Privacy protection method and device for power grid data and electronic equipment

Abstract

The application provides a power grid data privacy protection method and device and electronic equipment. The method comprises the following steps: acquiring a plurality of power grid user usage data sets and the perceived sensitivity of a plurality of elements in the usage data set, wherein the usage data set comprises a plurality of usage data of the power grid user; partitioning the usage data set according to the perceived sensitivity to determine a plurality of subsets of the usage data set, wherein the plurality of subsets have different perceived sensitivities; determining a sampling tuple comprising a subset according to a preset sampling mechanism of an individual differential privacy algorithm and the subset; determining a noise output of the subset according to a preset calculation mechanism of the differential privacy algorithm and the sampling tuple; and performing a preset level of noise protection on the subset according to the noise output to protect the power grid data. The application solves the problem that the existing power grid data privacy protection research ignores the differences between users in terms of privacy preferences or sensitivities.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information security, in particular to a power grid data privacy protection method, a power grid data privacy protection device, a computer readable storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of smart grid and Internet of Things technology, the power grid system also collects and stores a large amount of user power consumption data, which is crucial for third parties to manage energy, predict demand and optimize the power grid. However, current research on power grid data privacy protection often ignores the differences in privacy preferences or sensitivity between users, which can lead to privacy protection measures that are either too strict, limiting the reasonable use of data, or insufficient, putting user privacy at risk. At the same time, if the power consumption data that users consider non-sensitive or highly public is excessively noisy, not only will it increase the cost of privacy protection, but it may also reduce the accuracy of data analysis and the efficiency of power grid services. SUMMARY

[0003] The present application provides a power grid data privacy protection method, a power grid data privacy protection device, a computer readable storage medium and an electronic device to solve the problem of increased privacy protection costs due to the lack of user perception of sensitivity in power grid data privacy protection in the prior art.

[0004] According to one aspect of the present application, a power grid data privacy protection method is provided, the method comprising: obtaining a plurality of power grid user usage data sets and the perceived sensitivity of a plurality of elements in the usage data set, the usage data set comprising a plurality of usage data of power grid users; partitioning the usage data set according to the perceived sensitivity, determining a plurality of subsets of the usage data set, a plurality of the subsets having different perceived sensitivities; determining a sampling tuple comprising the subset according to at least a preset sampling mechanism of an individual differential privacy algorithm and the subset; determining a noise output of the subset according to at least a preset calculation mechanism of a differential privacy algorithm and the sampling tuple; and performing a preset level of noise protection on the subset according to the noise output, to protect the privacy of the power grid data.

[0005] Optionally, the partitioning of the usage data set according to the perceived sensitivity and the determination of a plurality of subsets of the usage data set comprise: determining the categories of the perceived sensitivity according to the perceived sensitivity, the categories including high sensitivity, medium sensitivity, low sensitivity and non-sensitivity; and partitioning the usage data set according to the categories and determining a plurality of subsets of the usage data set.

[0006] Optionally, the determining, according to the preset sampling mechanism of the individualized differential privacy algorithm and the subset, of the sampling tuple comprising the subset comprises: determining a privacy level of the subset according to the subset and the perception sensitivity corresponding to the subset, and determining a privacy budget according to the privacy level; determining a privacy threshold of the subset according to the privacy budget; determining an element of the subset according to the use data set, the privacy threshold and the privacy level, to obtain the subset; and determining the sampling tuple comprising the subset according to the subset, the privacy budget and the privacy threshold.

[0007] Optionally, the determining, according to the preset algorithm mechanism of the differential privacy algorithm and the sampling tuple, of the noise output of the subset comprises: obtaining a query function; and determining the noise output of the subset according to the query function, the sampling tuple and the preset algorithm mechanism.

[0008] Optionally, the privacy protection method further comprises: determining a privacy level of a boundary of an adjacent subset according to at least a differential privacy algorithm model and a symmetric difference of the adjacent subset.

[0009] Optionally, the privacy protection method further comprises: determining a privacy budget of a boundary of an adjacent subset according to at least an individualized differential privacy algorithm model, the privacy level and a symmetric difference of the adjacent subset.

[0010] Optionally, the preset sampling mechanism is: wherein δ is a privacy threshold corresponding to a category of the perception sensitivity, ∈ i is a privacy level, and ω(r) is an element obtained in the subset.

[0011] According to another aspect of the present application, there is provided a privacy protection device for power grid data, the device comprising: an acquisition module configured to acquire a use data set of a plurality of power grid users and a perception sensitivity of a plurality of elements in the use data set, the use data set comprising a plurality of use data of power grid users; a first determination module configured to partition the use data set according to the perception sensitivity, and determine a plurality of subsets of the use data set, the plurality of subsets having different perception sensitivities; a second determination module configured to determine a sampling tuple comprising the subset according to at least a preset sampling mechanism of an individualized differential privacy algorithm and the subset; a third determination module configured to determine a noise output of the subset according to at least a preset algorithm mechanism of a differential privacy algorithm and the sampling tuple; and a control module configured to perform a preset level of noise protection on the subset according to the noise output, to protect the privacy of the power grid data.

[0012] According to another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium comprising a stored program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to perform the power grid data privacy protection method according to any one of the above when the program is running.

[0013] According to another aspect of the present application, an electronic device is provided, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for performing the power grid data privacy protection method according to any one of the above.

