Data processing method and system of power grid and storage medium

Abstract

The invention discloses a data processing method and system of a power grid and a storage medium. The method comprises the steps of obtaining first power grid associated data collected by a plurality of embedded devices in a power grid, and performing initial differential privacy processing on the first power grid associated data for each group of the first power grid associated data to obtain second power grid associated data; and performing aggregation processing on the multiple groups of second power grid associated data through an edge computing node to obtain target power grid associated data, and uploading the target power grid associated data to a cloud. And the data processing security is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data processing method, system and storage medium for a power grid. Background Art

[0002] In smart grids, embedded devices distributed at various nodes continuously collect sensitive data such as the grid operation status, which needs to be initially processed and aggregated by edge computing nodes before being uploaded to the cloud or central data center for in-depth analysis and decision support.

[0003] However, traditional data processing methods have significant shortcomings in protecting user privacy and ensuring data security. Summary of the invention

[0004] The present invention provides a data processing method, system and storage medium for a power grid, so as to solve the problem of low security of data processing in the power grid.

[0005] According to one aspect of the present invention, a method for processing data of a power grid is provided, the method comprising:

[0006] Acquire first power grid-related data collected by a plurality of embedded devices in the power grid, and for each group of the first power grid-related data, perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data;

[0007] Aggregate multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data, and upload the target power grid-related data to the cloud.

[0008] According to another aspect of the present invention, there is provided a data processing system for a power grid, characterized in that it comprises:

[0009] A data acquisition module, configured to acquire first power grid-related data collected by a plurality of embedded devices in the power grid, and for each group of the first power grid-related data, perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data;

[0010] The data uploading module is used to aggregate the plurality of groups of the second power grid-related data through the edge computing node to obtain the target power grid-related data, and upload the target power grid-related data to the cloud.

[0011] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data processing method for the power grid described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data processing method for a power grid described in any embodiment of the present invention when executed.

[0016] The technical solution of the embodiment of the present invention obtains first power grid-related data collected by multiple embedded devices in the power grid, and performs initial differential privacy processing on the first power grid-related data for each group of the first power grid-related data to obtain second power grid-related data; performs preliminary differential privacy processing on the embedded device end to ensure the security of the first power grid-related data, aggregates multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data, and uploads the target power grid-related data to the cloud, thereby solving the problem of low data processing security in the power grid and achieving the beneficial effect of improving data processing security.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a flow chart of a data processing method for a power grid provided according to Embodiment 1 of the present invention;

[0020] Figure 2 is a flow chart of a data processing method for a power grid provided according to a second embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of the structure of a data processing system for a power grid provided according to a third embodiment of the present invention;

[0022] Figure 4 It is a structural schematic diagram of an electronic device for implementing the data processing method for a power grid according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Embodiment 1

[0026] Figure 1 A flowchart of a data processing method for a power grid is provided for the first embodiment of the present invention. This embodiment is applicable to the data processing of a power grid. The method can be executed by a data processing system for a power grid. The data processing system for a power grid can be implemented in the form of hardware and / or software. The data processing system for a power grid can be configured in an electronic device. Figure 1 As shown, the method includes:

[0027] S110, obtaining first power grid-related data collected by multiple embedded devices in the power grid, and performing initial differential privacy processing on each group of the first power grid-related data to obtain second power grid-related data.

[0028] The first grid-related data can be understood as the original grid-related data, and the second grid-related data can be understood as the data after the initial differential privacy processing.

[0029] Optionally, the data collected by the device includes power consumption behavior data, power distribution network status data and charging pile charging data; the embedded device includes at least one of a smart meter, a power distribution terminal and an electric vehicle charging pile. Exemplarily, the power consumption behavior data includes at least one of power consumption, power consumption time and power consumption mode. The power distribution network status data includes at least one of voltage, current, power and power factor, and the charging pile charging data includes at least one of charging current, charging voltage, charging power and charging time.

