Electric power data processing method and system based on homomorphic encryption and medium

Abstract

The invention discloses an electric power data processing method and system based on homomorphic encryption and a medium, and belongs to the technical field of information security and intelligent power grids, and the method comprises the following steps: carrying out data partitioning on electric power data according to a time sequence at a client, and carrying out fully homomorphic encryption on the electric power data after data partitioning by using an encryption public key to obtain ciphertext data, sending the ciphertext data to a server side; processing the ciphertext data from the client in an encrypted state at the server side to obtain a processing result, and storing the processing result in a database of the server side; and the processing result is returned to the client according to requirements, and the client performs fully homomorphic decryption by using the decryption private key to obtain the processing result in the plaintext state. According to the method, the server can process and store the data in the ciphertext state under the condition that the server does not acquire the original information of the data, so that the safety and reliability of the power data are ensured, and the privacy of a user can be effectively protected.

Description

Technical Field

[0001] The present invention relates to the technical fields of information security and smart grid, and more particularly to a power data processing method, system and medium based on homomorphic encryption. Background Art

[0002] At present, the smart grid is developing rapidly, and power companies can collect a large amount of user power consumption data for power preference analysis, load forecasting and service optimization; for example, using big power data to manage charging demand and energy supply, so as to formulate a reasonable power dispatching plan. However, these data may contain users' privacy information, and directly using the original data for calculation may lead to the leakage of users' privacy. For example, there are risks of leakage of privacy data such as users' locations, when users go home, and whether users are traveling. However, with the development of the mobile Internet, more and more storage and calculations are completed on cloud servers, and the storage and processing of the massive data generated by power users are also outsourced by service providers to cloud platforms. Under the cloud platform, external attacks or internal malicious leaks will threaten the privacy and security of power data, resulting in the public or unauthorized third parties being able to obtain relevant data.

[0003] Therefore, how to ensure the security and reliability of users' power data and effectively protect users' privacy is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention provides a power data processing method, system and medium based on homomorphic encryption that at least solves the above partial technical problems, which is beneficial to ensuring the security and reliability of users' power data during transmission, processing and storage, and can effectively protect users' privacy.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] In the first aspect, the present invention provides a power data processing method based on homomorphic encryption, and the method includes the following steps:

[0007] S1. At the client side, power data is block-divided according to a time series, and the block-divided power data is fully homomorphically encrypted using an encryption public key to obtain ciphertext data, and then the ciphertext data is sent to the server side;

[0008] S2. At the server side, the ciphertext data from the client is processed in an encrypted state to obtain a processing result, and the processing result is stored in the database of the server side;

[0009] S3. According to requirements, the processing result is returned to the client, and the client performs full homomorphic decryption using a decryption private key to obtain the processing result in plaintext state.

[0010] Preferably, in S1, the power data is encrypted homomorphically in full to obtain ciphertext data by using the modulo component method. The process includes:

[0011] 1) Randomly generate a projection basis S = {s1, s2,..., s n} and a position basis P = {p1, p2,..., p n} according to the encryption public key; among them, the projection basis S is used to split the original data, and the elements in the projection basis S are relatively prime to each other; the position basis P is used to insert the real modulo components;

[0012] 2) Split the power data D into a set of real modulo components d: split the power data D by using the projection basis S, and perform modulo operations on the elements in the projection basis S respectively to obtain the set of real modulo components d = {d1, d2,..., d n}; d i = Dmods i , i = 1, 2,... n; mod is an operator that supports homomorphic operations;

[0013] 3) Generate a redundancy set R based on the set of real modulo components d: generate n redundancy vectors each containing j redundant terms according to the values of the elements in the set of real modulo components d = {d1, d2,..., d n} to obtain the redundancy set R = {R1, R2,..., R n}; among them, R i = {R i1 , R i2 ,..., R ij}, i = 1, 2,..., n, and j is the number of redundant terms used to confuse the redundancy vector;

