Power grid load prediction method based on privacy calculation fusion block chain and related equipment
By adopting privacy computing and blockchain technology in power grid load prediction, the power data is homomorphically encrypted, the problems of data leakage and privacy leakage are solved, and the secure transmission of power data and privacy protection in the prediction process is realized, which is improved. Safety and transparency of grid load forecasts.
Patent Information
- Application Number
- CN202410959007.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-26
AI Technical Summary
Existing grid load prediction methods have the risks of data leakage and privacy leakage, especially during centralized storage and processing of data, and the privacy protection policies of different models are inconsistent, which may lead to vulnerabilities.
Using a method of integrating blockchain based on privacy computing, a blockchain network is established by homomorphic encryption of power data, and each platform node encrypts the power data and uses the encrypted ciphertext data to predict the data. Privacy and secure transmission.
The privacy protection of power data is achieved, ensuring the security and consistency of data in the prediction process, avoiding data leakage and privacy leakage, and improving the security and transparency of grid load prediction.
Smart Images

Figure CN119029841A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the technical field of power grid load management, and in particular, to a power grid load forecasting method and related equipment based on privacy computing and blockchain integration. Background Art
[0002] In relevant power grid load forecasting, user data usually needs to be stored in a single or a few servers, which increases the risk of data leakage. In addition, during the data collection and processing process, if the data is not encrypted or a secure communication protocol is not used, there may be a risk of data interception and monitoring.
[0003] On the other hand, electricity-sensitive data needs to be used as input to the model, which may lead to the leakage of the privacy of electricity users, especially when it is not encrypted, and the model itself may also indirectly leak information. If an attacker has access to the parameters of the model, it is possible to reversely infer data about the individual.
[0004] Furthermore, when using machine learning or artificial intelligence to make predictions, a large amount of data is required for training. If the collection and storage of this data is not properly protected, it may lead to user privacy issues.
[0005] At the same time, other prediction methods often require the use of detailed prior knowledge about data distribution, which may involve privacy leakage issues; and when different models may adopt different privacy protection strategies, integrating these strategies may lead to inconsistencies in privacy protection and even create loopholes. Summary of the invention
[0006] In view of this, the purpose of this application is to propose a power grid load forecasting method and related equipment based on privacy computing and blockchain.
[0007] Based on the above purpose, the present application provides a power grid load forecasting method based on privacy computing and blockchain fusion, which is applied to blockchain, wherein the blockchain includes multiple platform nodes, each platform node includes multiple monitoring sub-nodes; The method includes: Each platform node is required to homomorphically encrypt the acquired power data to obtain multiple ciphertext data; In response to any platform node publishing a load forecasting task in the blockchain, causing other platform nodes to obtain ciphertext data of the platform node that publishes the load forecasting task; Instruct the platform node that obtains the ciphertext data to use the trained load forecasting model to predict the ciphertext data, obtain the result ciphertext, and submit it to the platform node that publishes the load forecasting task; The platform node that issues the load forecasting task is ordered to decrypt the result ciphertext to obtain decrypted load data.
[0008] Furthermore, before each platform node performs homomorphic encryption on the acquired power data, it also includes: Instruct each monitoring sub-node to collect power data; Each platform node is required to obtain power data from the corresponding monitoring sub-nodes.
[0009] Furthermore, after each platform node obtains power data from each corresponding monitoring sub-node, the method further includes: Each platform node is required to fill in the missing values in the acquired power data and normalize the power data.
[0010] Furthermore, before any platform node publishes a load forecasting task in the blockchain, it also includes: Instruct the platform node to obtain historical power data from the corresponding monitoring sub-nodes and perform homomorphic encryption on each historical power data; Use the encrypted historical power data to train the load forecasting model to be trained, and send the trained model parameters to other platform nodes after the training is completed; The other platform nodes receive the model parameters and use the model parameters to train their respective load forecasting models to be trained.
[0011] Further, in response to any platform node publishing a load forecasting task in the blockchain, other platform nodes are instructed to obtain the ciphertext data of the platform node that publishes the load forecasting task, including: In response to any platform node publishing a load forecasting task through a preset smart contract, other platform nodes authenticated by the smart contract are instructed to accept the load forecasting task through the smart contract and download the ciphertext data.
[0012] Further, downloading the ciphertext data includes: Instructing the platform node that issues the load forecasting task to divide the ciphertext data into multiple parts; Each platform node that accepts the load forecasting task obtains a copy of the encrypted data.