[0030] Specifically, the first grid-related data collected by multiple embedded devices in the grid are obtained, and initial differential privacy processing is performed on each group of the collected first grid-related data to obtain the second grid-related data after the initial differential privacy processing. Noise is introduced into the first grid-related data to ensure that a single data point (such as the electricity consumption data of a smart meter) will not have a significant impact on the overall data analysis results, while protecting data security and maintaining the statistical characteristics and analysis value of the data.

[0031] Optionally, the initial differential privacy processing of the initial power grid-associated data to obtain second power grid-associated data includes: quantizing the initial power grid-associated data based on a preset quantization step size to obtain quantized power grid-associated data; sampling a pre-constructed Laplace density function to obtain Laplace noise; and adding noise to the quantized power grid-associated data based on the Laplace noise to obtain second power grid-associated data.

[0032] Specifically, the initial power grid-associated data is quantized based on a preset quantization step size, and the continuous data values ​​are converted into discrete data values. Through quantization, the original continuous data can be converted into a discrete form that is easy to process and store, and it also helps to reduce the complexity of the data. Noise samples are extracted from the Laplace density function, and noise is added to the quantized power grid-associated data based on the obtained Laplace noise. The noise samples are added to the quantized power grid-associated data to obtain the second power grid-associated data.

[0033] Exemplarily, by quantifying the initial grid-related data, the scope of data to be processed is reduced:

[0034]

[0035] Wherein, a represents initial grid-related data, Δ represents a preset quantization step, and Q(a) represents quantized grid-related data.

[0036] Optionally, construct the Laplace density function using the following formula:

[0037]

[0038] Where λ represents the scale parameter of the Laplace distribution and x represents the random variable of the noise.

[0039] Laplace noise is obtained by sampling from the probability density function, so:

[0040] noise = Lap(λ);

[0041] Where Lap(λ) represents sampling from the Laplace distribution.

[0042]

[0043] Among them, Δ 1 represents the sensitivity of the initial power grid related data, ∈ 1 represents the privacy budget.

[0044] The embedded device adds noise to the quantized grid-related data Q(a) to obtain the noisy data x':

[0045]

[0046] Wherein, a' represents the second power grid associated data.

[0047] Optionally, a dynamic noise adjustment strategy is adopted in the preliminary differential privacy processing to dynamically adjust the noise intensity according to the computing power of the embedded device and the importance of the first power grid-related data, as follows:

[0048]

[0049] Where: λ represents the scale parameter of the Laplace distribution; Δ 1 represents the sensitivity of the initial power grid-related data, that is, the range of quantified data variation, ∈ 1 represents the privacy budget, α represents the device resource adjustment coefficient, which is used to adjust the impact of device computing resources; represents the computing resource utilization of the device, which is measured based on the CPU load of the embedded device; β represents the data importance adjustment coefficient; I(a) represents the importance index of the initial power grid-related data, which is set according to the sensitivity of the initial power grid-related data.

[0050] Optionally, after performing initial differential privacy processing on the first power grid-related data to obtain second power grid-related data, it also includes: encrypting the second power grid-related data, and updating the second power grid-related data based on the encrypted data.

[0051] Specifically, in this embodiment, the encryption algorithm adopts the lightweight symmetric encryption algorithm AES (Advanced Encryption Standard); the key management uses the key exchange protocol based on elliptic curve cryptography; each embedded device pre-exchanges the public key with its corresponding edge computing node; and the session key is generated through the key exchange protocol for symmetric encryption;

[0052] Exemplarily, the specific encryption process is as follows: Divide the data after differential privacy processing into blocks, each block size is 128 bits. Use the AES-128 algorithm and session key to encrypt each data block. Use the CipherBlock Chaining (CBC) mode to enhance security, and use a randomly generated initialization vector (IV). Calculate the Hash-based Message Authentication Code (HMAC) of the encrypted data, using the SHA-256 hash function. The HMAC key is managed separately from the encryption key to improve security. Construct the data packet format: [Device ID] [Timestamp] [IV] [Encrypted data] [HMAC] The device ID and timestamp are included in plain text for data management and synchronization. Communication protocol: Use the lightweight message queue telemetry transport protocol MQTT (Message Queuing Telemetry Transport) protocol for data transmission. Configure the transport layer security protocol TLS (Transport Layer Security) to protect the MQTT connection. Implement a data compression algorithm to reduce the amount of transmitted data. Use a breakpoint resume mechanism to ensure data integrity in the event of network instability.

