Data protection method, system and equipment of new energy power grid system and medium

Abstract

The invention relates to the technical field of power grid data protection, in particular to a data protection method, system and device of a new energy power grid system and a medium. The method comprises the steps of firstly collecting a real-time load data sequence of a new energy power grid system, then establishing a dynamic mapping relation between load characteristics and watermark positions by analyzing characteristic parameters such as a wave crest, a wave trough and a stable interval of a load curve, further determining an embedding position set of watermarks, and finally embedding watermark information into a selected position. The watermark embedding position is associated with the load characteristics, so that the watermark embedding process can adapt to the dynamic characteristics of the load data, the robustness of the watermark is ensured, and the practicability of the scheme is improved.

Description

Technical Field

[0001] This application relates to the technical field of power grid data protection, and particularly to a data protection method, system, device and medium for a new energy power grid system. Background Technique

[0002] With the continuous increase in the penetration rate of new energy in the power system, the power grid structure has become increasingly complex, and the security protection of power data has become particularly important. As an effective data protection means, digital watermarking technology can achieve data copyright protection and traceability without affecting data use.

[0003] Currently, in the power system, mainly watermark embedding methods based on discrete wavelet transform and discrete cosine transform are adopted. These methods convert power data into the transform domain, embed watermark information in the transform coefficients, and then obtain watermarked data through inverse transformation.

[0004] However, existing watermark embedding methods often adopt fixed embedding positions and unified embedding strategies, and fail to specifically select data positions more suitable for embedding watermarks, which affects the practicability of the watermark scheme; this situation needs to be further improved. Summary of the Invention

[0005] In order to solve the problem that existing watermark embedding methods fail to specifically select data positions more suitable for embedding watermarks, which affects the practicability of the watermark scheme, this application provides a data protection method, system, device and medium for a new energy power grid system, and adopts the following technical solutions: In the first aspect, this application provides a data protection method for a new energy power grid system, including the following steps: Collect the load data of the new energy power grid system to obtain a real-time load data sequence; Based on the real-time load data sequence, calculate the load curve characteristic parameters; According to the load curve characteristic parameters, establish a dynamic watermark embedding position mapping relationship; Based on the watermark embedding position mapping relationship, determine the watermark embedding position set; According to the watermark embedding position set, embed a digital watermark into the data to obtain watermarked data.

[0006] To protect the data security in the new energy power grid system, it is necessary to embed digital watermarks in the data. Since the load data of the new energy power grid system has significant dynamic characteristics, for example, the load difference between photovoltaic power generation during the day and at night is huge, and the output of the wind farm fluctuates with the change of wind speed. These dynamic characteristics make it difficult for traditional fixed-position watermark embedding methods to adapt. By adopting the above technical solution, this application first collects the real-time load data sequence of the new energy power grid system, then analyzes the characteristic parameters such as the peaks and valleys, and stable intervals of the load curve, establishes a dynamic mapping relationship between the load characteristics and the watermark position, and then determines the set of watermark embedding positions. Finally, the watermark information is embedded into the selected positions. Associating the watermark embedding positions with the load characteristics enables the watermark embedding process to adapt to the dynamic characteristics of the load data, ensuring both the robustness of the watermark and the practicality of the solution.

[0007] Optionally, the load curve characteristic parameters include the peak and valley positions of the load curve, the load stable interval, the load mutation interval, and the load periodic change characteristics.

[0008] By adopting the above technical solution, this application first collects the real-time load data sequence of the new energy power grid system, extracts multi-dimensional characteristic parameters such as the peak and valley positions, stable intervals, mutation intervals, and periodic changes of the load curve, establishes a dynamic mapping relationship between these characteristics and the watermark position, and then determines the optimal set of watermark embedding positions. Utilizing the multi-dimensional characteristic information in the load data to guide the watermark embedding process enables the watermark scheme to better adapt to the dynamic characteristics of the new energy load and improves the effectiveness of data protection.

[0009] Optionally, the method further includes the following steps: Collect new energy power generation data to obtain a power time series; Calculate the power change rate according to the power time series; Determine the number of watermark embedding bits based on the power change rate; Adjust the least significant bit of the data according to the number of watermark embedding bits to obtain the watermark embedding strength parameter.

