[0036] It should be noted that when the task is executed for the first time, it is necessary to determine the type information based on the power data to be collected, so as to ensure that the input values Ti and To of the second interface are accurate. Therefore, the data acquisition end will randomly generate some template data of the same type but with tampered numerical values according to the actual power data and send it to the server terminal to assist in generating the task description process. In subsequent data transmissions, similar steps are not required again, as Figure 2 shown in Figure 3 and

[0037] The first object can be the above-mentioned X, and the second interface can be the above-mentioned GetData.

[0038] It can be understood that the data y returned by GetData is the security data described in step 3.

[0039] The generated instance objects (e.g., OptimizeSche of Example A or FaultWarn of Example B) need to inherit from the template object.

[0040] The following shows the rewritten code of Example A.

[0041] class OptimizeSche : public TaskDesp<Ti, To>{ public: / / Override the GetData method of the parent class to provide a different implementation To GetData(Ti input) override { X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42); model = RandomForestRegressor(n_estimators=100, random_state=42) ; model.fit(X_train, y_train) ; y_pred = model.predict(X_test) ; return y_pred; } }; # Generate an instance object inst_A of TaskDesp and call the second interface y_pred = dynamic_cast<TaskDesp *>(&inst_A)->GetData(X) ; # Evaluate the model performance mse = mean_squared_error(y_test, y_pred) ; The following shows the rewritten code of Example B.

[0042] class FaultWarn: public TaskDesp<Ti, To>{ public: / / Override the GetData method of the parent class to provide a different implementation To GetData(Ti input) override { d, pressure = X; result = 0; # Normal if d>temperature_threshold or pressure>pressure_threshold: result = 1; # Fault return 'Fault Detected' if result == 1 else 'Normal'; } }; # Generate an instance object inst_B of TaskDesp and call the second interface warning = dynamic_cast<TaskDesp *>(&inst_B)->GetData(X); print(f"Sensor: {warning}; It can be understood that in this case, the data acquisition end only needs to create a pointer to the template object and make it automatically adapt to the category of the instance object itself based on dynamic_cast, without paying attention to the specific implementation details, thus realizing the secure encapsulation of data.

[0043] However, not all task requirements meet the conditions of inheriting from the said template object. If the task requirements themselves are not discriminated, the generated task description process is very likely to be incorrect.

[0044] For example: Suppose the actual real input of the task requirement is to statistically calculate the median or mode of the power generation data over a certain period of time (non - continuous time or a time period that is too long), then the corresponding task description process cannot be generated, that is, the task description process can only be empty.

[0045] It should be noted that for almost all task requirements, the input from the interface level is time - series power generation data (i.e., the input parameter of GetData). However, its internal logic is a black box, and it is unknown whether its final output result (i.e., the output result of GetData) completely depends on all the input data. Therefore, how to determine the actual real input of the task requirement is the core of the present invention.

[0046] More specifically, step 2 specifically includes steps 2.1 to 2.3.

[0047] Step 2.1: Determine the input parameter of the second interface. If the input parameter is a single power generation data, it is determined that the task description process is not empty, and the step ends; if the input parameter is not time-series power generation data, it is determined that the task description process is empty, and the step ends.

[0048] It is not difficult to understand that based on the internal logic of GetData in FaultWarn, the task requirements of the fault warning in the embodiments of the present invention are essentially to judge each time-series data one by one, which conforms to the situation where the input parameter is a single power generation data. Therefore, its actual real input is each time-series power generation data.

[0049] Step 2.2: If the input parameter is time-series power generation data, perform sample expansion on the time-series power generation data to obtain multiple reference sample data.

[0050] Step 2.3: Compare the output result of the time-series power generation data passing through the second interface and the output results of multiple reference sample data passing through the second interface to determine whether the task description process is empty.

[0051] Assume that the internal logic of GetData in FaultWarn is not visible. In some embodiments, the following method can be used for judgment.

[0052] Specifically, in the first embodiment, Step 2 specifically includes: for each element in a piece of time-series power generation data, perform addition, deletion, and modification on it to obtain a total of 3N + 1 reference sample data; where N is the length of the time-series power generation data; and Step 3 specifically includes: Steps 3.1 to 3.3.

[0053] Step 3.1: Set the marking parameter k = 1.

[0054] Step 3.2: Compare the output result of the time-series power generation data passing through the second interface and the output results of multiple reference sample data passing through the second interface; if there are the same output results among all the above output results, let k = k + 1.