[0053] S120. Aggregate the plurality of groups of the second power grid-related data through an edge computing node to obtain target power grid-related data, and upload the target power grid-related data to the cloud.

[0054] Optionally, after receiving the encrypted data, the edge computing node decrypts the data; data reception and verification: receiving the encrypted data packet through the MQTT message server MQTT broker; verifying the integrity and authenticity of the data packet: checking the validity of the device ID, verifying the timestamp, preventing replay attacks, and using the pre-shared HMAC key to verify the message authentication code HMAC to ensure data integrity. The private key of the edge node and the public key of the corresponding embedded device are used to regenerate the session key through the key exchange protocol ECDH protocol. Exemplarily, extract the information value IV (Information Value) and the encrypted data. Decrypt using the AES-128 algorithm and the recovered session key in CBC mode. Decrypt the data in blocks, with each block being 128 bits. After decryption, calculate the hash value of the data and compare it with the hash value of the original data to ensure the correctness of the decryption. If the data has been compressed, use the corresponding decompression algorithm to decompress it. Convert the decrypted data into the data format used internally by the edge computing node. Temporarily store the decrypted data in a secure memory area in preparation for subsequent processing. Record key information of the decryption process, including device ID, timestamp, decryption status, etc., but do not record sensitive data content. Implement error handling mechanisms to handle and report abnormal situations such as decryption failures and data corruption. After decryption is complete, securely clear the keys and other sensitive information in memory.

[0055] The technical solution of the embodiment of the present invention obtains first power grid-related data collected by multiple embedded devices in the power grid, and performs initial differential privacy processing on the first power grid-related data for each group of the first power grid-related data to obtain second power grid-related data; performs preliminary differential privacy processing on the embedded device end to ensure the security of the first power grid-related data, aggregates multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data, and uploads the target power grid-related data to the cloud, thereby solving the problem of low data processing security in the power grid and achieving the beneficial effect of improving data processing security.

[0056] Embodiment 2

[0057] Figure 2 A flowchart of a data processing method for a power grid provided in Embodiment 2 of the present invention, this embodiment and the above-mentioned embodiment are similar to how to aggregate multiple groups of the second power grid-related data through edge computing nodes to obtain further refinement of target power grid-related data. Optionally, the aggregating multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data includes: aggregating multiple groups of the second power grid-related data based on a preset density clustering algorithm to obtain aggregated power grid-related data; performing multi-dimensional differential privacy processing on the aggregated power grid-related data to obtain target power grid-related data.

[0058] like Figure 2 As shown, the method includes:

[0059] S210, obtaining first power grid-related data collected by multiple embedded devices in the power grid, and performing initial differential privacy processing on each group of the first power grid-related data to obtain second power grid-related data.

[0060] S220: Aggregate the plurality of groups of the second power grid-related data based on a preset density clustering algorithm to obtain aggregated power grid-related data.

[0061] The aggregated power grid-related data may be understood as multi-dimensional power grid-related data obtained by merging and aggregating multiple groups of the second power grid-related data.

[0062] Specifically, a plurality of groups of the second power grid associated data are aggregated by using a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) density clustering algorithm to obtain aggregated power grid associated data.

[0063] S230, performing multi-dimensional differential privacy processing on the aggregated power grid-related data to obtain target power grid-related data, and uploading the target power grid-related data to the cloud.

[0064] Among them, the target power grid-related data can be understood as the power grid-related data after multi-dimensional differential privacy processing.