[0014] 4) Generate ciphertext data C: insert the real modulo components into the redundancy set R respectively, and use the position basis P to replace the elements corresponding to the original positions of the redundancy set R in turn with the elements in the set of real modulo components d according to the insertion positions represented by the elements in the position basis P to obtain the ciphertext data C, C = {C1, C2,..., C n}, C i = {C i1 , C i2 ,..., C pi ..., C ij} = {R i1 , R i2 ,..., dp i ,..., R ij}, i = 1, 2,..., n; that is, C i is the real modulo component d i replacing the redundancy vector R ithe p-th among the j redundant items i modular component vector after the p-th redundant item i where p is the position of the true modular component.

[0015] Preferably, in S1, the original power data is normalized before encryption.

[0016] Preferably, in S1, independent random noise is added to the power data after data chunking during the encryption process.

[0017] Preferably, in S2, the server uses a power prediction model based on deep learning to perform computational processing on the ciphertext data to obtain the power load prediction result of the user; the power prediction model includes a convolutional neural network, a BiLSTM neural network, and an attention mechanism layer.

[0018] Preferably, in S2, the database on the server side uses full ciphertext storage, and the data in the database is stored in the form of modular components. All data is in ciphertext state, and each ciphertext data has a unique identifier to distinguish different ciphertext data.

[0019] In a second aspect, the present invention also provides a power data processing system based on homomorphic encryption, which is applied to the above-mentioned power data processing method based on homomorphic encryption. The system includes: a client and a server, where:

[0020] At the client, the power data is chunked by time series, and the power data after data chunking is fully homomorphically encrypted using the encryption public key to obtain ciphertext data, and then the ciphertext data is sent to the server.

[0021] At the server, the ciphertext data from the client is processed in the encrypted state to obtain a processing result, and the processing result is stored in the database of the server; and according to the requirement, the processing result is returned to the client, and the client uses the decryption private key to perform full homomorphic decryption to obtain the processing result in plaintext state.

[0022] In a third aspect, the present invention also provides a storage medium, on which one or more programs readable by a computing device are stored. The one or more programs include instructions, and when the instructions are executed by the computing device, the computing device is caused to execute a power data processing method based on homomorphic encryption as described above.

[0023] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0024] 1. A method, system, and medium for processing power data based on homomorphic encryption provided by the present invention can perform fully homomorphic encryption on power data at the client side and send it to the server side. The server side analyzes and processes the data and stores the ciphertext. Finally, the server side sends the data analysis and processing results back to the client side, and the client side performs fully homomorphic decryption to obtain the processing results. The present invention helps to ensure the security and reliability of users' power data during transmission, processing, and storage, realizes data processing and storage in ciphertext state without obtaining the original information of the data, and has high security.

[0025] 2. The present invention uses an advanced fully homomorphic encryption algorithm to encrypt power data and operates in ciphertext form throughout the entire life cycle of the data. Even if problems such as data leakage occur, the true information of the data will not be leaked, ensuring the data security throughout the life cycle.

[0026] 3. By combining homomorphic encryption and artificial intelligence technologies, the homomorphic encryption during the data interaction process in the present invention ensures the security requirements of the data and can also efficiently predict the power load of users, improving the efficiency. It realizes the efficient processing of power user data under the premise of protecting user privacy and is applicable to various application scenarios in the smart grid environment.

[0027] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0028] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention.

[0031] Figure 1 It is a schematic flowchart of a method for processing power data based on homomorphic encryption provided by an embodiment of the present invention.

[0032] Figure 2Schematic diagram of the structure of the power prediction model based on deep learning provided by the embodiments of the present invention.

