Photovoltaic power grid data lightweight adaptive encryption method, device, equipment, medium and product

Abstract

The application discloses a photovoltaic power grid data lightweight adaptive encryption method, device, equipment, medium and product, and relates to the technical field of communication. The method comprises the following steps: acquiring equipment operation data, electrical parameter data and environment monitoring data corresponding to a photovoltaic power grid; calculating the equipment operation data based on a first equipment reference range to obtain an equipment anomaly score; calculating the electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score; calculating the environment monitoring data based on a third environment reference range to obtain an environment anomaly score; determining a photovoltaic operation state coefficient based on a first equipment weight, a second electrical weight, a third environment weight, the equipment anomaly score, the electrical anomaly score and the environment anomaly score; and determining a target sensitivity level based on the photovoltaic operation state coefficient and encrypting service data to obtain an encrypted message. The method can adaptively and dynamically adjust the encryption strength to simultaneously consider security and system performance.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a lightweight adaptive encryption method, device, equipment, medium and product for photovoltaic power grid data. Background Technology

[0002] With the energy structure shifting towards cleaner and distributed energy, the proportion of distributed photovoltaic (PV) power in new power systems is continuously increasing. Due to the randomness and volatility of its output, it poses challenges to the stable operation of the power grid. Therefore, accurate sensing and scheduling of distributed PV power through real-time data acquisition is essential. The accuracy, real-time nature, and reliability of the collected data are crucial to ensuring the safe and efficient operation of the power grid. During data transmission, information such as operating status and scheduling instructions are subject to security threats such as eavesdropping, tampering, and forgery. Malicious damage will directly affect scheduling decisions and system stability. Therefore, encryption technology must be used for security protection during the data acquisition and access process of distributed PV power.

[0003] Existing encryption technologies mostly employ fixed strategies. To ensure the security of critical instructions, systems are often uniformly configured with high-security algorithms to apply the same level of high-level encryption protection to all types of data.

[0004] However, this one-size-fits-all, fixed high-strength encryption method can lead to excessive encryption computation overhead in photovoltaic scenarios with large data volumes and frequent data collection, ultimately making it difficult to balance security and system performance. Summary of the Invention

[0005] This application provides a lightweight adaptive encryption method, device, equipment, medium, and product for photovoltaic power grid data, which can achieve adaptive dynamic adjustment of encryption strength to simultaneously ensure security and system performance.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a lightweight adaptive encryption method for photovoltaic power grid data, including: Acquire equipment operation data, electrical parameter data, and environmental monitoring data corresponding to the photovoltaic power grid; Based on the first equipment reference range, anomaly calculations are performed on the equipment operation data to obtain an equipment anomaly score; based on the second electrical reference range, anomaly calculations are performed on the electrical parameter data to obtain an electrical anomaly score; based on the third environmental reference range, anomaly calculations are performed on the environmental monitoring data to obtain an environmental anomaly score. Based on the first equipment weight, the second electrical weight, and the third environmental weight, the equipment anomaly score, electrical anomaly score, and environmental anomaly score are fused and calculated to obtain the photovoltaic operating state coefficient. The sensitivity level of the target is determined based on the photovoltaic operating status coefficient; Based on the target sensitivity level, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

