A privacy-protecting method, system, and storage medium for energy analysis of power grid customers

Abstract

The application discloses a kind of power grid user energy analysis method, system and storage medium of privacy protection, belong to smart grid technical field, method includes: obtaining the shared key between energy analysis server and each power grid user;According to the pre-constructed Lenet-5 network model, through the energy server, using the shared key, each power grid user is sent energy analysis request;In response to the energy analysis request, according to the privacy point multiplication algorithm, through each power grid user, using the shared key, the energy analysis response is sent to the energy server;In response to the energy analysis response, according to the Lenet-5 network model, through the energy analysis server, output energy analysis result.The method solves the problem of energy data privacy while solving the problem of data integrity protection.

Description

Technical Field

[0001] This invention relates to a privacy-preserving method, system, and storage medium for analyzing energy consumption of power grid users, belonging to the field of smart grid technology. Background Technology

[0002] With the growth in industrial and residential electricity demand, energy-saving equipment and technologies are experiencing a surge in market demand. The core of energy-saving technology lies in using modern information technology for energy efficiency management and demand-side management, thereby achieving energy conservation, emission reduction, and supply-demand balance. The key lies in analyzing and mining the energy usage of electricity end users and developing energy-saving solutions based on end-user electricity consumption. This requires the power grid to collect and analyze end-user load data in real time, i.e., energy consumption analysis and load monitoring.

[0003] The energy consumption analysis server contains a machine learning model that receives energy consumption data from multiple grid users, trains the model based on this data, and ultimately obtains an inference model capable of analyzing the energy consumption data. Energy consumption data privacy is a key issue in the design of the energy consumption analysis system.

[0004] Existing solutions to energy consumption data privacy issues mainly include homomorphic encryption, differential privacy, and multi-party computation algorithms. In homomorphic encryption, users encrypt their private data, the energy analysis server directly operates on the ciphertext, and then the user decrypts the result to obtain the final calculation. However, while this solution protects user data privacy, users can also obtain the server's calculation results, leading to leaks. Furthermore, the high computational cost of homomorphic encryption hinders its practical deployment. In differential privacy, users add noise to their data to prevent malicious attackers from obtaining their true energy consumption information. However, differential privacy reduces the accuracy of machine learning models. In traditional multi-party computation, participating parties use unintentional transmission protocols to exchange private data and use obfuscated circuits to replace the computation process, thus completing the computation without revealing their individual private data. However, multi-party computation requires a large number of modular exponentiation operations, resulting in excessive computational complexity and making practical deployment difficult. Meanwhile, there are also multi-party computation schemes based on secret sharing; however, these also suffer from high computational costs. In addition, existing solutions only focus on the privacy of energy consumption data, without considering the protection of data integrity. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, and storage medium for analyzing energy consumption of power grid users that protects privacy, thereby solving the problem of energy consumption data privacy while also addressing the issue of data integrity protection.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a privacy-protecting method for analyzing the energy consumption of power grid users, comprising:

[0008] Obtain the shared key between the energy consumption analysis server and various power grid users;

[0009] Based on the pre-built Lenet-5 network model, the energy consumption server sends energy consumption analysis requests to each of the power grid users using the shared key;

[0010] In response to the energy consumption analysis request, an energy consumption analysis response is sent to the energy consumption server through each of the power grid users using the shared key, based on the privacy dot product algorithm;

[0011] In response to the energy consumption analysis, the energy consumption analysis results are output through the energy consumption analysis server according to the Lenet-5 network model.

[0012] In conjunction with the first aspect, further obtaining the shared keys between the energy consumption analysis server and various power grid users includes:

[0013] The key parameters are initialized through the key distribution server so that the analysis server and each power grid user hold the public key parameters and their respective private keys.

[0014] Based on the public key parameters and the private key of the energy consumption analysis server, the energy consumption analysis server generates a shared key with each power grid user.

[0015] Based on the public key parameters and the private keys of each power grid user, each power grid user generates a shared key with the energy consumption analysis server.

[0016] The shared key generated by the energy consumption analysis server and shared with each grid user is the same as the shared key generated by each grid user and shared with the energy consumption analysis server.

[0017] In conjunction with the first aspect, further, based on the pre-built Lenet-5 network model, sending energy consumption analysis requests to each of the power grid users through the energy consumption server using the shared key includes:

[0018] Based on the pre-constructed Lenet-5 network model, the weight parameters of the first layer of the Lenet-5 network model are converted into a set of public information and a set of secret information;

[0019] Using the shared key, a first digital signature is generated for the public information;

[0020] The energy consumption analysis server sends the public information and the first digital signature to each of the power grid users.