[0033] Figure 3 Schematic diagram of the framework of a power data processing system based on homomorphic encryption provided by the embodiments of the present invention. Detailed implementation manners

[0034] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0035] In the description of the present invention, it should be noted that: in some processes described in the specification and drawings of this application, there are multiple operations that appear in a specific order, but it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. In addition, various serial numbers, etc. are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0036] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0037] Embodiment 1:

[0038] See Figure 1 As shown, the embodiments of the present invention provide a power data processing method based on homomorphic encryption, which mainly includes:

[0039] S1. At the client side, power data is segmented by time series, and the segmented power data is subjected to fully homomorphic encryption using an encryption public key to obtain ciphertext data, and then the ciphertext data is sent to the server side;

[0040] S2. At the server side, the ciphertext data from the client is processed in the encrypted state to obtain a processing result, and the processing result is stored in the database of the server side;

[0041] S3. According to the requirement, the processing result is returned to the client, and the client uses a decryption private key to perform full homomorphic decryption to obtain the processing result in the plaintext state.

[0042] The following will introduce the specific implementation manners of the method of the present invention in detail:

[0043] In the embodiments of the present invention, before encryption, preprocessing operations are performed on the original power data, such as min-max normalization or Z-score standardization. Data preprocessing helps reduce the impact of numerical range differences on subsequent calculations and can protect user privacy to a certain extent.

[0044] Furthermore, on the client side, the power data is divided into data chunks according to the time series, and the long-time series power consumption data is divided into multiple time windows or batches, each batch containing a certain number of time points. Doing so can not only reduce the complexity of a single calculation but also support parallel processing, improving the overall efficiency.

[0045] Furthermore, the encrypted public key is used to perform fully homomorphic encryption on the power data after data chunking to obtain ciphertext data, and then the ciphertext data is sent to the server side. In the embodiments of the present invention, preferably, the modular component method is used to perform fully homomorphic encryption on the power data to obtain ciphertext data, and the process mainly includes:

[0046] 1) Generating a projection basis and a position basis: According to the encrypted public key, a projection basis S = {s1, s2,..., s n} and a position basis P = {p1, p2,..., p n} are randomly generated; among them, the projection basis S is used to split the original data, and the elements in the projection basis S are pairwise relatively prime; the position basis P is used to insert real modular components;

[0047] 2) Splitting the power data D into a set of real modular components d: Using the projection basis S to split the power data D, and performing a modulo operation on each element in the projection basis S to obtain a set of real modular components d = {d1, d2,..., d n}; d i = D mod s i , i = 1, 2,... n; mod is an operator that supports homomorphic operations;

[0048] 3) Generating a redundancy set R based on the set of real modular components d: According to the values of the elements in the set of real modular components d = {d1, d2,..., d n}, n redundancy vectors each containing j redundant terms are generated to obtain a redundancy set R = {R1, R2,..., R n}; where, R i = {R i1 , R i2 ,..., R ij}, i = 1, 2,..., n, and j is the number of redundant terms used to obfuscate the redundancy vector;

[0049] 4) Generate ciphertext data C: Insert the real modulus components into the redundancy set R respectively. Using the position basis P, replace the elements corresponding to the original positions in the redundancy set R with the elements in the real modulus component set d in sequence according to the insertion positions represented by the elements in the position basis P, to obtain the ciphertext data C, C = {C1, C2,..., C n}, C i = {C i1 , C i2 ,..., C pi ..., C ij} = {R i1 , R i2 ,..., dp i ..., R ij}, i = 1, 2,..., n; that is, C i is the modulus component vector after the real modulus component d i replaces the p i -th redundant item among the j redundant items of the redundant vector R i , where p i is the position where the real modulus component is located.

[0050] In an alternative embodiment, independent random noise is added to each data point during the encryption process; this increases the difficulty for attackers. Additionally, for particularly sensitive operations, a multi-party secure computation protocol can be combined to enable multiple participating parties to jointly cooperate to complete specific tasks without any single party having sole access to the complete information. For example, to calculate a weighted average, combine the weights of different clients and then securely obtain the result through the MPC protocol.