[0007] In some possible implementations, anomaly calculations are performed on equipment operating data based on a first equipment reference range to obtain an equipment anomaly score; anomaly calculations are performed on electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score; and anomaly calculations are performed on environmental monitoring data based on a third environmental reference range to obtain an environmental anomaly score, including: For each sub-indicator in the equipment operation data, the value of the sub-indicator is compared with the first equipment reference range. If the value of the sub-indicator deviates from the first equipment reference range, the absolute difference between the value of the sub-indicator and the median value of the first equipment reference range is taken as the equipment anomaly value corresponding to the sub-indicator value. If the value of the sub-indicator is within the first equipment reference range, the equipment anomaly value corresponding to the sub-indicator value is zero. All the equipment anomaly values ​​are accumulated to obtain the equipment anomaly score. For each sub-index within the electrical parameter data, the value of the sub-index is compared with the second electrical reference range. If the value of the sub-index deviates from the second electrical reference range, the absolute difference between the value of the sub-index and the median value of the second electrical reference range is taken as the electrical anomaly value corresponding to the sub-index value. If the value of the sub-index is within the second electrical reference range, the electrical anomaly value corresponding to the sub-index value is zero. All electrical anomaly values ​​are summed to obtain the electrical anomaly score. For each sub-indicator in the environmental monitoring data, the value of the sub-indicator is compared with the third environmental benchmark range. If the value of the sub-indicator deviates from the third environmental benchmark range, the absolute difference between the value of the sub-indicator and the median value of the third environmental benchmark range is taken as the environmental anomaly value corresponding to the value of the sub-indicator. If the value of the sub-indicator is within the third environmental benchmark range, the environmental anomaly value corresponding to the value of the sub-indicator is zero. All environmental anomaly values ​​are accumulated to obtain the environmental anomaly score.

[0008] In some possible implementations, the photovoltaic operating state coefficient is obtained by fusing the equipment anomaly score, electrical anomaly score, and environmental anomaly score based on a first equipment weight, a second electrical weight, and a third environmental weight, including: Multiply the first equipment weight by the equipment anomaly score to obtain the first weighted value; Multiply the second electrical weight by the electrical anomaly score to obtain the second weighted value; Multiply the third environmental weight by the environmental anomaly score to obtain the third weighted value; The photovoltaic operating state coefficient is obtained by summing the first weighted value, the second weighted value, and the third weighted value. The first equipment weight, the second electrical weight, and the third environmental weight are set as gradient-layered values, with the first equipment weight being greater than the second electrical weight, and the second electrical weight being greater than the third environmental weight.

[0009] In some possible implementations, the target sensitivity level is determined based on the photovoltaic operating state coefficient, including: Based on the numerical distribution of historical photovoltaic operating state coefficients, multiple non-overlapping sensitivity intervals are determined. The photovoltaic operating state coefficient is matched with the sensitivity interval to determine the target sensitivity interval; The target sensitivity level is determined based on the target sensitivity range.

[0010] In some possible implementations, based on sensitivity levels, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages, including: Encryption strategies are determined based on sensitivity levels; different encryption strategies correspond to different key specifications. Generate encryption keys based on the encryption strategy; Based on the encryption key, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

[0011] In some possible implementations, the business data corresponding to the photovoltaic grid is encrypted based on the encryption key to obtain encrypted messages, including: Based on the encryption key, perform key expansion operations to generate multiple sets of round encryption subkeys; Encryption operations are performed based on the encryption rounds specified in the key specification to obtain encrypted messages; the encryption operations include initial subkey XOR, byte substitution, row shifting, column obfuscation, and round key addition.

[0012] Secondly, this application provides a lightweight adaptive encryption device for photovoltaic power grid data, comprising: The acquisition module is used to acquire equipment operation data, electrical parameter data, and environmental monitoring data corresponding to the photovoltaic power grid; The calculation module is used to perform anomaly calculation on equipment operation data based on a first equipment reference range to obtain an equipment anomaly score; perform anomaly calculation on electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score; perform anomaly calculation on environmental monitoring data based on a third environmental reference range to obtain an environmental anomaly score; and perform fusion calculation on the equipment anomaly score, electrical anomaly score, and environmental anomaly score based on the first equipment weight, the second electrical weight, and the third environmental weight to obtain the photovoltaic operating state coefficient. The encryption module is used to determine the target sensitivity level based on the photovoltaic operating status coefficient; based on the target sensitivity level, it encrypts the business data corresponding to the photovoltaic grid to obtain encrypted messages.