[0010] Due to the strong volatility and uncertainty of the power output of new - energy power generation, for example, the power of a wind farm may change from full - load generation to zero - load generation in a short period of time, and the output of a photovoltaic power station may drop sharply due to cloud occlusion. Such drastic power changes will affect the embedding strength of the watermark; traditional watermark methods use fixed embedding bits and cannot adapt to the impact brought by such power fluctuations; this application first collects the power time - series of new - energy power generation, calculates the power change rate between adjacent time points, dynamically adjusts the watermark embedding bits according to the degree of power fluctuation, and then determines the adjustment strategy of the least - significant bit to obtain an adaptive watermark embedding strength parameter; by establishing a mapping mechanism between the power change rate and the watermark embedding strength, the watermark embedding process can be adaptively adjusted according to the power fluctuation situation, ensuring both the stability of the watermark and the robustness of the scheme.

[0011] Optionally, the power change rate includes the power difference between adjacent time points, the power change amount per unit time, and the power change trend feature within a preset time window.

[0012] By adopting the above - mentioned technical solution, this application captures instantaneous fluctuations by calculating the power difference between adjacent time points, characterizes continuous changes by analyzing the power change amount per unit time, and extracts the power change trend feature within a preset time window to reflect long - term fluctuations, so as to realize the refined adjustment of the watermark embedding strength; the watermark embedding process can more comprehensively adapt to the dynamic characteristics of new - energy power, improving the adaptability and reliability of the watermark scheme.

[0013] Optionally, the method further includes the following steps: Obtain the power - grid topology structure data to get the node connection relationship matrix; Calculate the node importance weights according to the node connection relationship matrix; Based on the node importance weights, determine the watermark information amount at each level; Construct a multi - level watermark coding structure according to the watermark information amount at each level.

[0014] Since there are significant differences in the importance of each node in the new - energy power - grid system, for example, the data leakage of a key substation node may lead to the collapse of the system, while the impact of data leakage of an ordinary distribution node is relatively small. This difference in node importance requires that the watermark protection strength should also be differentiated; traditional watermark methods often adopt a unified information - amount allocation strategy and fail to reflect the differentiated protection requirements of nodes; this application first obtains the topology structure data of the power grid and establishes a node connection relationship matrix, calculates its importance weights by analyzing the connection degree and location characteristics of the nodes, then determines the watermark information amount at different levels according to the weights, and finally constructs a multi - level watermark coding structure; realizing a differentiated protection mechanism based on node importance, ensuring the security of key nodes and optimizing the resource allocation of the watermark system.

[0015] Optionally, according to the node connection relationship matrix, calculate the node importance weight, which specifically includes the following steps: Obtain the node connection degree data according to the node connection relationship matrix; Calculate the power flow volume between nodes according to the node connection degree data to obtain the flux eigenvalue; Based on the flux eigenvalue, determine the positional relationship of the nodes in the network to obtain the position importance index; Calculate the comprehensive weighting coefficient according to the position importance index, the flux eigenvalue, and the node connection degree data to obtain the node importance weight.

[0016] By adopting the above technical solution, the present application first obtains the basic connection degree data through the node connection relationship matrix, then analyzes the power flow relationship between nodes to obtain the flux eigenvalue, and then combines the network position of the nodes to determine the position importance index. Finally, the characteristics of these three dimensions are comprehensively weighted to obtain a comprehensive node importance evaluation result; a multi-dimensional evaluation system including connection degree, flux, and position importance is constructed, making the calculation of node importance more scientific and reasonable, and providing a reliable basis for differential watermark protection.

[0017] Optionally, the method further includes the following steps: Based on the power change rate and the node importance weight, establish a node priority matrix; According to the node priority matrix, adjust the watermark embedding position mapping relationship to obtain an optimized mapping relationship; Based on the optimized mapping relationship, dynamically allocate the watermark embedding bits to obtain the watermark embedding strategy for each node; According to the watermark embedding strategy for each node, realize the differential embedding of watermark information to obtain hierarchical watermarked data.