[0055] It can be understood that all the above output results include the data result itself of the time-series power generation data, that is, a total of 3N + 2 output results.

[0056] Step 3.3: Independently execute Step 2 and Step 3.2 multiple times. If k = N, it is determined that the task description process is empty; otherwise, the task description process is not empty; where N is the number of executions.

[0057] It is understandable that assuming the time - sequenced power generation data is {d[0], d[1], d[2], d[3]}, the transformations of addition, deletion, and modification for an element (such as d[1]) can be respectively: {d[0], d[2], d[3]}, {d[0], d[1], d, d[2], d[3]}, {d[0], d, d[2], d[3]}. Among them, d can be selected as the average value of other values after removing d[1], and it is ensured that d is not equal to d[1]. It is understandable that for the element d[0], d can also be added to the front of d[0]. Therefore, there are a total of 3N + 1 reference sample data.

[0058] However, for the vast majority of task requirements involving deep - learning algorithms or machine - learning algorithms (such as the task requirement of optimal scheduling), in these scenarios, the internal logic of GetData is full of random settings. That is to say, even for the same input, the output each time is not the same, because the output of the algorithm is essentially a probability game, subject to factors such as the number of executions, and even internal random parameters and initialization parameters. More critically, since developers cannot build from scratch, the internal logic of GetData must call functions from a certain third - party package, and the functions of this third - party package may contain a large amount of code, and whether it is open - source is unknown.

[0059] Based on this, in the second embodiment, step 2 specifically includes steps S21 to S22, and step 3 includes steps S31 to S33.

[0060] Step S21: Taking the time - sequenced power generation data as the input and the output of the time - sequenced power generation data through the second interface as the output, training a clustering algorithm model.

[0061] In some embodiments, the clustering algorithm model can be the K - means clustering algorithm.

[0062] Step S22: Determining the upper limit value and the lower limit value of each element in the time - sequenced power generation data, and changing each element, obtaining a total of 2N reference sample data.

[0063] Step S31: Taking the output results of the time - sequenced power generation data and the 2N reference sample data through the second interface together as the first output result, and again taking the output results of the time - sequenced power generation data and the 2N reference sample data directly obtained through the server terminal together as the second output result, and again taking the output results of the time - sequenced power generation data and the 2N reference sample data directly obtained through the server terminal together as the third output result.

[0064] It is understandable that in step S31, the essence of the second output result and the third output result is to eliminate randomization. If the second output result is always equal to the third output result, the method mentioned in the first embodiment can be adopted.

[0065] Step S32: Independently execute step 2 and step S31 multiple times, and obtain the first similarity and the second similarity respectively; wherein, the first similarity is the similarity between the first output result and the second output result, and the second similarity is the similarity between the second output result and the third output result.

[0066] As an example, the first similarity o_X1X2 can be shown as follows: o_X1X2=(cov(X1,X2)) / (σ_X1 σ_X2 ) Wherein, σ_X1 and σ_X2 are the sample standard deviations of X1 and X2 respectively. X1 is a vector with a length equal to the number of executions in step S32, and each element x1 therein is the first output result of a certain execution; similarly, X2 is a vector with a length equal to the number of executions in step S32, and each element x2 therein is the second output result of a certain execution.

[0067] Step S33: If the difference between the first similarity and the second similarity is greater than a preset threshold, it is determined that the task description process is empty; otherwise, the task description process is not empty.

[0068] Among them, the preset threshold must be a positive number, and it can be set based on the error value of the first similarity itself. That is to say, in practice, multiple second output results or third output results can be generated, and the "average" error of the similarity between them is used as the preset threshold.

[0069] It should be understood that among all neural network algorithms, different from the motivation of GetData in OptimizeSche, the clustering motivation of the K-means clustering algorithm is necessarily the strongest. Even the purpose of GetData in OptimizeSche is not for clustering at all. For example, the purpose of GetData in OptimizeSche in Embodiment A is to optimize scheduling. Therefore, generally speaking, the value of the second similarity is almost certainly greater than the first similarity. Therefore, the preset threshold can essentially be set to 0.

[0070] Correspondingly, the present invention also discloses a system for time-sequential secure storage of power generation data, including: a server terminal and a data acquisition terminal.

[0071] The server terminal is used to generate a corresponding task description process based on task requirements; and determine whether the task description process is empty; if it is empty, end the process; otherwise, transmit the task description process to the data acquisition end.