[0065] Specifically, multi-dimensional differential privacy processing is performed on the multi-dimensional aggregated power grid-related data to determine the privacy budget, which determines the degree of privacy protection. A smaller privacy budget value indicates stronger privacy protection, but may lead to a decrease in the accuracy of data analysis results. Sensitivity is calculated, and sensitivity reflects the maximum impact of data changes on the analysis results. In the case of multiple dimensions, it is necessary to calculate the sensitivity of each dimension and the cross-sensitivity between dimensions. According to the privacy budget and sensitivity, an appropriate amount of random noise is added to each dimension. After multi-dimensional differential privacy processing, the aggregated power grid-related data is converted into target power grid-related data.

[0066] Optionally, the multi-dimensional differential privacy processing of the aggregated grid-related data to obtain target grid-related data includes: determining a covariance matrix corresponding to the aggregated grid-related data, performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector matrix and a diagonal matrix; constructing a principal component space based on the eigenvector matrix and the diagonal matrix, adding adaptive noise to the data points after projection of the aggregated grid-related data in the principal component space, and reconstructing the data points with added noise to obtain target grid-related data.

[0067] Specifically, the covariance matrix corresponding to the aggregated power grid-related data is calculated, and the covariance matrix is ​​subjected to eigenvalue decomposition to obtain eigenvectors and corresponding eigenvalues. The eigenvector represents the principal component direction of the data, and the eigenvalue represents the variance size in these directions. The eigenvectors are organized into an eigenvector matrix, and the eigenvalues ​​are arranged in descending order and placed in a diagonal matrix. According to the size of the eigenvalue, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected to construct the principal component space. The principal component space contains the main direction of change in the data. The original data is projected into the principal component space to obtain the projected data points. According to the requirements of differential privacy, the noise level to be added is determined. In the principal component space, adaptive noise is added to the projected data points. The addition of adaptive noise can be adjusted according to the position of the data point, the characteristics of the principal component space, and the requirements of privacy protection. The data points after adding noise are reversely projected from the principal component space back to the original data space. The reversely projected data points are the target power grid-related data with differential privacy protection added, and the target power grid-related data is uploaded to the cloud.

[0068] Exemplarily, multi-dimensional differential privacy processing is performed on the aggregated power grid-related data based on an adaptive differential privacy budget allocation strategy.

[0069] The adaptive differential privacy budget allocation is performed on the aggregated grid-related data using the following formula:

[0070] ∈ 4 =∈ total -∈ 1 ;

[0071]

[0072] Among them, ∈ 4 represents the privacy budget of multi-dimensional differential privacy processing; ∈ total represents the total privacy budget; ∈ 1 represents the privacy budget used by the initial differential privacy; ∈ 4,i represents the privacy budget allocated to the i-th subtask; w i represents the weight of the i-th task, which is dynamically adjusted according to the sensitivity and importance of the data; n represents the number of subtasks.

[0073] In this embodiment, by dynamically allocating the privacy budget, the system can flexibly adjust the privacy protection strength according to the importance of different tasks, ensuring that important data processing tasks can obtain sufficient privacy budget while protecting privacy, thereby improving the overall data utility.

[0074] For example, for each device j, data x j Calculate the locality sensitive hash:

[0075] LSH j = hash(x j ,r);

[0076] Where r represents a random projection vector.

[0077] For example, we use the differentially private version of local sensitive hashing for anomaly detection:

[0078]

[0079] Among them, Δ 2 represents the sensitivity of locality sensitive hashing, ∈ 4,i represents the privacy budget allocated to subtask i.

[0080] based on Perform clustering to identify potential anomalies.

[0081] In this embodiment, local sensitive hashing (LSH) and differential privacy version of LSH are used for anomaly detection, which not only protects data privacy but also efficiently identifies potential abnormal data. The application of DBSCAN clustering algorithm further improves the accuracy of anomaly detection, and is particularly suitable for processing complex data distribution.

[0082] Adaptive Weighted Aggregation:

[0083] y=∑(b j *a j ) / ∑b j ;

[0084] b j =q j *exp(-β*∈ j );

[0085] Among them, y represents the aggregated grid-related data, a j b represents the first power grid associated data of the embedded device j; j represents the weight of embedded device j, q j represents the data quality score of embedded device j,∈ j represents the privacy budget used by embedded device j, and β represents the privacy sensitivity parameter.