[0013] Furthermore, after the platform node that issues the load forecasting task decrypts the result ciphertext, the method further includes: Instructing the platform node that issues the load forecasting task to continuously obtain power data from the corresponding monitoring sub-nodes; According to the difference between the decrypted load data and the continuously acquired circuit data, the parameters of the corresponding load prediction model are adjusted.
[0014] Based on the same inventive concept, the present application also provides a power grid load forecasting device based on privacy computing and blockchain fusion, including: an encryption module, a task interaction module, a prediction module and a decryption module; The encryption module is configured to enable each platform node to perform homomorphic encryption on the acquired power data to obtain a plurality of ciphertext data; The task interaction module is configured to, in response to any platform node publishing a load forecasting task in the blockchain, enable other platform nodes to obtain the ciphertext data of the platform node that publishes the load forecasting task; The prediction module is configured to enable the platform node that obtains the ciphertext data to use the trained load prediction model to predict the ciphertext data, obtain the result ciphertext, and submit it to the platform node that issues the load prediction task; The decryption module is configured to instruct the platform node that issues the load forecasting task to decrypt the result ciphertext to obtain decrypted load data.
[0015] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and run on the processor. When the processor executes the program, it implements the power grid load forecasting method based on privacy computing and blockchain as described in any one of the above.
[0016] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned power grid load forecasting method based on privacy computing and blockchain fusion.
[0017] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the power grid load forecasting method based on privacy computing and blockchain fusion as described in any of the above items.
[0018] From the above, it can be seen that the power grid load forecasting method and related equipment based on privacy computing and blockchain provided by this application are based on the constructed blockchain network, in which each platform node homomorphically encrypts the power data, so that other platform nodes can directly make predictions based on the encrypted ciphertext data, so that the real power data is not involved in the prediction process, thereby realizing the privacy protection of the actual power data, and obtaining the predicted load data by decrypting the predicted ciphertext data, which comprehensively considers the privacy of the power data and the security of the transmission process between platform nodes. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 This is a schematic diagram of the steps of a power grid load forecasting method based on privacy computing and blockchain integration according to an embodiment of the present application; Figure 2 This is a first flow chart of a method for predicting power grid load based on privacy computing and blockchain fusion according to an embodiment of the present application; Figure 3 This is a second flow chart of the power grid load forecasting method based on privacy computing and blockchain fusion according to an embodiment of the present application; Figure 4 This is a schematic diagram of the structure of a power grid load prediction device based on privacy computing and blockchain fusion according to an embodiment of the present application; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0022] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connecting" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0023] As described in the background technology section, the relevant power grid load forecasting methods are still difficult to meet the needs of actual production.
[0024] In the process of implementing this application, the applicant discovered that the main problems with the relevant power grid load forecasting methods are: in the relevant power grid load forecasting, it is usually necessary to store user data in a single or a few servers, which increases the risk of data leakage, and during the data collection and processing, if the data is not encrypted or a secure communication protocol is not used, there may be a risk of data interception and monitoring.
[0025] On the other hand, electricity-sensitive data needs to be used as input to the model, which may lead to the leakage of the privacy of electricity users, especially when it is not encrypted, and the model itself may also indirectly leak information. If an attacker has access to the parameters of the model, it is possible to reversely infer data about the individual.
[0026] Furthermore, when using machine learning or artificial intelligence to make predictions, a large amount of data is required for training. If the collection and storage of this data is not properly protected, it may lead to user privacy issues.
[0027] At the same time, other prediction methods often require the use of detailed prior knowledge about data distribution, which may involve privacy leakage issues; and when different models may adopt different privacy protection strategies, integrating these strategies may lead to inconsistencies in privacy protection and even create loopholes.
[0028] Based on this, one or more embodiments in the present application provide a power grid load forecasting method based on privacy computing and blockchain integration.
[0029] In the embodiment of the application, a power grid of multiple regions is taken as a specific example, wherein each region includes multiple monitoring sub-nodes and is provided with a platform node, which establishes a communication connection with each monitoring sub-node in the region.
[0030] In this embodiment, each monitoring sub-node is equipped with a power data collection device for collecting power data in a sub-area. The power data collection device includes a smart meter for collecting power consumption data of power users or users, such as power load data and corresponding timestamps.