[0051] In another embodiment, to enhance security, the present invention preferably uses the following method to determine the decryption private key and the encryption public key: Among them, the method for generating the decryption private key is: randomly select an odd number z with a bit length of e, where e = αλ 3 , α and λ are security parameters. In the present invention, the larger the values of the α and λ parameters, the higher the security of the scheme; in practical applications, the value of α can be taken as 4 and the value of λ can be taken as 36; further, randomly select an integer g m with a bit length of e′, where e′ = αλ 2 , m = {1, 2,..., h}; h is an integer with a bit length of t, where Use the odd number z with a bit length of e and the integer g with a bit length of e′ m to generate the decryption private key as (z, g), where g m follows a normal distribution, The method for generating the encryption public key is: randomly select two integers q0 and q1, and calculate: x0 = zq0, and satisfy that x0 and x1 are relatively prime, and x0 is greater than x1; then randomly select k pairwise relatively prime prime numbers ym As part of the public key, calculate: Finally, the encrypted public key generated is (x0, x1, y, (y1, y2,..., y k ))

[0052] Furthermore, on the server side, the ciphertext data from the client is processed in the encrypted state to obtain a processing result, and the processing result is stored in the database on the server side; in a specific embodiment, the server side uses a power prediction model based on deep learning to perform computational processing on the ciphertext data to obtain the power load prediction result of the user.

[0053] As Figure 2 shown, the power prediction model in the present invention is a deep learning model built using CNN-BiLSTM-AE, which mainly includes a convolutional neural network, a BiLSTM neural network, and an attention mechanism layer connected in sequence; in this model, first, a one-dimensional convolutional neural network CNN processes the spatio-temporal features in the time series to provide higher-quality input data for BiLSTM, and the extracted features are passed into the Dropout layer. By randomly discarding neurons, the robustness of the neural network is increased. After the data passes through the BiLSTM neural network, Dropout regularization is performed again, and then it is input into the attention mechanism module to allocate weights to different input variables, enabling the model to pay more attention to those variables that play a decisive role in the prediction result. Finally, the data is flattened and the power load prediction result is output through the fully connected layer.

[0054] In the embodiment of the present invention, the server side obtains the user's power historical data of each client, and performs data diffusion processing on the user's power historical data as the local dataset data; then, the above power prediction model is trained locally through the dataset. Training the power prediction model locally means training the CNN-BiLSTM-AE deep learning model. In each round of training, it includes reshaping the data, compiling the power prediction model using the Adam optimizer and the mean absolute error (MAE) loss, and fitting the power prediction model for a specified number of rounds; through multiple trainings until the local power prediction model converges, the training is completed. The trained power prediction model can efficiently and accurately perform the power load prediction of the user. Finally, according to the demand, the processing result is returned to the client, and the client uses the decryption private key for fully homomorphic decryption to obtain the processing result in the plaintext state and display it through the front end, which helps the power company manage the charging demand and energy supply situation, analyze the user's power preferences, and thus can formulate a reasonable power scheduling plan for service optimization.

[0055] The present invention is not limited to the CNN-BiLSTM-AE deep learning model. A load forecasting system based on homomorphic encryption can also be constructed. This system can integrate multiple machine learning models, such as linear regression, decision tree, and support vector machine (SVM), etc., and select the best model through cross-validation for load forecasting of user electricity. It can accurately predict the electricity demand in the region while ensuring user privacy, and details will not be elaborated here.

[0056] In a specific embodiment, the database on the server side of the present invention uses full ciphertext storage. The data in the database is stored in the form of modulo components, and the modulo components can be true or false; that is, the encrypted data in the database is stored in the form of modulo components, and all data is in ciphertext state. Each piece of ciphertext data has a unique identifier to distinguish different ciphertext data. The identifier is only used for data identification and does not contain any information in the plaintext state of the ciphertext data, so it will not cause data leakage, realizing the storage and query of encrypted data.