[0021] In conjunction with the first aspect, further, in response to the energy consumption analysis request, according to the privacy dot product algorithm, each of the grid users sends an energy consumption analysis response to the energy consumption server using the shared key, including:

[0022] Receive public information and a first digital signature sent by the energy analysis server, and verify the first digital signature;

[0023] According to the privacy dot product algorithm, the energy consumption data corresponding to the weight parameters is injected into the public information to obtain privacy dot product information;

[0024] Using the shared key, a second digital signature is generated for the private dot product information;

[0025] Each of the aforementioned power grid users sends the private multiplication information and the second digital signature to the energy consumption analysis server.

[0026] In conjunction with the first aspect, further verification of the first digital signature includes:

[0027] Based on the shared key and public information, each of the power grid users generates a third digital signature corresponding to the first digital signature;

[0028] The third digital signature is compared with the first digital signature. If the third digital signature is the same as the first digital signature, it is determined that the public information has not been tampered with by an attacker; otherwise, it is determined that the public information has been tampered with by an attacker.

[0029] In conjunction with the first aspect, further, in response to the energy consumption analysis response, based on the Lenet-5 network model, the energy consumption analysis server outputs energy consumption analysis results including:

[0030] Receive confidential multiplication information and a second digital signature sent by each of the power grid users, and verify the second digital signature;

[0031] The energy consumption analysis results are parsed from the privacy dot product information and used as the output of the first layer of the Lenet-5 network model.

[0032] In conjunction with the first aspect, further verification of the second digital signature includes:

[0033] Based on the shared key and the privacy dot product information, the energy analysis server generates a fourth digital signature corresponding to the second digital signature;

[0034] The fourth digital signature is compared with the second digital signature. If the fourth digital signature is the same as the second digital signature, it is determined that the private dot product information has not been tampered with by the attacker; otherwise, it is determined that the private dot product information has been tampered with by the attacker.

[0035] Secondly, the present invention provides a privacy-protecting power grid user energy consumption analysis system, comprising:

[0036] Key generation module: used to obtain the shared key between the energy consumption analysis server and various power grid users;

[0037] Energy consumption analysis request module: used to send energy consumption analysis requests to each of the power grid users through the energy consumption server and using the shared key, based on the pre-built Lenet-5 network model;

[0038] Energy consumption analysis response module: In response to the energy consumption analysis request, it sends an energy consumption analysis response to the energy consumption server through the shared key of each of the power grid users, based on the privacy dot product algorithm.

[0039] Energy consumption analysis output module: In response to the energy consumption analysis response, it outputs energy consumption analysis results through the energy consumption analysis server according to the Lenet-5 network model.

[0040] Thirdly, the present invention provides a privacy-protecting power grid user energy consumption analysis system, including a processor and a storage medium;

[0041] The storage medium is used to store instructions;

[0042] The processor is configured to operate according to the instructions to perform the steps of the method according to any one of the first aspects.

[0043] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] The present invention provides a privacy-protecting power grid user energy consumption analysis method. It uses the Lenet-5 network model to analyze the energy consumption data of power grid users and employs a privacy dot product algorithm to ensure that the energy consumption data of power grid users is available but not visible. At the same time, it also provides authentication for the energy consumption data analysis process through a shared key between the energy consumption analysis server and each power grid user, thereby realizing an integrity protection mechanism. Attached Figure Description

[0046] Figure 1This is a flowchart of a privacy-protecting power grid user energy consumption analysis method provided by an embodiment of the present invention. Detailed Implementation

[0047] The technical solution of this patent will be further described in detail below with reference to specific embodiments.

[0048] The embodiments of this patent are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this patent, and should not be construed as limiting this patent. Unless otherwise specified, the embodiments of this application and the technical features within them can be combined with each other.

[0049] Example 1:

[0050] Figure 1 This is a flowchart illustrating a privacy-protecting power grid user energy consumption analysis method according to Embodiment 1 of the present invention. This flowchart only shows the logical sequence of the method in this embodiment; in other possible embodiments of the present invention, different methods may be used, provided there are no conflicts. Figure 1 Complete the steps shown or described in the order indicated.