[0031] Furthermore, the power data collection device also includes various sensors for collecting environmental data related to the grid load, such as weather, temperature and humidity data.
[0032] Furthermore, the platform nodes in each region are organized into a blockchain network and serve as nodes in the blockchain network.
[0033] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0034] refer to Figure 1, a power grid load forecasting method based on privacy computing and blockchain fusion in one embodiment of the present application is applied to a blockchain, wherein the blockchain includes a plurality of platform nodes, and each platform node includes a plurality of monitoring sub-nodes; And specifically includes the following steps: Step S101: Instruct each platform node to perform homomorphic encryption on the acquired power data to obtain multiple ciphertext data.
[0035] In an embodiment of the present application, each platform node can obtain multiple power data and encrypt each power data respectively, so as to obtain ciphertext data corresponding to each power data.
[0036] Specifically, Figure 2 As shown, the platform node can send a data request to each monitoring sub-node to enable each monitoring sub-node to collect power data. After each monitoring sub-node collects the power data, the power data is sent to the platform node corresponding to the area.
[0037] Based on this, Figure 2 and Figure 3 As shown, after acquiring various power data, the platform node can pre-process the power data.
[0038] Specifically, the platform node is provided with a preprocessing unit, which can denoise and normalize the collected power data, fill in the missing values in each power data, and filter out the erroneous values in the power data, thereby completing the preprocessing of the power data.
[0039] Based on this, Figure 2 and Figure 3 As shown, the platform node can encrypt the pre-processed power data.
[0040] Specifically, an encryption / decryption unit is also provided in the platform node, and the encryption / decryption unit can perform homomorphic encryption on each pre-processed power data, so as to obtain ciphertext data corresponding to each power data.
[0041] Among them, the ciphertext data obtained through the same-station encryption has the characteristic of being computably invisible, that is, the ciphertext data is calculated using a preset calculation method, and the calculation result is decrypted to obtain the decrypted result data, and the decrypted result data is the same as the calculation result obtained by calculating the unencrypted power data using the same calculation method.
[0042] In a specific embodiment, homomorphic encryption can be, for example, TFHE (fully homomorphic encryption algorithm). The platform node can generate a public key and a private key by using a TFHE library, retain the private key, use the private key to homomorphically encrypt the power data, and distribute the public key to other platform nodes in the blockchain that participate in the composite prediction task.
[0043] Based on this, after encryption, the data format of the ciphertext data is converted into a format supported by TFHE, such as converted into binary ciphertext data. Based on this, the ciphertext data can be securely transmitted to the blockchain network, and the integrity and traceability of the data can be ensured by using the immutability of the blockchain for subsequent processing and analysis.
[0044] In some embodiments, the platform node may also perform desensitization processing on the pre-processed power data before encrypting the power data.
[0045] Specifically, the platform node can use the hash function to perturb the preprocessed power data, thereby generating data that is similar to the real data in statistical characteristics, while avoiding the problem of leaking the real data, thereby protecting privacy.
[0046] In some embodiments, when the platform node performs homomorphic encryption on power data, it can obtain a key from a preset third-party node to encrypt the power data using the key.
[0047] Among them, the third-party node is used to store the keys for homomorphic encryption and decryption, and only allows authorized nodes to access and obtain the keys, thereby ensuring the security of the keys.
[0048] Step S102: In response to any platform node publishing a load forecasting task in the blockchain, other platform nodes are instructed to obtain the ciphertext data of the platform node that publishes the load forecasting task.
[0049] In this embodiment, any platform node is based on the multiple ciphertext data obtained in the above steps, such as Figure 2 and Figure 3 As shown, by publishing the load forecasting task to other platform nodes in the blockchain, other platform nodes can obtain the encrypted data of the platform node that publishes the load forecasting task based on the blockchain.
[0050] Specifically, a smart contract is set up in the blockchain network, and each platform node in the blockchain is also equipped with a distributed ledger to store the ciphertext data obtained in the above steps.
[0051] Furthermore, any platform node can publish load forecasting tasks to other platform nodes in the blockchain through smart contracts.
[0052] Among them, access rules are set in the smart contract, and the download rights of encrypted data can be automatically opened to platform nodes that meet the access rules.