[0018] Since the actual importance of a node is affected by both its topological status and power dynamic characteristics, for example, a critical node with high topological importance but significant power fluctuations is not suitable for a large amount of watermark embedding, or a general node with stable power but unimportant location does not require strong protection. This coupling relationship between dynamic characteristics and static importance makes the design of watermark protection schemes complex. Traditional watermark methods often consider power characteristics and node importance separately, making it difficult to achieve the optimal protection effect. This application first combines the power change rate and node importance weight to construct a node priority matrix, then dynamically adjusts the position mapping relationship of the watermark based on this matrix, and further allocates different numbers of watermark embedding bits to different nodes, ultimately achieving hierarchical watermark protection. By establishing a collaborative optimization mechanism between power dynamic characteristics and node static importance, the watermark scheme can achieve a better balance between protection intensity and implementation feasibility, improving the overall protection effect.

[0019] In a second aspect, this application provides a data protection system for a new energy power grid system, including: A real-time load data sequence acquisition module, configured to collect the load data of the new energy power grid system to obtain a real-time load data sequence; A load curve characteristic parameter calculation module, configured to calculate load curve characteristic parameters based on the real-time load data sequence; An embedding position mapping relationship establishment module, configured to establish a dynamic watermark embedding position mapping relationship according to the load curve characteristic parameters; A watermark embedding position set determination module, configured to determine a watermark embedding position set based on the watermark embedding position mapping relationship; A watermark-containing data generation module, configured to embed a digital watermark into data according to the watermark embedding position set to obtain watermark-containing data.

[0020] In a third aspect, this application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the data protection method for the new energy power grid system described above are implemented.

[0021] In a fourth aspect, this application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the data protection method for the new energy power grid system described above are implemented.

[0022] In summary, this application includes at least one of the following beneficial technical effects: 1. This application first collects the real-time load data sequence of the new energy power grid system, then analyzes the characteristic parameters such as the peaks and valleys and stable intervals of the load curve to establish a dynamic mapping relationship between the load characteristics and the watermark positions, and then determines the set of watermark embedding positions. Finally, the watermark information is embedded into the selected positions; by establishing an association between the watermark embedding positions and the load characteristics, the watermark embedding process can adapt to the dynamic characteristics of the load data, ensuring both the robustness of the watermark and the practicality of the solution. 2. Since the power output of new energy power generation has strong volatility and uncertainty, for example, the power of a wind farm may change from full load to zero load in a short period of time, and the output of a photovoltaic power station may drop sharply due to cloud occlusion. Such drastic power changes will affect the watermark embedding strength; traditional watermark methods use fixed embedding bits and cannot adapt to the impact of such power fluctuations; this application first collects the power time series of new energy power generation, calculates the power change rate between adjacent time points, dynamically adjusts the watermark embedding bits according to the degree of power fluctuation, and then determines the adjustment strategy for the least significant bit to obtain an adaptive watermark embedding strength parameter; by establishing a mapping mechanism between the power change rate and the watermark embedding strength, the watermark embedding process can be adaptively adjusted according to the power fluctuation situation, ensuring both the stability of the watermark and the robustness of the solution. 3. Since there are significant differences in the importance of each node in the new energy power grid system, for example, the data leakage of a key substation node may lead to the collapse of the system, while the data leakage of an ordinary distribution node has relatively little impact. This difference in node importance requires that the watermark protection strength should also be differentiated; traditional watermark methods often adopt a unified information allocation strategy and fail to reflect the differentiated protection requirements of nodes; this application first obtains the topological structure data of the power grid and establishes a node connection relationship matrix, calculates the importance weight of each node by analyzing its connection degree and location characteristics, then determines the watermark information volume at different levels according to the weight, and finally constructs a multi-level watermark coding structure; realizing a differentiated protection mechanism based on node importance, ensuring both the security of key nodes and optimizing the resource allocation of the watermark system. Description of the Drawings

[0023] Figure 1 is a schematic flow chart of a data protection method for a new energy power grid system according to an embodiment of this application; Figure 2 is a schematic flow chart of adjusting the watermark embedding strength in a data protection method for a new energy power grid system according to an embodiment of this application; Figure 3 is a schematic flow chart of constructing a multi-level watermark coding structure in a data protection method for a new energy power grid system according to an embodiment of this application; Figure 4It is a schematic flow chart of step S320 in a data protection method for a new energy power grid system according to an embodiment of the present application; Figure 5 It is a schematic flow chart of constructing a node priority matrix in a data protection method for a new energy power grid system according to an embodiment of the present application; Figure 6 It is a schematic diagram of modules of a data protection system for a new energy power grid system according to an embodiment of the present application; Figure 7 It is an internal structure diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0024] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in the present application refers to any and all possible combinations including one or more of the listed items.