[0051] The privacy-preserving power grid user energy consumption analysis method provided in this embodiment can be applied to a terminal and executed by a privacy-preserving power grid user energy consumption analysis system. This system can be implemented in software and / or hardware and can be integrated into the terminal, such as any tablet computer or computer device with communication capabilities. See also... Figure 1 The method in this embodiment specifically includes the following steps:

[0052] Step 1: Obtain the shared key between the energy consumption analysis server and each power grid user;

[0053] Obtaining the shared key between the energy consumption analysis server and various power grid users involves the following steps:

[0054] Step 1: Initialize the key parameters through the key distribution server so that the analysis server and each power grid user hold the public key parameters and their respective private keys.

[0055] During the key parameter initialization phase, the key distribution server generates public key parameters and their respective private keys for the energy consumption analysis server and each power grid user, and then distributes these public keys and their respective private keys to the energy consumption analysis server and each power grid user respectively.

[0056] When initializing key parameters, the key parameter initialization algorithm Init is used. Init is run by the key distribution server, and its inputs include: the server identifier ID. s A set U consisting of the identifiers of each power grid user, U = {U i The output of the key parameter initialization algorithm Init includes: public key parameter PUB, and the private key sk of the power analysis server. s SK is a set of private keys belonging to each power grid user, where SK = {sk} i U, 1≤i≤n}, where n is the total number of grid users, i is the i-th grid user, and U i Let sk be the identifier of the i-th power grid user. i Let be the private key of the i-th grid user. The specific steps of the key parameter initialization algorithm Init are shown in Algorithm 1:

[0057]

[0058] After the key parameter initialization algorithm Init is completed, both the energy server and each power grid user hold the public key parameter PUB; the energy server holds its own private key sk. s The i-th grid user holds their own private key sk i .

[0059] In the subsequent shared key generation and energy consumption analysis phases, the energy consumption analysis server and the grid user will use their respective private and public key parameters to generate a shared key, and use the shared key to protect the security of subsequent data transmission.

[0060] Step 2: Based on the public key parameters and the private key of the energy consumption analysis server, the energy consumption analysis server generates a shared key with each power grid user;

[0061] During the shared key generation phase, the energy consumption analysis server uses the EASGenk algorithm to generate shared keys with each grid user. The EASGenk algorithm is run by the energy consumption analysis server, and its inputs include the private key sk held by the energy consumption server. s Public key parameter PUB, Energy analysis server identifier ID s The output includes: the shared key sk between the energy analysis server and the i-th grid user. si The specific steps of the EASGenk algorithm are shown in Algorithm 2:

[0062]

[0063] Step 3: Based on the public key parameters and the private keys of each power grid user, each power grid user generates a shared key with the energy consumption analysis server;

[0064] During the shared key generation phase, each power grid user uses the UGenk algorithm to generate a shared key with the energy consumption analysis server. The UGenk algorithm is run by each power grid user, and its input includes the private key sk of the i-th power grid user. i Public key parameter PUB, i-th grid user identifier U i The output includes: the shared key sk between the i-th grid user and the energy consumption analysis server. si The specific steps of the UGenk algorithm are shown in Algorithm 3:

[0065]

[0066] The shared key generated by the energy consumption analysis server and shared with each grid user is the same as the shared key generated by each grid user and shared with the energy consumption analysis server.

[0067] After the shared key generation phase ends, the energy consumption analysis server and each grid user hold a shared key with each other. This shared key is used to protect the integrity of the data transmitted in subsequent energy consumption analysis phases.

[0068] Step 2: Based on the pre-built Lenet-5 network model, send energy consumption analysis requests to each grid user through the energy consumption server using a shared key;

[0069] Based on the pre-built Lenet-5 network model, the process of sending energy consumption analysis requests to various grid users via the energy consumption server using a shared key includes the following steps:

[0070] Step a: Based on the pre-built Lenet-5 network model, convert the weight parameters of the first layer of the Lenet-5 network model into a set of public information and a set of secret information;

[0071] When the energy consumption analysis server prepares to analyze the energy consumption data of the i-th grid user, it uses the hidden weight algorithm Convert to transform the weight parameters of the first layer of the Lenet-5 network model. The hidden weight algorithm Convert is run by the energy consumption analysis server, and its input includes the weight parameters W of the first layer of the Lenet-5 network model, W = {w1, ..., w2}. l The output includes: a set of public information PubI and a set of secret information PriI. The specific steps of the hidden weight algorithm Convert are shown in Algorithm 4:

[0072]

[0073] Step b: Use the shared key to generate a first digital signature for the public information;

[0074] The energy analysis server uses the Sig1 algorithm and a hash function to calculate the first digital signature σ of the publicly available information. i1 , σ i1 =h(w1′|...|w l ′|r1|...|r l |sk si The Sig1 algorithm, run by the energy consumption analysis server, is used to generate the first digital signature for the public information PubI. The inputs to the Sig1 algorithm include: the public information PubI, and the shared key sk between the energy consumption analysis server and the i-th grid user. si The output of the Sig1 algorithm includes: the first digital signature σ i1 .