[0014] By applying the technical solution of the present application, the power grid data privacy protection method is used to first acquire a plurality of power grid user usage data sets and a plurality of elements in the usage data sets, partition the usage data sets according to the perception sensitivity, determine a plurality of subsets of the usage data sets having different perception sensitivities, determine a sampling tuple comprising the subset according to a preset sampling mechanism of a personalized differential privacy algorithm and the subset, determine a noise output of the subset according to a preset calculation mechanism of the differential privacy algorithm and the sampling tuple, and perform a preset level of noise protection on the subset according to the noise output, so as to protect the privacy of the power grid data. By introducing a sensitivity perception partitioning preset sampling mechanism to realize a sensitivity perception partitioning personalized differential privacy protection model (SPPDP, SPPDP), each user in the online power grid user network can define the sensitivity level of the social relationship of the user, thereby promoting personalized privacy settings. The above privacy protection method can be run in a trusted service provider, and can establish a privacy protection level according to the sensitivity perceived by the user. The problem of increasing the cost of privacy protection due to the neglect of the sensitivity perceived by the user in the prior art is solved. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and the illustrative embodiments of the present application and their description serve the purpose of explaining the present application. The accompanying drawings in which:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal of a power grid data privacy protection method according to an embodiment of the present application is shown;

[0017] Figure 2 A flowchart of a power grid data privacy protection method according to an embodiment of the present application is shown;

[0018] Figure 3 A schematic diagram of a privacy protection device for grid data according to an embodiment of the application is shown.

[0019] Wherein, the above figures include the following reference signs:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output device. DETAILED DESCRIPTION

[0021] It should be noted that the embodiments and features in the application can be combined with each other without conflict. The application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0022] In order to enable those skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] Due to the rapid popularization of smart grid technology, Internet of Things devices and advanced metering infrastructure (AMI), the grid has become an indispensable key infrastructure in modern society, and grid data is also experiencing unprecedented growth. According to the latest statistical data, the number of users of global smart grid has broken through the billion mark in 2023, which has increased significantly compared with ten years ago. Many grid operators and service providers collect a large amount of personal user power consumption data in the operation process, and allow third parties (including research institutions and energy service companies) to obtain statistical information of these data by submitting queries, in order to optimize energy distribution, predict demand trends and improve grid efficiency.

[0025] However, the widespread collection and sharing of personal electricity data in smart grids has raised deep concerns about privacy leakage among users. Users do not want their sensitive electricity habits, living conditions, and other information to be accessed by unauthorized third parties. At the same time, the implementation of international and regional privacy laws and regulations such as the California Privacy Rights Act (CPRA), the Consumer Credit Reporting Agencies Act (CCRA), and the European Union's General Data Protection Regulation (GDPR) has also emphasized the importance of personal privacy rights in grid data management. These regulations require grid operators and data processors to follow the principles of transparency, fairness, and security when collecting, processing, and sharing personal information, ensuring that users can control their own data and understand its use.

[0026] Considering the diversity of user privacy preferences and in order to build a more adaptive and user-centered framework for grid data privacy protection, researchers have begun to explore the application of differential privacy (DP) technology in grid data management and have proposed the concept of personalized differential privacy (PDP). As an important theoretical basis for DP, personalized differential privacy integrates personalized privacy settings based on user privacy rights and emphasizes the central role of user control and authorization in grid data privacy protection. It breaks the limitations of traditional DP, which provides a uniform global privacy parameter for all users, and can flexibly adapt to different privacy needs of users.

[0027] In smart grids, the application of personalized differential privacy mainly focuses on two aspects: one is the electricity data query response for individual users, which adds different levels of noise according to the user's privacy preferences and sensitivity levels to achieve personalized privacy protection; the other is personalized privacy protection in the process of grid data release, ensuring that the release of grid operation data, user electricity statistics, and other information fully respects and protects the personal privacy of users. Although there have been some research results in the former aspect, the latter—personalized privacy protection in grid data release—is still an area that needs further research.

[0028] Giving users the ability to independently specify the sensitivity level of personal electricity data is an important manifestation of respecting personal privacy rights (or personalization). This not only helps to improve user trust in smart grids, but also promotes the legal and compliant use of grid data, laying a solid foundation for the sustainable development of smart grids.

[0029] The aforementioned research on power grid data privacy protection often overlooks the differences in privacy preferences or sensitivities among users. This may lead to privacy protection measures that are either overly strict, limiting the reasonable use of data, or insufficient, exposing user privacy to risks. Furthermore, excessive noise processing of electricity consumption data that users deem non-sensitive or highly public not only increases the cost of privacy protection but may also reduce the accuracy of data analysis and the efficiency of power grid services. To address the problem that existing research on power grid data privacy protection neglects the differences in privacy preferences or sensitivities among users, embodiments of this application provide a method for protecting power grid data privacy, a device for protecting power grid data privacy, a computer-readable storage medium, and an electronic device.

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0031] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of protecting the privacy of power grid data according to an embodiment of this application. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the power grid data privacy protection method in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the method described above, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific examples of the network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.

[0033] In the embodiments, a power grid data privacy protection method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 2 FIG. 1 is a flow diagram of a power grid data privacy protection method according to an embodiment of the present application. As shown in FIG. 1, the method includes the following steps: Figure 2

[0035] In step S201, a plurality of usage data sets of power grid users and a perceived sensitivity of a plurality of elements in the usage data sets are obtained. The usage data set includes a plurality of usage data of the power grid users.