[0025] Hereinafter, the terms "first" and "second" are only for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0026] The following further describes the embodiments of the present application in conjunction with the accompanying drawings of the specification.

[0027] In a first aspect, the present application provides a data protection method for a new energy power grid system. Referring to Figure 1 , the method includes the following steps: S110. Collect the load data of the new energy power grid system to obtain a real-time load data sequence.

[0028] In this embodiment, the load data of the new energy power grid system refers to the real-time power consumption load values of each node in the power grid. The real-time load data sequence represents a set of load data collected at a preset sampling interval within a continuous time window and can be expressed as L(t) = {l1, l2,..., ln}, where li represents the load value at the i-th sampling moment and n is the number of sampling points.

[0029] Specifically, by deploying load acquisition devices at key nodes of the new energy power grid system, the sampling interval is set to 5 minutes, and the load data is continuously collected for 24 hours. The acquisition device transmits the sampled data to the data processing center in real time. After eliminating outliers through data preprocessing, the real-time load data sequence in standard format is sorted in chronological order.

[0030] S120. Calculate the characteristic parameters of the load curve based on the real-time load data sequence.

[0031] Among them, the characteristic parameters of the load curve are key indicators characterizing the dynamic change law of the load data. In this embodiment, by analyzing the local and global characteristics of the load curve, multi-dimensional characteristic parameters including the positions of peaks and valleys, load stable intervals, load mutation intervals, and load periodic change characteristics are extracted. Among them, the positions of peaks and valleys reflect the distribution of extreme points of the load; the load stable interval represents the time period when the load change rate is lower than the preset threshold; the load mutation interval refers to the time period when the load changes significantly; the load periodic change characteristics describe the repetitive change pattern of the load over time.

[0032] Specifically, a hierarchical feature extraction strategy is adopted to calculate the characteristic parameters: First, the positions of peaks and valleys are identified through an extreme point detection algorithm, and the local maximum points are marked as peaks and the local minimum points are marked as valleys; then, the load change rate between adjacent sampling points is calculated, and when the change rate of multiple consecutive points is lower than the threshold, it is marked as a stable interval, and when the change rate exceeds the threshold, it is marked as a mutation interval; finally, a simple autocorrelation analysis method is used to determine the periodic characteristics of the load change by calculating the correlation coefficients at different time delays.

[0033] S130. Establish a mapping relationship between the dynamic watermark embedding positions according to the characteristic parameters of the load curve.

[0034] In this embodiment, the mapping relationship between the dynamic watermark embedding positions refers to the corresponding rule between the characteristic parameters and the watermark embedding positions.

[0035] Specifically, the system pre-constructs a mapping table between the characteristic parameter intervals and the embedding positions, divides the value range of the characteristic parameters into multiple intervals, and each interval corresponds to a group of candidate watermark embedding positions. When it is necessary to determine the embedding position, the corresponding position information is obtained by looking up the table according to the actual characteristic parameters, realizing the rapid mapping from the characteristic parameters to the embedding positions.

[0036] S140. Determine the set of watermark embedding positions based on the mapping relationship between the watermark embedding positions.

[0037] In this embodiment, the set of watermark embedding positions refers to the combination of data positions finally selected for embedding the watermark. By screening and optimizing the candidate positions obtained by mapping, the most suitable set of positions for embedding the watermark is selected.

[0038] Specifically, first, obtain the candidate position set according to the mapping relationship, and then screen it through the set position selection rules. For example, it is required that the interval between adjacent positions is not less than a preset threshold to avoid the watermark being too concentrated; at the same time, consider the importance of the data segment and preferentially select positions with a higher degree of importance. Finally, obtain the watermark embedding position set that meets the requirements.

[0039] S150. According to the watermark embedding position set, embed the digital watermark into the data to obtain the watermarked data.

[0040] In this embodiment, the digital watermark refers to the identification information that needs to be embedded into the load data and can be in the form of a binary sequence.

[0041] Specifically, first convert the watermark information into a binary sequence, and then according to the determined embedding position set, embed the watermark bits into the least significant bit of the data at the corresponding positions in turn. The embedding of the watermark information is achieved by replacing the least significant bit of the original data, and the load data sequence containing the watermark information is obtained.

[0042] In one embodiment, referring to Figure 2 , the method further includes the following steps: S210. Collect the new energy power generation data to obtain the power time series.