[0053] Based on this, after any platform node publishes a load forecasting task, when other platform nodes request the load forecasting task, the smart contract can automatically verify whether the platform node making the request has the authority to undertake the load forecasting task based on the access rules, and automatically screen out platform nodes without authority, and automatically open the permission to download encrypted data to the platform nodes verified by the smart contract. In other words, after the platform node publishes the load forecasting task, the load forecasting task can be automatically triggered by the smart contract.
[0054] Based on this, platform nodes that have passed authority verification can obtain various ciphertext data from the distributed ledger.
[0055] Step S103: instruct the platform node that obtains the ciphertext data to use the trained load forecasting model to predict the ciphertext data, obtain the ciphertext result, and submit it to the platform node that publishes the load forecasting task.
[0056] In this embodiment, if Figure 2 and Figure 3 As shown, a load forecasting model is also provided in each platform node. Each platform node that accepts the load forecasting task can input the ciphertext data into the trained load forecasting model based on the ciphertext data obtained in the aforementioned steps, and use the trained load forecasting model to perform load forecasting.
[0057] Among them, multiple targets can be predicted, for example, the power consumption within a predetermined period, the highest voltage during power consumption, the highest power, the voltage change rate and the power change rate.
[0058] Among them, operations supported by TFHE can be used to perform calculations on ciphertext data. Since TFHE supports fully homomorphic operations, various mathematical and logical operations, such as four arithmetic operations and comparison operations, can be performed without decrypting the ciphertext data. During this process, the data processor cannot access the actual data content and can only operate the encrypted ciphertext data.
[0059] Furthermore, after the prediction is completed, the result ciphertext is obtained.
[0060] Among them, since each platform node that accepts the load forecasting task uses encrypted data to perform predictions, the results obtained after the prediction is completed are also in an encrypted state rather than in a plaintext state, ensuring the privacy and security of the calculation process.
[0061] Based on this, each platform node that completes the prediction can submit the encrypted result ciphertext to the smart contract, and the smart contract automatically submits the result ciphertext to the platform node that publishes the task, thereby ensuring that the execution of the load forecasting task meets the privacy protection requirements.
[0062] In some embodiments, multiple platform nodes that receive load forecasting tasks may respectively perform forecasting for different objectives.
[0063] Specifically, for example, there are 5 platform nodes that accept load forecasting tasks. The first platform node can predict the power consumption, the second platform node can predict the maximum voltage, the third platform node can predict the maximum power, the fourth platform node can predict the voltage change rate, and the fifth platform node can predict the power change rate.
[0064] Based on this, each platform node can be responsible for a part of the prediction, and after each platform node has completed the prediction, their respective ciphertext results can be aggregated, thereby improving the efficiency of data processing and the speed of load prediction. At the same time, privacy can be increased by dispersing ciphertext data.
[0065] Step S104: instruct the platform node that issues the load forecasting task to decrypt the result ciphertext to obtain decrypted load data.
[0066] In this embodiment, the platform node that issues the load forecasting task decrypts the result ciphertext based on the result obtained in the above steps.
[0067] Among them, since the platform node that publishes the load forecasting task uses homomorphic encryption when encrypting the power data, other platform nodes are allowed to perform calculations directly on the resulting ciphertext without decrypting it first, while ensuring that the calculation results remain correct after decryption, and then the actual predicted load data can be obtained after decryption.
[0068] When the platform node decrypts the power data, it can use the private key retained in the above steps to decrypt the ciphertext data.
[0069] In some other embodiments, when decrypting power data, the platform node may obtain a key from the third-party node mentioned above, and use the key to decrypt the ciphertext data.
[0070] In another embodiment of the present application, after any platform node obtains the predicted load data, it can continue to obtain the actual load data from each corresponding monitoring sub-node.
[0071] Furthermore, the platform node can determine the gap between the predicted load data and the actual load data within a preset period.
[0072] Furthermore, the platform node can publish the gap to the blockchain so that other platform nodes participating in the load forecasting task can obtain the gap, and thus adjust the parameters of the load forecasting model according to the gap to achieve the purpose of continuously optimizing the load forecasting model.
[0073] In another embodiment of the present application, Figure 3 As shown, after the platform node obtains the predicted load data after decryption, it can visualize the load data to facilitate the management of the power grid.
[0074] In another embodiment of the present application, before any platform node issues a load forecasting task, the load forecasting model needs to be trained to obtain a trained load forecasting model.
[0075] Specifically, Figure 2 and Figure 3 As shown, each platform node can obtain historical power data from its own monitoring sub-node and pre-process the historical power data.