[0036] ​Specifically, by obtaining the usage data set of multiple power grid users and the perceptual sensitivity of multiple elements in the usage data set, the influence degree of different data elements on user privacy can be evaluated, thereby targeted privacy protection measures can be taken, by analyzing the sensitivity in the user usage data set, the data can be encrypted, anonymized or desensitized according to the importance and sensitivity of different data elements, to protect user privacy information from being leaked, and it can also help to find the commonness and regularity in the data set, further improve the efficiency of data processing and analysis, by analyzing the usage data of multiple users, the behavior habits and demands of users can be better understood, and more personalized and effective services can be provided for the power grid system.

[0037] Step S202, partitioning the usage data set according to the perceptual sensitivity, determining multiple subsets of the usage data set, the multiple subsets having different perceptual sensitivities.

[0038] Specifically, by using data set partitioning and determining that multiple subsets have different perceptual sensitivities, the privacy information of users can be protected, by dividing the data set into multiple subsets, each subset has different perceptual sensitivity, different degrees of data protection and privacy protection measures can be taken for each subset according to actual needs, thereby effectively reducing the risk of data leakage, while ensuring that the data can still be effectively utilized, for example, for subsets with higher sensitivity, more stringent data encryption, access control and anonymization measures can be taken to ensure that the data is not accessed by unauthorized personnel, while for subsets with lower perceptual sensitivity, relatively relaxed protection strategies can be adopted to reduce costs to ensure data availability and effectiveness.

[0039] Step S203, determining a sampling tuple including the subset according to at least a preset sampling mechanism of a personalized differential privacy algorithm and the subset.

[0040] Specifically, by using the preset sampling mechanism of the personalized differential privacy algorithm and the subset, the sampling tuple including the subset can be determined, thereby realizing the privacy protection of the data, by sampling a part of the tuple in the data set and adding noise to it, the confusion and disturbance of the data can be realized, thereby protecting the privacy of the data, at the same time, the personalized differential privacy algorithm can also protect the data according to the personalized privacy needs of the user, effectively balancing the privacy protection of the data and the accuracy of the data analysis, by designing the sampling mechanism and the subset, the risk of data leakage can be reduced to a certain extent, and the privacy information of the user can be protected.

[0041] Step S204, determining the noise output of the subset according to at least the sampling tuple and the preset calculation mechanism of the differential privacy algorithm.

[0042] Specifically, the differential privacy algorithm protects data privacy by adding appropriate noise to the query result while maintaining the effectiveness of data analysis as much as possible. The privacy of the user's electricity data can be effectively protected by determining the noise output of the subset, preventing malicious users or attackers from obtaining the user's personal information or behavior habits by analyzing the data. By adding noise output, desensitization processing of the data can be achieved, thereby ensuring the effective protection of the user's privacy while maintaining the effectiveness and accuracy of data analysis.

[0043] In step S205, the subset is protected by a preset level of noise output to protect the privacy of the power grid data.

[0044] Specifically, by protecting the subset by a preset level of noise output according to the noise output, the privacy of the data can be effectively protected, preventing sensitive information from being leaked. By adding noise to the data set, the data can be blurred, making it difficult for attackers to accurately infer the information of the original data, thereby protecting the privacy of the user and increasing the security of the data, reducing the risk of data leakage, ensuring that the privacy of the user is not infringed. The noise protection can also help data analysts analyze and mine data without leaking sensitive information, thereby maintaining the usability and integrity of the data.

[0045] Through the embodiment, a sampling mechanism including a personalized differential privacy algorithm, a differential privacy algorithm and a sensitivity-aware partition is introduced to realize SPPDP, and a privacy threshold optimization strategy is proposed to optimize the privacy mechanism, thereby realizing the optimization trade-off between personalized privacy protection and improving data utility in the online power grid user network. SPPDP enables each user in the online power grid user network to individually define the sensitivity level of their social relationship, thereby facilitating personalized privacy settings. The above method can be run inside a trusted service provider and can set a privacy protection level according to the sensitivity perceived by the user. The problem of increasing the cost of privacy protection due to the neglect of user-perceived sensitivity in the prior art is solved.

[0046] It should be noted that the data model of the online power grid user can be simply represented as a tuple D, D={r1,r2,…,r n}, each record r i is associated with a user u i , and the tuple D also represents the user's power grid data set. The graph model adopts an undirected graph paradigm, and SPDP is realized by a sensitivity-aware sampling mechanism (SASM).

[0047] In particular, the personalized differential privacy model SPPDP of the above sensitivity perception partition is a differential privacy algorithm based on personalized needs. According to the privacy sensitivity of the user and the data partition condition, the level of privacy protection is dynamically adjusted to realize personalized privacy protection, aiming to find a better balance point between protecting user privacy and improving data use value. Personalization is seamlessly integrated into the differential privacy protection framework of the power grid by the user's self-perception of the sensitivity of the electricity consumption data. The perceived sensitivity refers to that the user can set the privacy level related to the electricity consumption behavior more carefully according to the personal situation, and establish a personalized sensitivity classification for the user's electricity consumption data, which reflects the user's personal privacy tendency. It may be influenced by cultural habits, personal values and social environment, and thus is unique and specific for each user.