[0086] In this embodiment, the weight of each device is dynamically adjusted by considering data quality and privacy budget usage, thereby ensuring a balance between the quality of the aggregation results and privacy protection; the impact of low-quality or high-privacy risk data is effectively mitigated, and the reliability of the aggregation results is improved.

[0087] Optionally, adaptive noise is added to the projected data points of the aggregated power grid-related data using the following formula:

[0088]

[0089] Among them, ∧' i represents the i-th data point after adding noise, ∧ i represents the i-th data point in the aggregated grid-related data; Lap() represents the Laplace distribution noise function, Δ n represents the sensitivity of the nth dimension, ∈ represents the privacy budget allocated to the subtask; φ i Represents the relative importance weight of the i-th data point.

[0090] φ i =φ i / ∑φ i ;

[0091] Among them, φ i Represents the relative importance weight of the i-th data point.

[0092] Exemplarily, the noisy data is reconstructed by the following formula:

[0093] y'=U(∧ i ) 1 / 2 U T *y;

[0094] Among them, (∧ i ) 1 / 2 It means that ∧' is subjected to 1 / 2 power operation, and ∧' represents a diagonal matrix whose diagonal elements are ∧' i The value of , y' represents the data point after adding noise.

[0095] In this embodiment, covariance analysis and eigenvalue decomposition are performed on the aggregated data, and then adaptive noise is added in the principal component space to protect the multidimensional characteristics of the data. By adding more noise to the main features and less noise to the secondary features, the statistical characteristics of the data are retained to the maximum extent while protecting privacy.

[0096] Furthermore, the Clustering is performed to identify potential anomalies, and the DBSCAN algorithm is used for clustering using the following formula:

[0097] DBSCAN(DP LSH ,r,MinPts);

[0098] Among them, DP LSH represents a set of differentially private local sensitive hash values, r represents the neighborhood radius, and MinPts represents the minimum number of neighbors required to form a core point.

[0099] Exemplarily, for each data point i, the anomaly score is calculated by the following formula:

[0100] AS i =(k-dist i -μ k ) / σ k ;

[0101] Among them, AS i represents the anomaly score of data point i, k-dist i represents the distance from data point i to its kth nearest neighbor, μ k Represents all k-dist i The average value, σ k Represents all k-dist i The standard deviation of the values, k is MinPts-1.

[0102] Specifically, if the anomaly score is greater than a preset anomaly score threshold, the data point is marked as anomaly, wherein the preset anomaly score threshold can be preset based on experience, and this embodiment does not limit it.

[0103] Exemplarily, the quality score is adjusted for each data point i by the following formula:

[0104] q' i =q i *(1-γ*AS i );

[0105] Among them, q' i represents the adjusted quality score, q i represents the quality score before adjustment, γ represents the adjustment factor, 0<γ<1.

[0106] Exemplarily, the privacy budget is adjusted according to the anomaly score for each data point i in the following manner:

[0107] ∈' i =∈ i *(1-δ*AS i );

[0108] Among them, ∈' i represents the adjusted privacy budget of data point i, ∈ irepresents the privacy budget of data point i before adjustment, δ represents the adjustment factor, 0<δ<1.

[0109] In this embodiment, the data quality score and privacy budget are dynamically adjusted based on the anomaly score, so that the system can adaptively handle abnormal data, which not only reduces the impact of abnormal data, but also enhances the protection of potential sensitive information.

[0110] Exemplarily, the preset anomaly score threshold θ is regularly updated by the following formula:

[0111] θnew=θold+η*(μAS-θold);

[0112] Among them, θnew represents the updated preset anomaly score threshold, λold represents the preset anomaly score threshold, η represents the learning rate, 0<η<1, μ AS Represents the average anomaly score of the current batch.

[0113] In the embodiment of the present invention, by regularly updating the anomaly detection threshold, the system can adapt to changes in data distribution, maintain the effectiveness of anomaly detection, and improve the robustness and long-term stability of the system.