[0076] Specifically, the historical power data can be denoised and normalized, and missing values in each historical power data can be filled and erroneous values in the historical power data can be filtered out, thereby completing the preprocessing of the historical power data.
[0077] Based on this, the platform node can perform homomorphic encryption on the preprocessed historical power data to obtain the ciphertext data corresponding to each historical power data.
[0078] Furthermore, the encrypted historical power data is input into the load forecasting model to be trained, and training of the model is started.
[0079] Furthermore, after the load forecasting model of the platform node is trained, the trained model parameters can be sent to other platform nodes in the blockchain.
[0080] Based on this, other platform nodes can use the obtained model parameters to continue training their load forecasting models.
[0081] It can be seen that the power grid load forecasting method based on privacy computing and blockchain fusion in the embodiment of the present application is based on the constructed blockchain network, in which each platform node homomorphically encrypts the power data, so that other platform nodes can directly make predictions based on the encrypted ciphertext data, so that the real power data is not involved in the prediction process, thereby realizing the privacy protection of the actual power data, and obtaining the predicted load data by decrypting the predicted ciphertext data, which comprehensively considers the privacy of the power data and the security of the transmission process between platform nodes.
[0082] On the other hand, by using blockchain to upload and store data, the encrypted ciphertext data is uploaded to the blockchain network. The integrity and traceability of the data are guaranteed based on the tamper-proof nature of the blockchain. The blockchain provides a secure and tamper-proof storage platform for ciphertext data through its chain data structure and consensus algorithm. Once each ciphertext data is added to the blockchain, it cannot be changed or deleted, which provides a strong security guarantee for the ciphertext data and load forecasting results.
[0083] Furthermore, the open and transparent ledger provided by blockchain technology can ensure that all transactions and data changes are publicly queryable, increasing the transparency of system operations. Every data push and access is recorded on the blockchain and can be traced to specific platform nodes, simplifying the investigation process of data errors or abuse.
[0084] Furthermore, load forecasting tasks are automatically executed through blockchain smart contracts. While automatically executing load forecasting tasks, the predicted load data is broadcast to the blockchain network based on homomorphic encryption to ensure the security and fairness of load data, thereby shortening processing time and eliminating the possibility of human error, and achieving the following functions: 1) Automatically execute load forecasting tasks; 2) Automatically update data or execute new load forecasting models when specific conditions are met; 3) Automatically manage and verify the permissions for interacting with related data to ensure data security and compliance.
[0085] Furthermore, by combining blockchain and privacy computing technology, a dual privacy protection mechanism is realized. The transparency and immutability of blockchain ensure the fairness of data processing and transactions, while smart contracts perform necessary operations on the chain without exposing plaintext data, thereby ensuring the confidentiality and integrity of the data.
[0086] Furthermore, the distributed architecture of the blockchain in the embodiments of the present application means that there is no single point of failure, which enhances the system's defense capabilities against network attacks, such as DDoS (distributed denial of service attacks); in addition, through incentive mechanisms, such as cryptocurrency rewards, the participation of nodes is increased, which promotes the health and security of the entire network.
[0087] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.
[0088] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0089] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, an embodiment of the present application also provides a power grid load forecasting device based on privacy computing and blockchain integration.
[0090] refer to Figure 4 The power grid load prediction device based on privacy computing and blockchain integration includes: an encryption module 401, a task interaction module 402, a prediction module 403 and a decryption module 404; The encryption module 401 is configured to enable each platform node to perform homomorphic encryption on the acquired power data to obtain a plurality of ciphertext data; The task interaction module 402 is configured to, in response to any platform node publishing a load forecasting task in the blockchain, enable other platform nodes to obtain the ciphertext data of the platform node that publishes the load forecasting task; The prediction module 403 is configured to enable the platform node that obtains the ciphertext data to use the trained load prediction model to predict the ciphertext data, obtain the result ciphertext, and submit it to the platform node that issues the load prediction task; The decryption module 404 is configured to instruct the platform node that issues the load forecasting task to decrypt the result ciphertext to obtain decrypted load data.
[0091] For the convenience of description, the above devices are described in terms of functions and are divided into various modules. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.
[0092] The device of the above-mentioned embodiment is used to implement the corresponding power grid load forecasting method based on privacy computing and blockchain fusion in any of the aforementioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0093] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the power grid load forecasting method based on privacy computing and blockchain fusion as described in any of the above embodiments.