[0048] In particular, after obtaining the use data set of a plurality of power grid users, the power grid data set D is input, and the user's perceived sensitivity set Then, the sensitivity profile of the data set D is initialized, that is, the sensitive subset And the non-sensitive subset

[0049] In particular, the personalized differential privacy model SPPDP of the sensitivity perception partition refers to that given a data set D and a personalized privacy budget Φ derived from the perceived sensitivity And the privacy perception mechanism A random mechanism Satisfies Φ-SPPDP, if And The following inequality holds:

[0050]

[0051] Where the neighborhood Refers to let Indicates the perceived sensitivity of the user set n Associated with the data set D = {r1, r2,..., r D' is the neighborhood data set of D, and there is a sensitive record r ∈ D s So that D' = D{r} or D' = D∪{r}, is expressed as Where, Is the neighborhood data set of the data set D.

[0052] Specifically, the above anti-joy protection is to protect the privacy of data by adding a certain amount of noise to the original data, which can effectively prevent the data from being identified or reconstructed by malicious attackers, thereby protecting the privacy information of the user. The implementation mode of the anti-joy protection can be various, for example, adding random noise to the power grid data, disturbing the timestamp or position information of the data, etc. These noises can blur the characteristics of the original data, thereby achieving the effect of protecting the data privacy.

[0053] In the specific implementation process, the usage data set is partitioned according to the perception sensitivity, and a plurality of subsets of the usage data set are determined, which can be realized by the following steps: according to the perception sensitivity, the category of the perception sensitivity is determined, and the category includes high sensitivity, medium sensitivity, low sensitivity and non-sensitivity; the usage data set is partitioned according to the category, and a plurality of subsets of the usage data set are determined.

[0054] In this scheme, by partitioning the usage data set according to the perception sensitivity, the data of different sensitivity levels in the data set can be determined, and targeted privacy protection measures can be taken. By dividing the data set into high sensitivity, medium sensitivity, low sensitivity and non-sensitivity subsets, different privacy protection measures can be taken for each subset to ensure that high sensitivity data is more strictly protected, and non-sensitivity data can be protected more relaxed, thereby protecting the privacy of the data while maintaining the availability and effectiveness of the data as much as possible. It can effectively improve the privacy protection level of the power grid data, while reducing the cost and complexity of data processing and management.

[0055] Specifically, based on the sensitivity The data set D is divided as follows: traverse each record r i ∈D, and classify the edges according to the sensitivity, if P(r i ) = 4, then D hs = D hs ∪r; if P(r i ) = 3, then D ms = D ms ∪r i ; if P(r i ) = 2, then D ls = D ls ∪r i ; if P(r i ) = 1, then D ns = D ns ∪r i Therefore, based on the user's perception sensitivity set , a sensitivity partition of the data set D can be obtained, that is, D = D s ∪D ns = D hs ∪Dms ∪D ls ∪D ns .

[0056] Specifically, the above perception sensitivity refers to the perception sensitivity of the user u i The perception sensitivity of the user u i is expressed as a mapping P i :{r→{1,2,3,4}}, wherein 1, 2, 3, and 4 respectively correspond to four sensitivity states of non-sensitivity (ns), low sensitivity (ls), medium sensitivity (ms), and high sensitivity (hs), and the function P i takes r i as input and determines the sensitivity level thereof.

[0057] That is, the user's The set D = {r1, r2, …, r n} is divided into four different subsets as follows: a high sensitivity subset D hs = {r | r ∈ D, P(r) = 4}, a medium sensitivity subset D ms = {r | r ∈ D, P(r) = 3}, a low sensitivity subset D ls = {r | r ∈ D, P(r) = 2}, and a non-sensitivity subset D ns = {r | r ∈ D, P(r) = 1}, so the sensitivity configuration of the data set D = {r1, r2, …, r n} is D = D s ∪D ns = D hs ∪D ms ∪D ls ∪D ns .

[0058] In a specific implementation process, at least according to a preset sampling mechanism and a subset of a personalized differential privacy algorithm, a sampling tuple including the subset is determined, which can be achieved by the following steps: determining a privacy level of the subset according to the subset and the perception sensitivity corresponding to the subset, and determining a privacy budget according to the privacy level; determining a privacy threshold of the subset according to the privacy budget; determining an element of the subset according to the use data set, the privacy threshold, and the privacy level, to obtain the subset; and determining the sampling tuple including the subset according to the subset, the privacy budget, and the privacy threshold.

[0059] In this scheme, by determining the privacy level and privacy budget of the subset, an appropriate privacy threshold can be set according to specific needs, thereby protecting user privacy while maintaining data validity as much as possible. Based on the privacy threshold and the elements of the subset, the sampling tuples including the subset can be determined, further obfuscating the data to increase privacy protection. Through personalized differential privacy algorithms, the validity and usability of the data can be preserved as much as possible while protecting user privacy, thus achieving a balance in data analysis and application. By determining the sampling mechanism and subset, the dimensionality and sensitivity of the data can be effectively reduced, the risk of data leakage can be lowered, and the level of data security and privacy protection can be improved.

[0060] Specifically, the aforementioned privacy-aware mechanism is a privacy-aware mechanism on the online power grid user network. The record r in D can be i Sensitivity P(r) i Mapped to the corresponding privacy level ∈ i And obtain a personalized privacy budget Φ={∈ i} 1≤i≤n The mechanism operates as follows:

[0061] 1. When P(r) i ) = 1 or r i ∈D ns ,

[0062] 2. When P(r) i ) = 2 or r i ∈D ls ,

[0063] 3. When P(r) i ) = 3 or r i ∈D ms ,∈ i In the interval [ b ,∈ c Randomly select a value from within )

[0064] 4. When P(r) i ) = 4 or r i ∈D hs ,∈ i In the interval [∈ a ,∈ b Randomly select a value from within )

[0065] Where, ∈ a ,∈ b ,∈ c >0 is an adjustable parameter, and it must satisfy the condition ∈ a ≤∈ b ≤ c .