[0075] Step c: Send the public information and the first digital signature to each power grid user through the energy analysis server;

[0076] The energy consumption analysis server converts the weighting parameters into a set of public information and a set of secret information. Grid users cannot recover the weighting parameters from the public information, thus ensuring the privacy of the energy consumption analysis server. The energy consumption analysis server generates a first digital signature for the public information, providing integrity protection for transmitted data.

[0077] Step 3: In response to the energy consumption analysis request, based on the privacy dot product algorithm, the energy consumption analysis response is sent to the energy consumption server through each power grid user using the shared key;

[0078] In response to an energy consumption analysis request, and based on a privacy dot product algorithm, the energy consumption analysis response is sent to the energy consumption server via shared keys through each grid user, including the following steps:

[0079] Step A: Receive the public information and the first digital signature sent by the power analysis server, and verify the first digital signature;

[0080] Verifying the first digital signature includes the following steps:

[0081] Step (1): Based on the shared key and public information, each power grid user generates a third digital signature corresponding to the first digital signature;

[0082] Step (2): Compare the third digital signature with the first digital signature. If the third digital signature is the same as the first digital signature, it is determined that the public information has not been tampered with by the attacker; otherwise, it is determined that the public information has been tampered with by the attacker.

[0083] The first digital signature is verified using the Verify1 algorithm, which is run by each power grid user. The inputs to the Verify1 algorithm include: public information PubI and the first digital signature σ. i1 The shared key sk between the i-th grid user and the energy consumption analysis server si ; Calculate the third digital signature σ i1 ′,σ i1 ′=h(w1′|...|w l ′|r1|...|r l |sk si ); The third digital signature σ i1 ′ and the first digital signature σ i1 For comparison, if the third digital signature σ i1 ′ and the first digital signature σ i1 If the results are the same, output True, indicating that the public information has not been tampered with by the attacker; otherwise, output False, indicating that the public information has been tampered with by the attacker.

[0084] Step B: Based on the privacy dot product algorithm, inject the energy consumption data corresponding to the weight parameters into the public information to obtain privacy dot product information;

[0085] When the i-th grid user injects the energy consumption data corresponding to the weight parameter into the public information, the Inject algorithm is used. The Inject algorithm is run by each grid user. The inputs to the Inject algorithm include: public information PubI and energy consumption data X corresponding to the weight parameter W; the output includes: private dot product information SP. The specific steps of the Inject algorithm are shown in Algorithm 5:

[0086]

[0087] Step C: Using the shared key, generate a second digital signature for the private dot product information;

[0088] Each power grid user uses the Sig2 algorithm and a hash function to calculate the second digital signature σ of the confidential dot product information. i2 , σ i2 =h(SP1|SP2|sk si The Sig2 algorithm, run by each grid user, is used to generate a second digital signature for the confidential multiplication information SP. The inputs to the Sig2 algorithm include: the confidential multiplication information SP, and the shared key sk between the i-th grid user and the energy consumption analysis server. si The output of the Sig2 algorithm includes: the second digital signature σ. i2 .

[0089] Step D: Send the privacy multiplication information and the second digital signature to the energy consumption analysis server through each power grid user;

[0090] Each power grid user injects their energy consumption data into public information to obtain confidential multiplication information. The energy consumption analysis server cannot recover the energy consumption data from the confidential multiplication information, thus ensuring the privacy of each power grid user. Each power grid user generates a second digital signature for the confidential multiplication information, which provides integrity protection for transmitted data.