[0043] In this embodiment, the new energy power generation data includes the real-time power output data of the wind farm and the photovoltaic power station. The power time series represents the set of power sampling data within a continuous time period and is used to reflect the dynamic characteristics of new energy power generation.

[0044] Specifically, the system installs power acquisition devices at the key measurement points of each new energy power generation unit. The acquisition devices upload the data to the nearby data aggregation nodes in real time, and then the aggregation nodes uniformly transmit it to the central database. The database sorts and fills the power data according to the time stamp to form a power time series in a standard format.

[0045] S220. Calculate the power change rate according to the power time series.

[0046] Among them, the power change rate includes the power difference between adjacent time points, the power change amount per unit time, and the power change trend feature within a preset time window.

[0047] In this embodiment, the system calculates the power change characteristics from three levels: instantaneous, short-term, and medium- and long-term through a pre-designed feature extraction rule library.

[0048] Specifically, first calculate the power difference between adjacent sampling points to establish a difference sequence; then, within a 5-minute sliding window, statistically analyze the power change using a simple cumulative quantization method; finally, extract the change trend features from the data within a 30-minute window through basic statistical analysis methods. The system has pre-established a feature extraction rule library that contains calculation formulas and parameter thresholds for various features, and can flexibly adjust the analysis parameters according to actual needs.

[0049] S230. Determine the number of watermark embedding bits based on the power change rate.

[0050] In this embodiment, the system can quickly determine the number of watermark embedding bits suitable for the current power change situation by pre-establishing a correspondence table between the power change rate and the embedding bits.

[0051] Specifically, the system establishes a mapping table that includes different power change rate intervals, and each interval corresponds to a recommended number of watermark embedding bits. The system looks up the recommended embedding bits in the table based on the currently calculated power change rate and can make fine-tuning according to the actual situation if necessary. For example, when the power is relatively stable, more embedding bits can be selected, while when the power fluctuates violently, the number of embedding bits is correspondingly reduced.

[0052] S240. Adjust the least significant bit of the data according to the number of watermark embedding bits to obtain the watermark embedding strength parameter.

[0053] In this embodiment, a binary bit adjustment method is used to control the watermark embedding strength. According to the preset valid bit adjustment rule, the adjustment range of the least significant bit is determined according to the precision requirements of different types of data.

[0054] Specifically, the system pre-establishes a correspondence table between the data type and the valid bit range, and sets different adjustment ranges for data with different precision requirements. The system quickly determines the adjustment range by looking up the table, and then combines the previously determined number of embedding bits to generate the final embedding strength parameter.

[0055] In one embodiment, referring to Figure 3 , the method further includes the following steps: S310. Obtain the power grid topology structure data to get the node connection relationship matrix.

[0056] In this embodiment, the power grid topology structure data describes the connection relationship between each node in the new energy power grid system. The node connection relationship matrix A is an N×N matrix (N is the number of nodes) and is used to represent the connection state between nodes.

[0057] Specifically, the system first imports the basic topology data from the power grid management system, including information such as node identifiers, connection relationships, and connection attributes. Then, it establishes a node index table to map the node identifiers to matrix indices. Finally, it generates a connection relationship matrix, where Aij = 1 indicates a direct connection between node i and node j, and Aij = 0 indicates no direct connection.

[0058] S320. Calculate the node importance weights based on the node connection relationship matrix.

[0059] In this embodiment, the node importance is calculated from two dimensions: the local connection characteristics and the global network status of the node through a preset evaluation rule library.

[0060] Specifically, the system first calculates the basic connection characteristics of the node, including the connection degree (the number of nodes directly connected to this node) and the connection strength (the weighted connection number considering the connection attributes). Then, it analyzes the position of the node in the network through a graph traversal algorithm to identify the nodes on the critical path. Finally, according to the preset weight calculation rules, various indicators are integrated to obtain the node importance weights. The system maintains an evaluation rule library containing the calculation methods and weight parameters of various indicators.

[0061] S330. Determine the watermark information amounts at each level based on the node importance weights.

[0062] In this embodiment, a hierarchical watermark allocation strategy is adopted. Through a preset allocation rule table, the watermark information amounts at different levels are determined according to the node importance weights.