[0066] Specifically, in the implementation of the privacy-aware mechanism After that, the corresponding privacy protection level and privacy budget value are shown in Table 1:

[0067] Table 1 Privacy level customization

[0068]

[0069] wherein, ∈ a = 0.5, ∈ b = 5 and ∈ c = 10, and Φ = Φ hs ∪ Φ ms ∪ Φ ls .

[0070] Specifically, the sampling mechanism based on edge sensitivity partitioning is as follows: first, the edge set is divided into four partitions D = D hs ∪ D ms ∪ D ls ∪ D ns , wherein three sensitive edge partitions D hs , D ms and D ls correspond to different privacy budget ranges, and the non-sensitive data partition D ns can be directly statistically published, second, the privacy threshold of each partition is calculated based on the privacy budget of each edge partition, and the privacy threshold of the partition D hs based on the privacy budget Φ hs = [0.5, 5) is denoted as δ hs , the privacy threshold of the partition D ms is denoted as δ ms , and the privacy threshold of the partition D ls is denoted as δ ls , and the sampling mechanism SM f (D, Φ hs , δ hs ) is performed on each edge in each edge sensitivity partition. f (D, Φ ms , δ ms ) and SM f (D, Φ ls , δ ls ).

[0071] In the specific implementation process, at least according to the sampling tuple and the pre-designed mechanism of the differential privacy algorithm, the noise output of the subset is determined, which can be realized by the following steps: obtaining a query function f; determining the noise output of the subset according to the query function f, the sampling tuple and the pre-designed mechanism.

[0072] In the scheme, the query function can ensure the availability and accuracy of the data while protecting the privacy of the user by using the differential privacy algorithm and the noise output mode. Through the noise output processing of the query function and the subset of the data, the leakage of sensitive information and the re-identification of the data can be effectively prevented, thereby protecting the privacy of the user.

[0073] The query function f can be a query for the edge weight.

[0074] It should be noted that the preset sampling mechanism is for the query function Data set A sampling threshold δ and a personalized privacy budget Φ = {∈1,…,∈ i ,…,∈ n} Let RS(D, Φ, δ) represent the process of independently sampling each tuple D hs , D ms and D ls in the data set D. The data of the entire power grid.

[0075] Specifically, according to the determined data set D of RS(D, Φ, δ), input to the query function f, to obtain , which represents that the sampling result corresponding to the data set D is The noise output result of the query function f is returned , wherein represents the sampling mechanism of the sensitivity-aware partition.

[0076] In the specific implementation process, the privacy protection method further includes the following steps: determining the privacy level of the boundary of the adjacent subset at least according to the differential privacy algorithm model and the symmetric difference of the adjacent subset.

[0077] In the scheme, by using the differential privacy algorithm model and calculating the symmetric difference of the adjacent subset, the privacy protection degree between different data sets can be evaluated, and the privacy level between the data sets can be determined, so that the privacy information of the user can be effectively protected while ensuring the accuracy of the data analysis result, preventing privacy leakage and abuse, ensuring that the personal privacy information of the user will not be leaked in the use and sharing process of the power grid data, and improving the data security and privacy protection level.

[0078] Specifically, the random algorithm satisfies ∈ i -Edge differential privacy, for any adjacent data sets D1 and D2 and any subset Z of Range(M) (data sequence), the algorithm satisfies:

[0079]

[0080] Where |D1ΔD2|=1, Pr(x) represents the probability distribution, and x is a variable.

[0081] In the specific implementation process, the above privacy protection method also includes the following steps: at least based on the personalized differential privacy algorithm model, the privacy level and the symmetric difference of the adjacent subsets, the privacy budget of the boundary of the adjacent subsets is determined.

[0082] This solution effectively protects the privacy of power grid data through a personalized differential privacy algorithm model, ensuring that sensitive personal information is not leaked when the data is used. By determining the privacy budget of the boundaries of adjacent subsets, it can help determine the permissible level of privacy leakage during data publication or querying, thereby better balancing the needs of data privacy protection and data analysis.

[0083] Specifically, the personalized differential privacy algorithm is a randomized algorithm. Satisfying Φ-Personalized Differential Privacy PDP, if for any neighboring datasets D1 and D1ΔD2=r, and any subset Z of Range(M), the algorithm satisfy: Where Δ represents the symmetric difference, and r∈D represents the difference with user u i Related records, ∈ i Indicates user u i Privacy requirements.

[0084] In the specific implementation process, the above-mentioned preset sampling mechanism is as follows: Where δ is the privacy threshold corresponding to the category of perceptual sensitivity, ∈ i Let ω(r) represent the privacy level, and let ω(r) represent the elements in the resulting subset.

[0085] This scheme controls the amount and quality of data sampling by setting different privacy thresholds and privacy levels, thereby protecting user privacy while ensuring the validity and availability of data, effectively reducing the risk of sensitive data leakage, and ensuring the accuracy of data analysis. By randomly selecting subset elements from the dataset, it can reduce the infringement on individual users and protect user privacy to a certain extent.