[0013] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0014] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0015] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0016] As can be seen from the above technical solution, this application has at least the following beneficial effects: In this application, an adaptive encryption protection for photovoltaic power grid business data is achieved by constructing a complete processing chain encompassing data acquisition, anomaly quantification, weighted fusion, level determination, and dynamic encryption. This method utilizes multi-dimensional anomaly assessment and gradient-level weighted fusion of equipment operation data, electrical parameter data, and environmental monitoring data. This allows the calculated photovoltaic operating state coefficient to objectively reflect the sensitivity of the current data, and then dynamically matches encryption strategies with different key lengths accordingly. Higher sensitivity requires longer keys and more encryption rounds, while lower sensitivity requires shorter keys and fewer encryption rounds. Thus, this application employs lightweight encryption to reduce computational overhead and ensure transmission efficiency when data sensitivity is low, and automatically strengthens encryption to ensure security when data sensitivity is high. This achieves adaptive dynamic adjustment of encryption strength, solving the problem in the prior art where a uniform high-strength encryption method struggles to balance security and system performance.

[0017] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0018] Figure 1 An application environment diagram for a lightweight adaptive encryption method for photovoltaic power grid data provided in this application embodiment; Figure 2 A flowchart illustrating a lightweight adaptive encryption method for photovoltaic power grid data provided in this application embodiment; Figure 3 A structural diagram of a lightweight adaptive encryption device for photovoltaic power grid data provided in this application embodiment; Figure 4 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0019] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0020] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0021] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first: A photovoltaic (PV) grid refers to a new type of power system that uses photovoltaic power generation as its primary power source and operates in parallel with the grid through power electronic equipment. Distributed PV, as an important component of the PV grid, is typically deployed on the user side or distribution network side and is characterized by small installed capacity, dispersed layout, and proximity to loads.

[0022] Currently, the proportion of distributed photovoltaic (PV) power in new power systems continues to increase. However, its output is significantly affected by environmental factors such as sunlight and temperature, exhibiting considerable randomness and volatility, posing challenges to the stable operation of the power grid. Therefore, high-frequency data acquisition and transmission are essential for real-time perception and precise scheduling of distributed PV operation status. During data transmission, equipment operating parameters, electrical measurements, and scheduling instructions are vulnerable to security threats such as eavesdropping, tampering, and forgery. Malicious damage to these data will directly impact the accuracy of scheduling decisions and the security and stability of the system. Therefore, encryption technology is necessary to protect the transmitted data.

[0023] Existing encryption technologies in photovoltaic power grid data acquisition and access scenarios often employ fixed strategies for data protection. To ensure data security, systems typically use uniformly configured high-security algorithms, applying the same level of encryption to all types of transmitted data. However, due to the diverse types of data collected from photovoltaic power grids, and the significant differences in physical meaning, impact on equipment security, and real-time requirements, this uniformly configured high-strength encryption method, while providing sufficient security, leads to a continuous increase in encryption computational overhead. For distributed photovoltaic scenarios with high acquisition frequency and massive data volumes, the conflict between computing resources and transmission bandwidth consumption becomes increasingly prominent, making it difficult to achieve an effective balance between security protection levels and overall system performance.

[0024] In view of this, embodiments of this application provide a lightweight adaptive encryption method for photovoltaic power grid data. To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown, this figure is an application environment diagram provided by an embodiment of this application.

[0025] In this application environment, the server acts as the execution entity, interacting with the data acquisition terminals. The data acquisition terminals are deployed at distributed photovoltaic (PV) sites to collect equipment operation data, electrical parameter data, and environmental monitoring data, and transmit the collected raw data to the server via a communication network. After receiving the collected data from each distributed PV site, the server executes the lightweight adaptive encryption method provided in this embodiment of the application. This method performs multi-dimensional anomaly assessment, weighted fusion processing, and sensitivity level determination on the received business data. Based on the determination results, it dynamically matches the corresponding encryption strategy to generate an encrypted data stream. The encrypted data is then transmitted to the scheduling platform via the communication network for use by upper-layer applications such as scheduling decisions, operation monitoring, and data analysis.