[0063] Specifically, a mapping table between the importance weight intervals and the watermark information amounts is established, and the nodes are divided into different levels according to the importance weights. This embodiment sets three levels: the core node layer, the important node layer, and the general node layer, corresponding to larger, medium, and smaller watermark information amounts respectively. The system quickly determines the watermark information amount to be allocated to each node by looking up the table, ensuring that important nodes receive more watermark protection.

[0064] S340. Construct a multi-level watermark coding structure according to the watermark information amounts at each level.

[0065] In this embodiment, through a predefined coding rule library, the watermark information at different levels is organized into a structured coding sequence.

[0066] Specifically, a rule library containing different coding modes is established, and different coding strategies are adopted for nodes at each level. For example, the core node layer uses a longer coding length and stronger error correction ability, while the general node layer uses a shorter coding length. The system generates the coding structures at each level according to the rule library and combines the watermark information at different levels into a complete watermark sequence through bit operations.

[0067] In one embodiment, with reference to Figure 4 , in step S320, according to the node connection relationship matrix, calculate the node importance weights, which specifically include the following steps: S321. Obtain the node connection degree data according to the node connection relationship matrix.

[0068] In this embodiment, the node connection degree data includes two dimensions: direct connection degree and weighted connection degree. The direct connection degree reflects the number of direct adjacent relationships of the node, and the weighted connection degree takes into account the capacity level of the connection line.

[0069] Specifically, obtain the direct connection degree of each node by calculating the row sum or column sum of the connection relationship matrix A. At the same time, establish a line weight mapping table, assign different weights according to different voltage levels and line types, generate a weighted connection relationship matrix, and calculate the weighted connection degree.

[0070] S322. Calculate the power flow volume between nodes according to the node connection degree data to obtain the flow volume eigenvalue.

[0071] In this embodiment, a power flow volume calculation model is established. By means of a preset flow distribution rule, estimate the power transmission capacity between nodes based on the node connection degree data, avoid complex power flow calculations, and improve the calculation efficiency.

[0072] Specifically, first establish a shortest path table between node pairs. Then, according to the connection degree data on the path, use the preset flow distribution rule to estimate the flow volume. For example, the minimum connection degree on the path can be used as the reference flow capacity of the path, and then corrected in combination with the path length to finally obtain the flow volume eigenvalue reflecting the node transmission capacity.

[0073] S323. Based on the flow volume eigenvalue, determine the position relationship of the node in the network to obtain the position importance index.

[0074] In this embodiment, through a pre-established network partition rule library, combined with the flow volume eigenvalue, quickly identify the network position attributes of the nodes, avoiding complex network topology analysis algorithms.

[0075] Specifically, first divide the network into several regions according to the geographical location and electrical connection relationship. Then establish a transmission channel identification rule between regions, and determine whether the node is located on the key transmission channel by looking up the table. Finally, combine the position characteristics of the node within and between regions to calculate the position importance index. In this embodiment, set the position importance of the nodes connecting between regions to a higher value, and determine the importance value of the nodes within the region according to their relative positions in the region.

[0076] S324. Calculate the comprehensive weighted coefficient based on the location importance index, traffic volume eigenvalue, and node connectivity data to obtain the node importance weight.

[0077] Specifically, the system pre - establishes a weight configuration table for three - dimensional characteristic indicators, including the weight coefficients of three dimensions: location importance, traffic volume, and connectivity. Flexibly adjust the weight values of each dimension according to actual needs. Through weighted summation operation, combine the characteristic indicators of the three dimensions into the final node importance weight.

[0078] In one embodiment, referring to Figure 5 , the method further includes the following steps: S510. Based on the power change rate and the node importance weight, establish a node priority matrix.

[0079] In this embodiment, the node priority matrix integrates information from two dimensions: dynamic characteristics (power change rate) and static characteristics (node importance weight).

[0080] Specifically, establish a priority mapping table for a two - dimensional feature space, where the horizontal axis represents the power change rate interval and the vertical axis represents the node importance level. After normalizing the power change rate and the node importance weight respectively, look up the table to determine the priority level of the node.

[0081] S520. According to the node priority matrix, adjust the watermark embedding position mapping relationship to obtain an optimized mapping relationship.

[0082] In this embodiment, adopt a dynamic adjustment method for the mapping relationship based on priority. Through a pre - established position adjustment rule library, select a suitable embedding position according to the node priority level to achieve differential configuration of the watermark protection intensity.