[0057] From the description of the above embodiments, those skilled in the art can know that: The embodiments of the present invention provide a method for processing power data based on homomorphic encryption, which has the following advantages:

[0058] The present invention can perform fully homomorphic encryption on power data at the client side and send it to the server side. The server side performs data analysis and processing and ciphertext storage on the data, and finally sends the data analysis and processing results back to the client side, and the client side performs fully homomorphic decryption to obtain the processing results; The present invention is beneficial to ensuring the security and reliability of user power data during transmission, processing, and storage, realizing data processing and storage in ciphertext state without obtaining the original information of the data, and having high security.

[0059] The present invention operates in ciphertext form throughout the entire life cycle of the data. Even if problems such as data leakage occur, the true information of the data will not be leaked, ensuring the data security throughout the life cycle.

[0060] By combining homomorphic encryption and artificial intelligence technologies, the homomorphic encryption in the data interaction process ensures the security requirements of the data, and can also realize the prediction of user power load, improving the efficiency; It realizes the efficient processing of power user data under the premise of protecting user privacy and is applicable to various application scenarios in the smart grid environment.

[0061] Embodiment 2:

[0062] Refer to Figure 3 As shown, the embodiments of the present invention also provide a power data processing system based on homomorphic encryption, which is applied to a method for processing power data based on homomorphic encryption described in Embodiment 1 above. The system includes: a client side and a server side, where:

[0063] At the client side, power data is chunked according to time series, and the chunked power data is subjected to fully homomorphic encryption using an encryption public key to obtain ciphertext data, and then the ciphertext data is sent to the server side;

[0064] At the server side, the ciphertext data from the client is processed in the encrypted state to obtain a processing result, and the processing result is stored in the database of the server side; and according to requirements, the processing result is returned to the client, and the client uses a decryption private key to perform fully homomorphic decryption to obtain the processing result in the plaintext state.

[0065] In an embodiment of the present invention, the communication layer of the server side transmits the ciphertext data from the client to the control module, and the control module calls the calculation processing module to process the ciphertext data. The present invention is applicable to the fully homomorphic encryption technology. Due to the fully homomorphic property, that is:

[0066]

[0067] Among them, a represents the original data a, b represents the original data b, E represents the fully homomorphic encryption algorithm, and the symbols ⊕ and It means that the operation under ciphertext is equivalent to the operation under plaintext. That is, performing fully homomorphic processing on the encrypted data is equivalent to performing the same processing on the plaintext. Therefore, it is possible to implement the server to process and store data in the ciphertext state without obtaining the original information of the data, which is beneficial to ensuring the security and reliability of power data and can effectively protect user privacy.

[0068] A power data processing system based on homomorphic encryption provided by an embodiment of the present invention has the same implementation principle and the same technical effects as the embodiment of the foregoing power data processing method based on homomorphic encryption. For the sake of brief description, for the parts not mentioned in this embodiment, reference can be made to the corresponding content in the foregoing method embodiment, and details will not be described herein again.

[0069] Embodiment 3:

[0070] An embodiment of the present invention further provides a storage medium, on which one or more programs readable by a computing device are stored. The one or more programs include instructions that, when executed by the computing device, cause the computing device to execute a power data processing method based on homomorphic encryption in Embodiment 1.

[0071] Examples of the computer-readable storage medium here include: read-only memory (ROM), programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, DVD-ROM, Blu-ray or optical disc memory, hard disk drive (HDD), solid state drive (SSD), cartridge memory (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, any of the above other devices being configured to store a computer program and any associated data, data files and data structures in a non-transitory manner and provide the computer program and any associated data, data files and data structures to a processor or computer such that the processor or computer can execute the computer program. The computer program in the above computer-readable storage medium can run in an environment deployed in computer devices such as client, host, proxy device, server, etc. In addition, in one example, the computer program and any associated data, data files and data structures are distributed on a networked computer system or cloud platform such that the computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers.