[0026] To make the technical solution of this application clearer and easier to understand, the following describes a lightweight adaptive encryption method for photovoltaic power grid data provided in the embodiments of this application, using the above application scenario and server 104 as the execution subject. Figure 2 As shown in the figure, this is a flowchart illustrating a lightweight adaptive encryption method for photovoltaic grid data provided in an embodiment of this application. The lightweight adaptive encryption method for photovoltaic grid data includes: S201. Obtain the equipment operation data, electrical parameter data and environmental monitoring data corresponding to the photovoltaic power grid.

[0027] Equipment operation data refers to parameters that reflect the health and working status of important hardware equipment in a photovoltaic power station, including operating efficiency and core temperature (i.e., the temperature of the main control chip and power core components), such as the operating efficiency of the inverter, the core temperature of the inverter (such as the operating temperature of the power switching tubes and the main control chip of the digital signal processor inside the inverter), the operating efficiency of the combiner box, and the core temperature of the combiner box (such as the temperature of important heat-generating components such as the combiner box microcontroller, power busbar, and fuses).

[0028] Electrical parameter data refers to the electrical measurement data generated by a photovoltaic power generation system during the power output process, including output current, output voltage, instantaneous power, and power generation. Output current and output voltage reflect the magnitude of the current and voltage level of the photovoltaic system transmitting electrical energy to the grid, respectively; instantaneous power is the output power value at the current moment; and power generation is the total amount of electrical energy generated cumulatively.

[0029] Environmental monitoring data refers to the meteorological and solar radiation parameters of the natural environment where the photovoltaic power station is located, including the surface temperature of the photovoltaic modules, the total solar radiation intensity, and wind speed parameters. The surface temperature of the photovoltaic modules reflects the actual operating temperature of the photovoltaic panels and has a direct impact on power generation efficiency; the total solar radiation intensity is the solar radiation power received per unit area; and wind speed parameters affect the heat dissipation conditions of the photovoltaic modules and the safety of the equipment.

[0030] For example, equipment operation data, electrical parameter data, and environmental monitoring data can be acquired through a layered communication network and data acquisition terminals. At the hardware deployment level, the inverter controller and combiner box controller of the photovoltaic power station are each equipped with data acquisition interfaces. As the core conversion device for photovoltaic power generation, the inverter's internal parameters, such as operating efficiency and core temperature, can be directly read through a standard communication interface. The combiner box is used to combine the DC input of the photovoltaic array, and it is also equipped with a monitoring unit.

[0031] In terms of environmental monitoring, a meteorological monitoring station is deployed at the photovoltaic power station site, equipped with solar total radiation sensors, module surface temperature sensors, and wind speed and direction sensors. All of these devices are connected to the data acquisition terminal via an RS485 industrial communication bus. The RS485 bus features long transmission distance, strong anti-interference capability, and the ability to connect multiple devices in series, making it suitable for the on-site environment of photovoltaic power stations. Communication between devices uses the Modbus RTU protocol. Photovoltaic inverters, combiner boxes, meteorological stations, and other devices provide their internal operating parameters externally in the form of register data through this protocol. The data acquisition terminal, acting as the communication master station, polls and reads data from each slave device according to the register addresses specified in the Modbus protocol.

[0032] At the data acquisition process level, the data acquisition terminal sends data read commands to each device according to a preset sampling period. Upon receiving the command, each device returns its current operating parameters to the data acquisition terminal via the RS485 bus. The data acquisition terminal performs preliminary processing on the received raw data, including removing obvious outliers and verifying data integrity, and then uploads the processed data to the server via the network. The server receives and stores this data.

[0033] S202. Based on the first equipment reference range, perform anomaly calculation on the equipment operation data to obtain the equipment anomaly score; based on the second electrical reference range, perform anomaly calculation on the electrical parameter data to obtain the electrical anomaly score; based on the third environmental reference range, perform anomaly calculation on the environmental monitoring data to obtain the environmental anomaly score.