[0114] The technical solution of the embodiment of the present invention aggregates multiple groups of the second power grid-related data based on a preset density clustering algorithm to obtain aggregated power grid-related data; and performs multi-dimensional differential privacy processing on the aggregated power grid-related data to obtain target power grid-related data. The efficiency, adaptability and security of data processing are significantly improved, while protecting data privacy and improving data availability.

[0115] Embodiment 3

[0116] Figure 3 This is a schematic diagram of the structure of a data processing system for a power grid provided by Embodiment 3 of the present invention. Figure 3 As shown, the system includes: a data acquisition module 310 and a data upload module 320.

[0117] Among them, the data acquisition module 310 is used to obtain the first power grid-related data collected by multiple embedded devices in the power grid, and for each group of the first power grid-related data, perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data; the data upload module 320 is used to aggregate multiple groups of the second power grid-related data through the edge computing node to obtain target power grid-related data, and upload the target power grid-related data to the cloud.

[0118] The technical solution of the embodiment of the present invention obtains first power grid-related data collected by multiple embedded devices in the power grid through a data acquisition module, and performs initial differential privacy processing on the first power grid-related data for each group of the first power grid-related data to obtain second power grid-related data; performs preliminary differential privacy processing on the embedded device end to ensure the security of the first power grid-related data, and then, through the data upload module, aggregates multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data, and uploads the target power grid-related data to the cloud, thereby solving the problem of low data processing security in the power grid and achieving the beneficial effect of improving data processing security.

[0119] Optionally, the data acquisition module includes:

[0120] A data quantization unit, configured to quantize the initial power grid associated data based on a preset quantization step size to obtain quantized power grid associated data;

[0121] A noise acquisition unit, used for sampling a pre-built Laplace density function to obtain Laplace noise;

[0122] A noise adding unit is used to add noise to the quantized power grid associated data based on the Laplace noise to obtain second power grid associated data.

[0123] Optionally, the noise acquisition unit is specifically used to:

[0124] The Laplace density function is constructed by the following formula:

[0125]

[0126] Where λ represents the scale parameter of the Laplace distribution and x represents the random variable of the noise.

[0127] Optionally, the data uploading module includes:

[0128] A data aggregation unit, configured to aggregate the plurality of groups of the second power grid-related data based on a preset density clustering algorithm to obtain aggregated power grid-related data;

[0129] The multi-dimensional differential privacy processing unit is used to perform multi-dimensional differential privacy processing on the aggregated power grid-related data to obtain target power grid-related data.

[0130] Optionally, the multi-dimensional differential privacy processing unit includes:

[0131] an eigendecomposition subunit, configured to determine a covariance matrix corresponding to the aggregated power grid associated data, and perform eigenvalue decomposition on the covariance matrix to obtain an eigenvector matrix and a diagonal matrix;

[0132] A data reconstruction subunit is used to construct a principal component space based on the eigenvector matrix and the diagonal matrix, add adaptive noise to the data points after the projection of the aggregated power grid associated data in the principal component space, and reconstruct the data points after the noise is added to obtain the target power grid associated data.

[0133] Optionally, the data reconstruction subunit is specifically used to:

[0134] Adaptive noise is added to the projected data points of the aggregated grid-related data using the following formula:

[0135]

[0136] Among them, ∧' i represents the i-th data point after adding noise, ∧ i represents the i-th data point in the aggregated grid-related data; Lap() represents the Laplace distribution noise function, Δ n represents the sensitivity of the nth dimension, ∈ represents the privacy budget allocated to the subtask; φ i Represents the relative importance weight of the i-th data point.

[0137] Optionally, the system further includes:

[0138] A data encryption module is used to perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data, encrypt the second power grid-related data, and update the second power grid-related data based on the encrypted data.

[0139] Optionally, the data collected by the device includes electricity consumption behavior data, distribution network status data and charging pile charging data; the embedded device includes at least one of a smart meter, a distribution terminal and an electric vehicle charging pile.