[0094] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.
[0095] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.
[0096] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solution provided in the embodiment of the present application is implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.
[0097] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0098] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0099] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).
[0100] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiment of the present application, and does not necessarily include all the components shown in the figure.
[0101] The device of the above-mentioned embodiment is used to implement the corresponding power grid load forecasting method based on privacy computing and blockchain fusion in any of the aforementioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0102] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the power grid load forecasting method based on privacy computing and blockchain fusion as described in any of the above embodiments.
[0103] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.
[0104] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the power grid load forecasting method based on privacy computing and blockchain integration as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0105] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the power grid load forecasting method based on privacy computing and blockchain fusion as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.
[0106] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.
[0107] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the well-known power / ground connections to the integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the device may be shown in the form of a block diagram so as to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0108] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.
[0109] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.
Claims
1. A power grid load forecasting method based on privacy computing and blockchain, characterized in that: Applied to a blockchain, the blockchain includes a plurality of platform nodes, each platform node includes a plurality of monitoring sub-nodes; The method includes: Each platform node is required to homomorphically encrypt the acquired power data to obtain multiple ciphertext data; In response to any platform node publishing a load forecasting task in the blockchain, causing other platform nodes to obtain ciphertext data of the platform node that publishes the load forecasting task; Instruct the platform node that obtains the ciphertext data to use the trained load forecasting model to predict the ciphertext data, obtain the result ciphertext, and submit it to the platform node that publishes the load forecasting task; The platform node that issues the load forecasting task is ordered to decrypt the result ciphertext to obtain decrypted load data.
2. The method according to claim 1, characterized in that: Before each platform node is instructed to homomorphically encrypt the acquired power data, the method further includes: Instruct each monitoring sub-node to collect power data; Each platform node is required to obtain power data from the corresponding monitoring sub-nodes.
3. The method according to claim 2, characterized in that After each platform node is instructed to obtain power data from each corresponding monitoring sub-node, the method further includes: Each platform node is required to fill in the missing values in the acquired power data and normalize the power data.
4. The method according to claim 1, characterized in that Before any platform node publishes the load forecasting task in the blockchain, the process further includes: Instruct the platform node to obtain historical power data from the corresponding monitoring sub-nodes and perform homomorphic encryption on each historical power data; Use the encrypted historical power data to train the load forecasting model to be trained, and send the trained model parameters to other platform nodes after the training is completed; The other platform nodes receive the model parameters and use the model parameters to train their respective load forecasting models to be trained.
5. The method according to claim 1, characterized in that In response to any platform node publishing a load forecasting task in the blockchain, enabling other platform nodes to obtain ciphertext data of the platform node that publishes the load forecasting task, including: In response to any platform node publishing a load forecasting task through a preset smart contract, other platform nodes authenticated by the smart contract are instructed to accept the load forecasting task through the smart contract and download the ciphertext data.
6. The method according to claim 5, characterized in that The downloading of the ciphertext data comprises: Instructing the platform node that issues the load forecasting task to divide the ciphertext data into multiple parts; Each platform node that accepts the load forecasting task obtains a copy of the encrypted data.
7. The method according to claim 1, characterized in that After instructing the platform node that issues the load forecasting task to decrypt the result ciphertext, the method further includes: Instructing the platform node that issues the load forecasting task to continuously obtain power data from the corresponding monitoring sub-nodes; According to the difference between the decrypted load data and the continuously acquired circuit data, the parameters of the corresponding load prediction model are adjusted.
8. A power grid load forecasting device based on privacy computing and blockchain, characterized in that: include: Encryption module, task interaction module, prediction module and decryption module; The encryption module is configured to enable each platform node to perform homomorphic encryption on the acquired power data to obtain a plurality of ciphertext data; The task interaction module is configured to, in response to any platform node publishing a load forecasting task in the blockchain, enable other platform nodes to obtain the ciphertext data of the platform node that publishes the load forecasting task; The prediction module is configured to enable the platform node that obtains the ciphertext data to use the trained load prediction model to predict the ciphertext data, obtain the result ciphertext, and submit it to the platform node that issues the load prediction task; The decryption module is configured to instruct the platform node that issues the load forecasting task to decrypt the result ciphertext to obtain decrypted load data.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions for causing a computer to execute the method according to any one of claims 1 to 7.