[0034] The calculation method for determining the equipment anomaly score can be as follows: For each sub-index within the equipment operation data, the value of the sub-index is compared with the first equipment reference range; if the value of the sub-index deviates from the first equipment reference range, the absolute difference between the value of the sub-index and the median value of the first equipment reference range is taken as the equipment anomaly value corresponding to the sub-index value; if the value of the sub-index is within the first equipment reference range, the equipment anomaly value corresponding to the sub-index value is zero; all equipment anomaly values ​​are summed to obtain the equipment anomaly score. The calculation method for determining the electrical anomaly score is as follows: For each sub-index within the electrical parameter data, the value of the sub-index is compared with the second electrical reference range; if the value of the sub-index deviates from the second electrical reference range, the absolute difference between the value of the sub-index and the median value of the second electrical reference range is taken as the electrical anomaly value corresponding to the sub-index value; if the value of the sub-index is within the second electrical reference range, the electrical anomaly value corresponding to the sub-index value is zero; all electrical anomaly values ​​are summed to obtain the electrical anomaly score. The calculation method for determining the environmental anomaly score is as follows: For each sub-indicator in the environmental monitoring data, the value of the sub-indicator is compared with the third environmental benchmark range; if the value of the sub-indicator deviates from the third environmental benchmark range, the absolute difference between the value of the sub-indicator and the median value of the third environmental benchmark range is taken as the environmental anomaly value corresponding to the value of the sub-indicator; if the value of the sub-indicator is within the third environmental benchmark range, the environmental anomaly value corresponding to the value of the sub-indicator is zero. All environmental anomaly values ​​are accumulated to obtain the environmental anomaly score.

[0035] The first equipment benchmark range is a reasonable fluctuation range calculated by the server for each sub-indicator in the equipment operation data, based on the values ​​recorded by the photovoltaic power station during its historical normal operation. This range uses the historical minimum value as the lower limit and the historical maximum value as the upper limit. Because different photovoltaic power stations have different inverter models, installation capacities, cooling conditions, etc., the first equipment benchmark range is set specifically for this power station, rather than a universal fixed threshold. For example, if the server analyzes the historical data of a power station during normal operation and finds that the operating efficiency is consistently between 93% and 97%, and the core temperature is consistently between 45℃ and 75℃, then the benchmark range for operating efficiency in the first equipment benchmark range is [93%, 97%], and the benchmark range for core temperature is [45℃, 75℃].

[0036] The device anomaly score is a comprehensive value obtained by the server after quantifying and summarizing the degree of anomalies in all sub-indicators of device operation data. For example, the server first calculates the anomaly values ​​for the two sub-indicators, operating efficiency and core temperature. If the current value of the sub-indicator is within the baseline range, the anomaly value is recorded as 0; if it deviates from the baseline range, the absolute difference between the current value and the median value of the baseline range is calculated as the anomaly value. After calculating the anomaly values ​​for the two sub-indicators, the server adds them together, and the result is the device anomaly score. The higher the device anomaly score, the more serious the deviation of core hardware devices such as inverters from normal operating conditions. For example, if the server collects current operating efficiency of 90% (baseline range [93%, 97%], median 95%), which deviates from the baseline range, the calculated anomaly value is |90% - 95%| = 5%; and the core temperature is 80℃ (baseline range [45℃, 75℃], median 60℃), which deviates from the baseline range, the calculated anomaly value is |80℃ - 60℃| = 20℃; then the device anomaly score = 5% + 20℃.

[0037] The second electrical reference range is a reasonable fluctuation range calculated by the server for each sub-index in the electrical parameter data, based on the electrical quantities such as output current, output voltage, instantaneous power, and power generation recorded during the historical normal operation of the photovoltaic power station. Each sub-index has its own independent upper and lower limits. Electrical parameters are affected by factors such as grid dispatch instructions, sunlight conditions, and load changes, and their normal fluctuation range is personalized by the server based on historical data of the power station under stable operating conditions. For example, after the server analyzes historical data of a power plant during normal operation, it finds that: the output current is consistently between 8A and 12A, the output voltage is consistently between 210V and 230V, the instantaneous power is consistently between 180kW and 220kW, and the power generation (calculated as the cumulative value for the day) has its specific cumulative range based on the installed capacity and sunshine duration. Therefore, in the second electrical reference range, the reference range for output current is [8A, 12A], the reference range for output voltage is [210V, 230V], the reference range for instantaneous power is [180kW, 220kW], and the corresponding range for power generation is set based on historical data from normal days during the same period.