[0086] Specifically, based on the privacy threshold δ and the privacy level ∈ i Determine the element r in the set D for each sensitivity level, according to the privacy level ∈ i The corresponding privacy budget Φ, dataset D, and privacy threshold δ yield the sampling result RS(D,Φ,δ), and the above sampling mechanism. Satisfying Φ-personalized differential privacy, where It is any delta-DP mechanism for computing a function f, where D = {r1, r2, ..., r}. n}and Representing user sets respectively The associated record set and perceptual sensitivity, r i Indicates with user u i Related records, P i Indicates by u i Assigned to r i Perceptual sensitivity.

[0087] As described above, this invention presents a groundbreaking study on sensitivity-aware personalization in online power grid user networks from an edge-granular perspective, enabling users to fine-grained control over the privacy of their social relationships based on their perceived sensitivity. A novel privacy framework, the SPPDP model, is proposed, integrating user-aware sensitivity into an edge differential privacy DP framework to provide personalized privacy protection for social relationships. A sensitivity-based privacy-aware mechanism is designed and embedded into a trusted service provider to effectively establish privacy protection levels based on user sensitivity settings. A sensitivity-aware partitioning sampling mechanism is introduced to implement SPPDP, and a privacy threshold optimization strategy is proposed to optimize the privacy mechanism, thereby achieving an optimal trade-off between personalized privacy protection and improved data utility in online power grid user networks. The reliability of the proposed SPPDP is rigorously determined, and a series of experiments are conducted using real datasets to verify it. Compared with state-of-the-art DP mechanisms, SPPDP provides substantial utility improvements for specific graph queries by utilizing non-sensitive social relationships.

[0088] In other words, the technical solution provided by the embodiments of the present invention comprehensively considers multiple factors and introduces a fine-grained, sensitivity-aware partitioned personalized differential privacy model (SPPDP) for online power grid user networks. Specifically, SPPDP enables each user in the online power grid user network to define the sensitivity level of their social relationships individually, thereby promoting personalized privacy settings. A privacy-aware mechanism is designed, which operates within a trusted service provider and can establish a privacy protection level based on the user's perceived sensitivity settings. In addition, a sensitivity-aware partitioning sampling mechanism is proposed to implement SPPDP. Finally, through theoretical analysis and comprehensive comparative experiments on benchmark datasets, the personalized privacy protection and utility improvement achieved by the SPPDP mechanism are rigorously verified.

[0089] The embodiment of the present application further provides a device for privacy protection of power grid data. It should be noted that the device for privacy protection of power grid data can be used to execute the method for determining power supply recovery of a fault power distribution network provided by the embodiment of the present application. The device is used to realize the above-mentioned embodiment and preferred embodiment, and details are not repeated. As used below, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiment is preferably realized in software, realization in hardware or a combination of software and hardware is also possible and is contemplated.

[0090] The device for privacy protection of power grid data provided by the embodiment of the present application is introduced below.

[0091] Figure 3 FIG. 1 is a schematic diagram of a device for privacy protection of power grid data according to the embodiment of the present application. As shown in FIG. 1, the device includes an acquisition module 31, a first determination module 32, a second determination module 33, a third determination module 34, and a control module 35. Figure 3

[0092] The acquisition module 31 is configured to acquire a usage data set of a plurality of power grid users and a perception sensitivity of a plurality of elements in the usage data set, the usage data set including a plurality of usage data of the power grid users.

[0093] The first determination module 32 is configured to partition the usage data set according to the perception sensitivity to determine a plurality of subsets of the usage data set, the plurality of subsets having different perception sensitivities.

[0094] The second determination module 33 is configured to determine a sampling tuple including the subset according to at least a preset sampling mechanism of an individualized differential privacy algorithm and the subset.

[0095] The third determination module 34 is configured to determine a noise output of the subset according to at least the sampling tuple and a preset calculation mechanism of the differential privacy algorithm.

[0096] The control module 35 is configured to perform a preset level of noise protection on the subset according to the noise output to protect the power grid data.

[0097] ​By the embodiment, first, the first acquisition module acquires the usage data set of the plurality of power grid users and the perception sensitivity of the plurality of elements in the usage data set, the first determination module partitions the usage data set according to the perception sensitivity, determines a plurality of subsets of the usage data set having different perception sensitivities, the second determination module determines a sampling tuple including the subset according to at least a preset sampling mechanism of the individualized differential privacy algorithm and the subset, the third determination module determines a noise output of the subset according to at least the sampling tuple and a preset calculation mechanism of the differential privacy algorithm, and the control module performs preset level protection on the subset according to the noise output, so as to protect the privacy of the power grid data. By introducing a preset sampling mechanism of the sensitivity perception partition, the sensitivity perception partition individualized differential privacy protection model is realized, so that each user in the online power grid user network can define the sensitivity level of the social relationship of the user, thereby promoting the individualized privacy setting. The above privacy protection method can be run in a trusted service provider, and the privacy protection level can be established according to the sensitivity setting perceived by the user. The problem that the cost of privacy protection is increased due to the fact that the sensitivity perceived by the user is ignored in the prior art is solved.

[0098] In some examples, the first determination module includes a first determination unit and a second determination unit, the first determination unit is configured to determine a category of the perception sensitivity according to the perception sensitivity, and the category includes high sensitivity, medium sensitivity, low sensitivity, and non-sensitivity; and the second determination unit is configured to partition the usage data set according to the category, and determine a plurality of subsets of the usage data set.