[0072] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, system or computer program product, etc. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0073] It should be noted that the word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention can be implemented by means of hardware including several different components and by means of a properly programmed computer.

[0074] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same and similar parts among the various embodiments can be referred to each other.

[0075] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing power data based on homomorphic encryption, characterized in that: The method comprises the following steps: S1. The power data is divided into blocks according to the time series on the client side, and the encrypted public key is used to perform fully homomorphic encryption on the divided power data to obtain ciphertext data, and then the ciphertext data is sent to the server side; S2, processing the ciphertext data from the client in an encrypted state on the server side to obtain a processing result, and storing the processing result in a database on the server side; S3. Return the processing result to the client as required, and the client uses the decryption private key to perform fully homomorphic decryption to obtain the processing result in plaintext.

2. According to claim 1, a method for processing power data based on homomorphic encryption is characterized in that: In S1, the power data is fully homomorphically encrypted using a modular component method to obtain ciphertext data, and the process includes: 1) Randomly generate a projection base S = {s1, s2, ..., s n } and position basis P = {p1,p2,...,p n }; The projection basis S is used to split the data, and the elements in the projection basis S are mutually prime; the position basis P is used to insert the real modulus component; 2) Use the projection basis S to split the power data D, perform modulus operations on the elements in the projection basis S, and obtain the real modulus component set d = {d1, d2, ..., d n };d i =Dmods i , i=1,2,...n; mod is an operator that supports homomorphic operations; 3) According to the real modulus component set d = {d1, d2, ..., d n }, generate n redundant vectors containing j redundant items respectively, and obtain the redundant set R = {R1, R2, ..., R n }; where R i = {R i1 ,R i2 ,...,R ij }, i = 1, 2, ..., n, j is the number of redundant items used to confuse the redundant vector; 4) Insert the true modulus components into the redundant set R respectively, and use the position basis P to replace the elements in the true modulus component set d with the elements in the redundant set R in the original position according to the insertion position represented by the elements in the position basis P, so as to obtain the ciphertext data.

3. The method for processing power data based on homomorphic encryption according to claim 1, characterized in that: In S1, the original power data is standardized before encryption.

4. The method for processing power data based on homomorphic encryption according to claim 1, characterized in that: In S1, independent random noise is added to the power data after data segmentation during the encryption process.

5. The method for processing power data based on homomorphic encryption according to claim 1, characterized in that: In S2, the server side uses a power prediction model based on deep learning to calculate and process the encrypted data to obtain the user's power load prediction result; the power prediction model includes a convolutional neural network, a BiLSTM neural network and an attention mechanism layer connected in sequence.

6. The method for processing power data based on homomorphic encryption according to claim 1, characterized in that: In S2, the database on the server side adopts full ciphertext storage, the data in the database is stored in the form of modular components, all data are in ciphertext state, and each ciphertext data has a unique identifier to distinguish different ciphertext data.

7. A power data processing system based on homomorphic encryption, characterized in that: When applied, a method for processing power data based on homomorphic encryption as described in any one of claims 1 to 6 is executed, the system comprising: a client and a server, wherein: The power data is divided into blocks according to the time series on the client side, and the encrypted public key is used to perform fully homomorphic encryption on the divided power data to obtain ciphertext data, and then the ciphertext data is sent to the server side; The ciphertext data from the client is processed in an encrypted state on the server side to obtain a processing result, and the processing result is stored in a database on the server side; and the processing result is returned to the client as needed, and the client uses the decryption private key to perform fully homomorphic decryption to obtain the processing result in a plaintext state.

8. A storage medium having stored thereon one or more programs readable by a computing device, characterized in that: The one or more programs include instructions, which, when executed by a computing device, enable the computing device to perform a power data processing method based on homomorphic encryption as described in any one of claims 1 to 6.

Images