[0083] Specifically, establish a correspondence table between the priority level and the embedding position characteristics, including the recommended data position characteristics under different priorities. High - priority nodes select stable regions of the data for embedding, medium - priority nodes select regions with less fluctuation, and low - priority nodes select general regions. The system looks up the table according to the priority level of the current node to determine the position characteristic requirements, and then makes corresponding adjustments on the basis of the original mapping relationship.

[0084] S530. Based on the optimized mapping relationship, dynamically allocate the number of watermark embedding bits to obtain the watermark embedding strategy for each node.

[0085] In this embodiment, through a pre - defined allocation rule table, dynamically determine the number of watermark embedding bits for each node according to the optimized mapping relationship, avoiding complex optimization algorithms.

[0086] Specifically, the system establishes a correspondence rule between mapping position features and the number of embedded bits, including the recommended range of the number of embedded bits under different position features. For nodes mapped to stable regions, a relatively large number of embedded bits (such as 3 - 4 bits) can be used, while for nodes mapped to fluctuating regions, a smaller number of bits (such as 1 - 2 bits) are used. The system quickly determines the specific number of embedded bits for each node through a look-up table method and generates a complete embedding strategy containing embedding position and bit information.

[0087] S540. According to the watermark embedding strategy of each node, the differential embedding of watermark information is realized to obtain hierarchical watermarked data.

[0088] Specifically, the system establishes a template library containing multiple embedding modes and presets corresponding embedding templates for different embedding strategies. For example, for high-priority nodes, a strong protection template is used; for medium-priority nodes, a standard template is used; and for low-priority nodes, a simplified template is used. The system selects the corresponding template according to the embedding strategy of each node to perform the watermark embedding operation, and finally generates hierarchical watermarked data with different protection strengths.

[0089] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0090] In a second aspect, the present application provides a data protection system for a new energy power grid system. The data protection system for the new energy power grid system of the present application will be described below in combination with the above data protection method for the new energy power grid system.

[0091] Referring to Figure 6 , a data protection system for a new energy power grid system includes: A real-time load data sequence acquisition module, configured to collect the load data of the new energy power grid system to obtain a real-time load data sequence; A load curve characteristic parameter calculation module, configured to calculate load curve characteristic parameters based on the real-time load data sequence; An embedding position mapping relationship establishment module, configured to establish a dynamic watermark embedding position mapping relationship according to the load curve characteristic parameters; A watermark embedding position set determination module, configured to determine a watermark embedding position set based on the watermark embedding position mapping relationship; A watermarked data generation module, configured to embed a digital watermark into data according to the watermark embedding position set to obtain watermarked data.

[0092] In one embodiment, the load curve characteristic parameters include the peak and valley positions of the load curve, the load stable interval, the load mutation interval, and the load periodic change characteristics.

[0093] In one embodiment, it further includes: A power time series acquisition module, configured to collect new energy power generation data to obtain a power time series; A power change rate calculation module, configured to calculate a power change rate according to the power time series; A watermark embedding bit number determination module, configured to determine a watermark embedding bit number based on the power change rate; An embedding strength parameter generation module, configured to adjust the least significant bit of data according to the watermark embedding bit number to obtain a watermark embedding strength parameter.

[0094] In one embodiment, the power change rate includes the power difference between adjacent time points, the power change amount per unit time, and the power change trend feature within a preset time window.

[0095] In one embodiment, it further includes: A node connection relationship matrix acquisition module, configured to obtain power grid topology structure data to obtain a node connection relationship matrix; A node importance weight calculation module, configured to calculate a node importance weight according to the node connection relationship matrix; A watermark information amount determination module, configured to determine the watermark information amount of each layer based on the node importance weight; A watermark coding structure construction module, configured to construct a multi-layer watermark coding structure according to the watermark information amount of each layer.

[0096] In one embodiment, the node importance weight calculation module includes: A node connection degree data acquisition unit, configured to obtain node connection degree data according to the node connection relationship matrix; A flux eigenvalue calculation unit, configured to calculate the power flux between nodes according to the node connection degree data to obtain a flux eigenvalue; A position importance index determination unit, configured to determine the position relationship of a node in the network based on the flux eigenvalue to obtain a position importance index; A comprehensive weighting coefficient calculation unit, configured to calculate a comprehensive weighting coefficient according to the position importance index, the flux eigenvalue, and the node connection degree data to obtain a node importance weight.