[0099] In the scheme, by partitioning the usage data set according to the perception sensitivity, the data of different sensitivity levels in the data set can be determined, and targeted privacy protection measures can be taken. By dividing the data set into subsets of high sensitivity, medium sensitivity, low sensitivity, and non-sensitivity, different privacy protection measures can be taken for each subset, so as to ensure that the high sensitivity data is more strictly protected, and the non-sensitivity data can be more relaxed, thereby protecting the data privacy while maintaining the availability and effectiveness of the data as much as possible, effectively improving the privacy protection level of the power grid data, and reducing the cost and complexity of data processing and management.

[0100] In some examples, the second determination module includes a third determination unit, a fourth determination unit, a fifth determination unit, and a sixth determination unit, the third determination unit is configured to determine a privacy level of the subset according to the subset and the perception sensitivity corresponding to the subset, and determine a privacy budget according to the privacy level; the fourth determination unit is configured to determine a privacy threshold of the subset according to the privacy budget; the fifth determination unit is configured to determine an element of the subset according to the usage data set, the privacy threshold, and the privacy level, and obtain the subset; and the sixth determination unit is configured to determine a sampling tuple including the subset according to the subset, the privacy budget, and the privacy threshold.

[0101] In the scheme, by determining the privacy level and privacy budget of the subset, a suitable privacy threshold can be set according to specific needs, so as to maintain the effectiveness of the data as much as possible while protecting the privacy of the user, and according to the privacy threshold and the elements of the subset, the sampling tuple including the subset can be determined, and the data is further confused to increase the privacy protection, and by using the personalized differential privacy algorithm, the effectiveness and usability of the data can be maintained as much as possible on the premise of protecting the privacy of the user, so as to achieve a balance in data analysis and application, and by determining the sampling mechanism and the subset, the dimension and sensitivity of the data can be effectively reduced, the risk of data leakage can be reduced, and the security and privacy protection level of the data can be improved.

[0102] In some examples, the third determining module includes an obtaining unit and a seventh determining unit, the obtaining unit is configured to obtain the query function, and the seventh determining unit is configured to determine the noise output of the subset according to the query function, the sampling tuple and the pre-designed calculation mechanism.

[0103] In the scheme, by using the differential privacy algorithm and the noise output mode, the usability and accuracy of the data can be ensured while protecting the privacy of the user, and by performing the query function and the noise output processing of the subset on the data, the leakage of sensitive information and the re-identification of the data can be effectively prevented, so as to protect the privacy of the user.

[0104] In some examples, the above device further includes a fourth determining module, the fourth determining module is configured to determine the privacy level of the boundary of the adjacent subset at least according to the differential privacy algorithm model and the symmetric difference of the adjacent subset.

[0105] In the scheme, by using the differential privacy algorithm model and calculating the symmetric difference of the adjacent subset, the privacy protection degree between different data sets can be evaluated, and the privacy level between the data sets can be determined, so as to effectively protect the privacy information of the user while ensuring the accuracy of the data analysis result, prevent privacy leakage and abuse, ensure that the personal privacy information of the user will not be leaked in the process of using and sharing the power grid data, and improve the data security and privacy protection level.

[0106] In some examples, the above device further includes a fifth determining module, the fifth determining module is configured to determine the privacy budget of the boundary of the adjacent subset at least according to the personalized differential privacy algorithm model, the privacy level and the symmetric difference of the adjacent subset.

[0107] In the scheme, by using the personalized differential privacy algorithm model, the privacy of the power grid data can be effectively protected, and it is ensured that the personal sensitive information will not be leaked when the data is used, and by determining the privacy budget of the boundary of the adjacent subset, the allowable privacy leakage degree in the process of data publishing or querying can be determined, so as to better balance the demand of data privacy protection and data analysis.

[0108] In some examples, the preset sampling mechanism is as follows: wherein, δ is a privacy threshold corresponding to a category of the perceptual sensitivity, ∈ i is a privacy level, and ω(r) is an element in the obtained subset.

[0109] In this scheme, by setting different privacy thresholds and privacy levels, the sampling amount and quality of data can be controlled, thereby protecting the privacy of users while ensuring the effectiveness and usability of data, effectively reducing the risk of sensitive data leakage, while ensuring the accuracy of data analysis. By randomly selecting subset elements in the data set, the invasion of individual users can be reduced, and the privacy of users is protected to some extent.

[0110] The power grid data privacy protection device includes a processor and a memory. The above-mentioned acquisition module, the first determination module, the second determination module, the third determination module, and the control module are all stored in the memory as program units, and the corresponding functions are realized by the processor executing the above-mentioned program units stored in the memory. The above-mentioned modules are located in the same processor; or, the above-mentioned modules are located in different processors in any combination.

[0111] The processor includes a core, and the core retrieves the corresponding program unit from the memory. The core can be set to one or more, and the problem that the existing technology ignores the differences in privacy preferences or sensitivities between users in the research on power grid data privacy protection can be solved by adjusting the core parameters.

[0112] The memory can include non-permanent memory in a computer readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0113] The embodiment of the present application provides a computer readable storage medium, which includes a stored program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the power grid data privacy protection method when the program is running.

[0114] The embodiment of the present application provides a processor, which is used to run a program, wherein the processor executes the power grid data privacy protection method when the program is running.