[0140] The data processing system for a power grid provided in the embodiment of the present invention can execute the data processing method for a power grid provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0141] Embodiment 4

[0142] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0143] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0144] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0145] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as data processing of the method power grid.

[0146] In some embodiments, the data processing of the method power grid can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the data processing of the method power grid described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the data processing of the method power grid in any other suitable manner (for example, by means of firmware).

[0147] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0149] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0150] To provide interaction with a service acquirer, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the service acquirer; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the service acquirer can provide input to the electronic device. Other types of devices may also be used to provide interaction with a service acquirer; for example, the feedback provided to the service acquirer may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the service acquirer may be received in any form (including acoustic input, voice input, or tactile input).

[0151] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a service acquirer computer having a graphical service acquirer interface or a web browser through which the service acquirer can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0152] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0153] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method for a power grid, characterized in that: include: Acquire first power grid-related data collected by a plurality of embedded devices in the power grid, and for each group of the first power grid-related data, perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data; Aggregate multiple groups of the second power grid-related data through edge computing nodes to obtain target power grid-related data, and upload the target power grid-related data to the cloud.

2. The method according to claim 1, characterized in that: The performing initial differential privacy processing on the initial power grid associated data to obtain second power grid associated data includes: quantizing the initial power grid associated data based on a preset quantization step size to obtain quantized power grid associated data; The pre-constructed Laplace density function is sampled to obtain Laplace noise; Noise is added to the quantized grid-related data based on the Laplace noise to obtain second grid-related data.

3. The method according to claim 2, characterized in that The Laplace density function is constructed by the following formula: Where λ represents the scale parameter of the Laplace distribution and x represents the random variable of the noise.

4. The method according to claim 1, characterized in that The aggregating the plurality of groups of the second power grid-related data by the edge computing node to obtain the target power grid-related data includes: Aggregating the plurality of groups of the second power grid-related data based on a preset density clustering algorithm to obtain aggregated power grid-related data; Multi-dimensional differential privacy processing is performed on the aggregated power grid-related data to obtain target power grid-related data.

5. The method according to claim 4, characterized in that The performing multi-dimensional differential privacy processing on the aggregated power grid-related data to obtain target power grid-related data includes: Determine a covariance matrix corresponding to the aggregated power grid associated data, and perform eigenvalue decomposition on the covariance matrix to obtain an eigenvector matrix and a diagonal matrix; A principal component space is constructed based on the eigenvector matrix and the diagonal matrix. In the principal component space, adaptive noise is added to the data points after the projection of the aggregated power grid associated data, and the data points after the noise is added are reconstructed to obtain the target power grid associated data.

6. The method according to claim 5, characterized in that Adaptive noise is added to the projected data points of the aggregated grid-related data using the following formula: Among them, ∧' i represents the i-th data point after adding noise, ∧ i represents the i-th data point in the aggregated grid-related data; Lap() represents the Laplace distribution noise function, Δ n represents the sensitivity of the nth dimension, ε represents the privacy budget allocated to the subtask; φ i Represents the relative importance weight of the i-th data point.

7. The method according to claim 1, characterized in that After performing initial differential privacy processing on the first power grid associated data to obtain second power grid associated data, the method further includes: The second power grid associated data is encrypted, and the second power grid associated data is updated based on the encrypted data.

8. The method according to claim 1, characterized in that The data collected by the device include power consumption behavior data, distribution network status data and charging pile charging data; the embedded device includes at least one of a smart meter, a distribution terminal and an electric vehicle charging pile.

9. A data processing system for a power grid, characterized in that: include: A data acquisition module, configured to acquire first power grid-related data collected by a plurality of embedded devices in the power grid, and for each group of the first power grid-related data, perform initial differential privacy processing on the first power grid-related data to obtain second power grid-related data; The data uploading module is used to aggregate the plurality of groups of the second power grid-related data through the edge computing node to obtain the target power grid-related data, and upload the target power grid-related data to the cloud.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data processing method for a power grid according to any one of claims 1 to 7 when the instructions are executed.

Images