[0072] The data acquisition end is used to generate security data corresponding to power generation data based on the task description process; and transmit the security data to the server terminal.

[0073] The present disclosure may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0074] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punch card or raised structures in a groove having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0075] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. The network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0076] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0077] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer - readable program instructions.

[0078] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine, such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, create a means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions comprises a manufacture, which includes instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0079] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0080] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for secure storage of power generation data based on time series, characterized in that: Including step 1 to step 4; Step 1: Generate a corresponding task description process based on the task requirements of the server terminal; Step 2, determine whether the task description process is empty; if it is empty, end the process; Otherwise, the task description process is transmitted to the data collection end; Step 3: Generate safety data corresponding to power generation data based on the task description process; Step 4: Pass the security data to the server terminal.

2. A method for secure storage based on time series of power generation data according to claim 1, characterized in that: Step 1 specifically includes step 1.1 to step 1.2; Step 1.1, creating a template object, including: a first object and a second interface; generating an instance object of the template object based on the task requirements of the server terminal; Step 1.2, rewrite the second interface of the instance object and use it as the task description process.

3. A method for secure storage based on time series of power generation data according to claim 2, characterized in that: The data collection end creates a pointer to the template object to automatically adapt to the category of the instance object itself.

4. A method for secure storage based on time series of power generation data according to claim 2, characterized in that: Step 2 specifically includes steps 2.1 to 2.3; Step 2.1, judging the input parameter of the second interface, if the input parameter is a single power generation data, judging that the task description process is not empty, and ending the step; if the input parameter is not a time-series power generation data, judging that the task description process is empty, and ending the step; Step 2.2, if the input parameter is time-series power generation data, perform sample expansion on the time-series power generation data to obtain multiple reference sample data; Step 2.3, comparing the output result of the time-series power generation data through the second interface and the output results of multiple reference sample data through the second interface, and determining whether the task description process is empty.

5. A method for secure storage based on time series of power generation data according to claim 2, characterized in that: Step 2 specifically includes: based on each element in a time-series power generation data, adding, deleting and modifying it, and obtaining 3N+1 reference sample data in total; wherein N is the length of the time-series power generation data; And step 3 specifically includes: step 3.1 to step 3.3; Step 3.1, set the marking parameter k=1; Step 3.2, comparing the output result of the time-series power generation data through the second interface and the output results of multiple reference sample data through the second interface; if all the above output results have the same output result, set k=k+1; Step 3.3, execute step 2 and step 3.2 independently multiple times. If k=N, the task description process is determined to be empty; otherwise, the task description process is not empty; wherein N is the number of executions.

6. A method for secure storage based on time series of power generation data according to claim 2, characterized in that: Step 2 specifically includes step S21 to step S22, and step 3 includes step S31 to step S33; Step S21, taking the time-series power generation data as input and the output of the time-series power generation data via the second interface as output, training a clustering algorithm model; Step S22, determining the upper limit and lower limit of each element in the time-series power generation data, and modifying each element to obtain 2N reference sample data in total; Step S31, the output result of the time-series power generation data and the 2N reference sample data through the second interface is taken as the first output result, and the output result of the time-series power generation data and the 2N reference sample data directly obtained through the server terminal is taken as the second output result, and the output result of the time-series power generation data and the 2N reference sample data directly obtained through the server terminal is taken as the third output result; Step S32, executing step 2 and step S31 independently for multiple times, and obtaining a first similarity and a second similarity respectively; wherein the first similarity is the similarity between the first output result and the second output result, and the second similarity is the similarity between the second output result and the third output result; Step S33: if the difference between the first similarity and the second similarity is greater than a preset threshold, it is determined that the task description process is empty; otherwise, the task description process is not empty.

7. A method for secure storage based on time series of power generation data according to claim 6, characterized in that: The preset threshold is 0.

8. A system based on time-series secure storage of power generation data, characterized in that: The system is applied to the method described in any one of claims 1 to 7, and the system comprises: a server terminal and a data acquisition terminal; The server terminal is used to generate a corresponding task description process based on the task requirements; and determine whether the task description process is empty; if it is empty, end the process; otherwise, transmit the task description process to the data acquisition terminal; The data acquisition terminal is used to generate safety data corresponding to the power generation data based on the task description process; and transmit the safety data to the server terminal.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images