[0115] A computer program product includes a non-volatile computer readable storage medium, the non-volatile computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the power grid data privacy protection method in the embodiments of the present application.

[0116] The application also provides an electronic device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a method for performing the power grid data privacy protection method in any of the above.

[0117] It is apparent that those skilled in the art should understand that the modules or steps of the application described above can be realized by general computing devices, which can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps can be manufactured into a single integrated circuit module. Thus, the application is not limited to any specific combination of hardware and software.

[0118] Those skilled in the art should understand that the embodiments of the application can be provided as a method, a system, or a computer program product. Therefore, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0119] The application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The device that implements the functions specified in one or more flows and / or blocks.

[0120] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1the function(s) specified in the block or blocks.

[0121] These computer program instructions can also be loaded into computer or other programmable data processing devices to cause a series of operational steps to be performed on the computer or other programmable devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable devices provide steps for implementing the flowchart block(s) or flowchart flow(s) and / or portions thereof. Figure 1 the flowchart block(s) or flowchart flow(s) and / or portions thereof. Figure 1 the function(s) specified in the block or blocks.

[0122] In one typical configuration, computer device includes one or more processors (CPUs), input / output interface, network interface, and memory.

[0123] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the computer stores information about an operating system, application software, and / or the like. Memory is an example of computer readable media.

[0124] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules 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, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "comprising", "comprises", "including", "includes" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article or apparatus that comprises the element.

[0126] The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A method for protecting the privacy of power grid data, characterized in that, The method includes: Obtain usage datasets from multiple power grid users and the perceptual sensitivity of multiple elements in the usage datasets, wherein the usage datasets include multiple usage data from power grid users; The dataset is partitioned according to the perceived sensitivity to determine multiple subsets of the dataset, and the multiple subsets have different perceived sensitivities. Based at least on the preset sampling mechanism of the personalized differential privacy algorithm and the subset, a sampled tuple including the subset is determined; The noise output of the subset is determined at least based on the preset calculation mechanism of the sampled tuples and the differential privacy algorithm; Based on the noise output, a preset level of noise reduction protection is applied to the subset to protect the privacy of the power grid data; The step of determining the sampled tuples including the subset based at least on the preset sampling mechanism of the personalized differential privacy algorithm and the subset includes: Based on the subset and the perception sensitivity corresponding to the subset, the privacy level of the subset is determined, and the privacy budget is determined based on the privacy level; Based on the privacy budget, determine the privacy threshold for the subset; The subset is obtained by determining the elements of the subset based on the dataset used, the privacy threshold, and the privacy level; Based on the subset, the privacy budget, and the privacy threshold, a sample tuple including the subset is determined.

2. The privacy protection method according to claim 1, characterized in that, The step of partitioning the usage dataset according to the perceptual sensitivity to determine multiple subsets of the usage dataset includes: Based on the perceived sensitivity, the category of the perceived sensitivity is determined, and the category includes high sensitivity, medium sensitivity, low sensitivity and no sensitivity; The dataset is partitioned according to the category to determine multiple subsets of the dataset.

3. The privacy protection method according to claim 1, characterized in that, The step of determining the noise output of the subset based at least on the sampled tuples and a preset calculation mechanism of the differential privacy algorithm includes: Get the query function; The noise output of the subset is determined based on the query function, the sampled tuple, and the preset calculation mechanism.

4. The privacy protection method according to claim 1, characterized in that, The privacy protection method also includes: The privacy level of the boundary of the adjacent subsets is determined at least based on the differential privacy algorithm model and the symmetric difference between the adjacent subsets.

5. The privacy protection method according to claim 1, characterized in that, The privacy protection method also includes: The privacy budget for the boundaries of adjacent subsets is determined based at least on the personalized differential privacy algorithm model, the privacy level, and the symmetric difference between adjacent subsets.

6. The privacy protection method according to claim 1, characterized in that, The preset sampling mechanism is as follows: ， in, Privacy thresholds corresponding to the categories of perception sensitivity, For privacy level, The elements in the obtained subset.

7. A privacy protection device for power grid data, characterized in that, The device includes: The acquisition module is used to acquire usage datasets of multiple power grid users and the perception sensitivity of multiple elements in the usage datasets, wherein the usage datasets include multiple usage data of power grid users; The first determining module is used to partition the usage dataset according to the perception sensitivity, and determine multiple subsets of the usage dataset, wherein the multiple subsets have different perception sensitivities; The second determining module is used to determine a sampling tuple including the subset based at least on the preset sampling mechanism of the personalized differential privacy algorithm and the subset; The third determining module is used to determine the noise output of the subset based at least on the sampled tuples and the preset calculation mechanism of the differential privacy algorithm; The control module is used to perform a preset level of noise protection on the subset based on the noise output, so as to protect the privacy of the power grid data; The second determining module includes: The third determining unit is used to determine the privacy level of the subset based on the subset and the perception sensitivity corresponding to the subset, and to determine the privacy budget based on the privacy level; The fourth determining unit is used to determine the privacy threshold of the subset based on the privacy budget; The fifth determining unit is used to determine the elements of the subset based on the dataset used, the privacy threshold, and the privacy level, thereby obtaining the subset; The sixth determining unit is used to determine a sampled tuple including the subset based on the subset, the privacy budget, and the privacy threshold.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the method for protecting the privacy of power grid data as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a privacy protection method for performing power grid data according to any one of claims 1 to 6.

Images