[0091] Step 4: In response to the energy consumption analysis, based on the Lenet-5 network model, output the energy consumption analysis results through the energy consumption analysis server;

[0092] In response to the energy consumption analysis, based on the Lenet-5 network model, the energy consumption analysis server outputs the energy consumption analysis results through the following steps:

[0093] Step 1: Receive the confidential multiplication information and second digital signature sent by each power grid user, and verify the second digital signature;

[0094] Verification of the second digital signature includes:

[0095] Step i: Based on the shared key and the privacy dot product information, the energy analysis server generates a fourth digital signature corresponding to the second digital signature;

[0096] Step ii: Compare the fourth digital signature with the second digital signature. If the fourth digital signature is the same as the second digital signature, it is determined that the private dot product information has not been tampered with by the attacker; otherwise, it is determined that the private dot product information has been tampered with by the attacker.

[0097] The second digital signature is verified using the Verify2 algorithm, which is run by the energy analysis server. The inputs to Verify2 include: the privacy dot product information SP and the second digital signature σ. i2 The shared key sk between the energy analysis server and the i-th power grid user si ; Calculate the fourth digital signature σ i2 ′,σ i2 =h(SP1|SP2|sk) si ); The fourth digital signature σ i2 ′ and the second digital signature σ i2 For comparison, if the fourth digital signature σ i2 ′ and the second digital signature σ i2 If the values ​​are the same, output True, indicating that the private dot product information has not been tampered with by the attacker; otherwise, output False, indicating that the private dot product information has been tampered with by the attacker.

[0098] Step II: Extract the energy consumption analysis results from the privacy dot product information and use the energy consumption analysis results as the output of the first layer of the Lenet-5 network model;

[0099] The energy analysis result R, R = WX, is parsed from the private dot product information SP. The energy analysis result R is used as the output of the first layer of the Lenet-5 network model. The Lenet-5 network model is trained and its parameters are tuned according to the forward and backward propagation mechanism of the neural network, or the Lenet-5 network is used for inference to optimize the Lenet-5 network model.

[0100] The energy consumption analysis server verifies the received private multiplication information and provides integrity protection for transmitted data. The server then obtains energy consumption analysis results to analyze the energy consumption data of various power grid users.

[0101] The privacy-preserving power grid user energy consumption analysis method provided in this embodiment analyzes the energy consumption data of power grid users based on the Lenet-5 network model; generates digital signatures based on shared keys to prevent attackers from tampering with the data; and uses a privacy-preserving dot product algorithm to ensure that the privacy of the energy consumption analysis server and each power grid user is not leaked during the energy consumption analysis process.

[0102] Example 2:

[0103] This embodiment provides a privacy-protecting power grid user energy consumption analysis device, including:

[0104] Key generation module: used to obtain the shared key between the energy consumption analysis server and various power grid users;

[0105] Energy consumption analysis request module: Used to send energy consumption analysis requests to various power grid users through the energy consumption server and using a shared key, based on a pre-built Lenet-5 network model;

[0106] Energy consumption analysis response module: In response to energy consumption analysis requests, it sends an energy consumption analysis response to the energy consumption server through each power grid user using a shared key, based on a privacy dot product algorithm.

[0107] Energy consumption analysis output module: In response to the energy consumption analysis reply, it outputs the energy consumption analysis results through the energy consumption analysis server based on the Lenet-5 network model.

[0108] The privacy-protected power grid user energy consumption analysis system provided in this embodiment of the invention can execute the privacy-protected power grid user energy consumption analysis method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0109] Example 3:

[0110] This embodiment provides a privacy-protecting power grid user energy consumption analysis system, including a processor and a storage medium;

[0111] Storage media are used to store instructions;

[0112] The processor is used to perform operations according to instructions to execute the steps of the method in Embodiment 1.

[0113] Example 4:

[0114] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in Embodiment 1.