[0097] In one embodiment, it further includes: A node priority matrix establishment module, configured to establish a node priority matrix based on the power change rate and the node importance weight; A mapping relationship optimization module, configured to adjust the watermark embedding position mapping relationship according to the node priority matrix to obtain an optimized mapping relationship; A watermark embedding strategy generation module, which is used to dynamically allocate the number of watermark embedding bits based on the optimized mapping relationship to obtain the watermark embedding strategies of each node. A differential watermark embedding module, which is used to implement differential embedding of watermark information according to the watermark embedding strategies of each node to obtain hierarchical watermarked data.

[0098] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as Figure 7 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a data protection method for a new energy power grid system.

[0099] Those skilled in the art can understand that Figure 7 the structure shown in

[0100] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0102] The above are all preferred embodiments of the present application. The protection scope of the present application is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A data protection method for a new energy power grid system, characterized in that, It includes the following steps: Collect the load data of the new energy power grid system to obtain a real-time load data sequence; Based on the real-time load data sequence, calculate the load curve characteristic parameters; According to the load curve characteristic parameters, establish a dynamic watermark embedding position mapping relationship; Based on the watermark embedding position mapping relationship, determine the watermark embedding position set; According to the watermark embedding position set, embed the digital watermark into the data to obtain the watermarked data.

2. The data protection method for the new energy power grid system according to claim 1, wherein The load curve characteristic parameters include the peak and valley positions of the load curve, the load stable interval, the load mutation interval, and the load periodic change characteristics.

3. The data protection method of the new energy power grid system according to claim 1, characterized in that The method further includes the following steps: Collect the new energy power generation power data to obtain a power time series; According to the power time series, calculate the power change rate; Based on the power change rate, determine the number of bits for watermark embedding; According to the number of bits for watermark embedding, adjust the least significant bit of the data to obtain the watermark embedding strength parameter.

4. The data protection method for the new energy power grid system according to claim 3, characterized in that The power change rate includes the power difference between adjacent time points, the power change amount per unit time, and the power change trend characteristic within a preset time window.

5. The data protection method for the new energy power grid system according to claim 3, characterized in that The method further includes the following steps: Obtain the power grid topology structure data to obtain a node connection relationship matrix; According to the node connection relationship matrix, calculate the node importance weights; Based on the node importance weights, determine the watermark information amount at each level; According to the watermark information amount at each level, construct a multi-level watermark coding structure.

6. The data protection method for the new energy power grid system according to claim 5, wherein According to the node connection relationship matrix, calculate the node importance weights, which specifically include the following steps: According to the node connection relationship matrix, obtain the node connection degree data; According to the node connection degree data, calculate the power flow between nodes to obtain a flux eigenvalue; Based on the flux eigenvalue, determine the position relationship of the node in the network to obtain a position importance index; According to the position importance index, the flux eigenvalue, and the node connection degree data, calculate a comprehensive weighting coefficient to obtain the node importance weights.

7. The data protection method for the new energy power grid system according to claim 5, wherein The method further includes the following steps: Based on the power change rate and the node importance weights, establish a node priority matrix; According to the node priority matrix, adjust the watermark embedding position mapping relationship to obtain an optimized mapping relationship; Based on the optimized mapping relationship, dynamically allocate the number of bits for watermark embedding to obtain the watermark embedding strategy for each node; According to the watermark embedding strategy for each node, implement differential embedding of watermark information to obtain hierarchical watermarked data.

8. A data protection system for a new energy power grid system, characterized in that, It includes: A real-time load data sequence acquisition module, which is used to collect the load data of the new energy power grid system to obtain a real-time load data sequence; A load curve characteristic parameter calculation module, which is used to calculate the load curve characteristic parameters based on the real-time load data sequence; An embedding position mapping relationship establishment module, which is used to establish a dynamic watermark embedding position mapping relationship according to the load curve characteristic parameters; A watermark embedding position set determination module, which is used to determine the watermark embedding position set based on the watermark embedding position mapping relationship; A watermarked data generation module, which is used to embed the digital watermark into the data according to the watermark embedding position set to obtain the watermarked data.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the data protection method for the new energy grid system described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the data protection method for the new energy grid system described in any one of claims 1-7.

Images