[0115] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will 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 program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0119] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A privacy-preserving method for analyzing energy consumption of power grid users, characterized in that, include: Obtain the shared key between the energy consumption analysis server and various power grid users; Based on the pre-built Lenet-5 network model, an energy consumption analysis request is sent to each grid user via an energy consumption server using a shared key. This includes: converting the weight parameters of the first layer of the Lenet-5 network model into a set of public information and a set of secret information; generating a first digital signature for the public information using a shared key; and sending the public information and the first digital signature to each grid user via the energy consumption analysis server. In response to an energy consumption analysis request, and based on a confidentiality multiplication algorithm, each grid user sends an energy consumption analysis response to the energy consumption server using a shared key. This includes: receiving public information and a first digital signature from the energy consumption analysis server and verifying the first digital signature; injecting energy consumption data corresponding to the weight parameters into the public information according to the confidentiality multiplication algorithm to obtain confidentiality multiplication information; generating a second digital signature for the confidentiality multiplication information using the shared key; and sending the confidentiality multiplication information and the second digital signature to the energy consumption analysis server through each grid user. In response to the energy consumption analysis, based on the Lenet-5 network model, the energy consumption analysis server outputs the energy consumption analysis results, including: receiving confidential multiplication information and second digital signatures sent by various power grid users, and verifying the second digital signature; parsing the energy consumption analysis results from the confidential multiplication information, and using the energy consumption analysis results as the output of the first layer of the Lenet-5 network model; verifying the second digital signature includes: generating a fourth digital signature corresponding to the second digital signature based on the shared key and the confidential multiplication information; comparing the fourth digital signature with the second digital signature, and if the fourth digital signature is the same as the second digital signature, it is determined that the confidential multiplication information has not been tampered with by an attacker; otherwise, it is determined that the confidential multiplication information has been tampered with by an attacker.

2. The privacy-protecting power grid user energy consumption analysis method according to claim 1, characterized in that, Obtaining the shared key between the energy consumption analysis server and various power grid users includes: The key parameters are initialized through the key distribution server so that the analysis server and each power grid user hold the public key parameters and their respective private keys. Based on the public key parameters and the private key of the energy consumption analysis server, the energy consumption analysis server generates a shared key with each power grid user. Based on the public key parameters and the private keys of each power grid user, each power grid user generates a shared key with the energy consumption analysis server. The shared key generated by the energy consumption analysis server and shared with each grid user is the same as the shared key generated by each grid user and shared with the energy consumption analysis server.

3. The privacy-protecting power grid user energy consumption analysis method according to claim 1, characterized in that, Verification of the first digital signature includes: Based on the shared key and public information, each of the power grid users generates a third digital signature corresponding to the first digital signature; The third digital signature is compared with the first digital signature. If the third digital signature is the same as the first digital signature, it is determined that the public information has not been tampered with by the attacker; otherwise, it is determined that the public information has been tampered with by the attacker.

4. A privacy-protecting power grid user energy consumption analysis system, characterized in that, include: Key generation module: used to obtain the shared key between the energy consumption analysis server and various power grid users; Energy consumption analysis request module: Used to send energy consumption analysis requests to various power grid users through the energy consumption server and using a shared key, based on a pre-built Lenet-5 network model; Energy consumption analysis response module: In response to energy consumption analysis requests, it sends an energy consumption analysis response to the energy consumption server through each power grid user using a shared key, based on a privacy dot product algorithm. Energy consumption analysis output module: In response to energy consumption analysis, it outputs energy consumption analysis results through the energy consumption analysis server based on the Lenet-5 network model; Based on the pre-built Lenet-5 network model, energy consumption analysis requests are sent to various grid users via the energy consumption server using a shared key, including: Based on the pre-built Lenet-5 network model, the weight parameters of the first layer of the Lenet-5 network model are converted into a set of public information and a set of secret information; Use a shared key to generate a first digital signature for public information; The public information and the first digital signature are sent to each power grid user through the energy consumption analysis server; In response to the energy consumption analysis request, based on the privacy dot product algorithm, and through each grid user using a shared key, an energy consumption analysis response is sent to the energy consumption server, including: Receive public information and a first digital signature sent by the energy analysis server, and verify the first digital signature; Based on the privacy dot product algorithm, the energy consumption data corresponding to the weight parameters is injected into the public information to obtain privacy dot product information; Use a shared key to generate a second digital signature for private dot product information; Through each power grid user, the private multiplier information and the second digital signature are sent to the energy consumption analysis server; In response to the energy consumption analysis, based on the Lenet-5 network model, the energy consumption analysis server outputs the following results: Receive confidential multiplication information and second digital signatures sent by various power grid users, and verify the second digital signatures; The energy consumption analysis results are extracted from the private dot product information and used as the output of the first layer of the Lenet-5 network model. Verification of the second digital signature includes: Based on the shared key and the private dot product information, the energy analysis server generates a fourth digital signature corresponding to the second digital signature; The fourth digital signature is compared with the second digital signature. If the fourth digital signature is the same as the second digital signature, it is determined that the private dot product information has not been tampered with by the attacker; otherwise, it is determined that the private dot product information has been tampered with by the attacker.

5. A privacy-protecting power grid user energy consumption analysis system, characterized in that, Including processor and storage media; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 3.

Images