[0038] The electrical anomaly score is a comprehensive value obtained by the server by summing up the abnormal values ​​of all sub-indicators (such as output current, output voltage, instantaneous power, and power generation) in the electrical parameter data.

[0039] The third environmental baseline range is a reasonable fluctuation range calculated by the server for each sub-indicator in the environmental monitoring data (photovoltaic module surface temperature, total solar radiation intensity, and wind speed parameter), based on the values ​​recorded by the photovoltaic power station during its historical normal operation. For example, after the server analyzes the historical data of a power station during normal operation on sunny summer days, it finds that the module surface temperature is between 25℃ and 65℃, the total solar radiation intensity is between 200W / m² and 1000W / m², and the wind speed is between 0.5m / s and 8m / s. Then, in the third environmental baseline range, the corresponding intervals for each sub-indicator are [25℃, 65℃], [200W / m², 1000W / m²], and [0.5m / s, 8m / s], respectively.

[0040] The environmental anomaly score is a comprehensive value obtained by the server by summing up the outlier values ​​of all sub-indicators (such as photovoltaic module surface temperature, total solar radiation intensity, and wind speed parameters) in the environmental monitoring data.

[0041] Sub-indicators refer to the specific monitoring parameters included in each type of data. For example, equipment operation data includes two sub-indicators: operating efficiency and core temperature; electrical parameter data includes four sub-indicators: output current, output voltage, instantaneous power, and power generation; and environmental monitoring data includes three sub-indicators: photovoltaic module surface temperature, total solar radiation intensity, and wind speed.

[0042] Outliers are values ​​obtained by the server after quantifying the degree to which the current value of a single sub-indicator deviates from its baseline range. When the sub-indicator value is within the baseline range, the outlier value is zero, indicating that the indicator is operating normally; when the sub-indicator value deviates from the baseline range (below the lower limit or above the upper limit), the outlier value is the absolute difference between the value and the median value of the baseline range, indicating the severity of the deviation from the normal center position.

[0043] The median is the arithmetic mean of the upper and lower limits of a certain reference range, representing the central reference point of the indicator under normal operating conditions. For example, if the reference range for operating efficiency is [93%, 97%], then the median is (93% + 97%) / 2 = 95%.

[0044] The absolute difference refers to the absolute value obtained by subtracting the current value of a sub-indicator from the median value of the baseline range. It is used to measure the distance of the current value from the normal center position. Using the absolute difference instead of the simple difference can avoid the cancellation of positive and negative values, and at the same time capture both abnormal directions of the indicator being too low and too high.

[0045] For example, for electrical parameter data, the server retrieves the current values ​​of four sub-indicators: output current, output voltage, instantaneous power, and power generation, and compares them independently with the corresponding reasonable intervals in the second electrical reference range. According to the same rule, if the value is within the reference range, the abnormal value is 0; if it deviates, the absolute difference from the median value is calculated. After calculating the abnormal values ​​of all sub-indicators, the values ​​are summed to obtain the electrical abnormality score.

[0046] For environmental monitoring data, the server extracts the current values ​​of three sub-indicators: photovoltaic module surface temperature, total solar radiation intensity, and wind speed. These values ​​are then compared with their respective reasonable intervals within the third environmental benchmark range. After calculating the outliers of each sub-indicator according to the same rules, the values ​​are summed to obtain the environmental anomaly score.

[0047] S203. Based on the first equipment weight, the second electrical weight, and the third environmental weight, the equipment anomaly score, electrical anomaly score, and environmental anomaly score are fused and calculated to obtain the photovoltaic operating state coefficient.

[0048] The photovoltaic operating state coefficient can be determined as follows: multiply the first equipment weight by the equipment anomaly score to obtain the first weighted value; multiply the second electrical weight by the electrical anomaly score to obtain the second weighted value; multiply the third environmental weight by the environmental anomaly score to obtain the third weighted value; and sum the first, second, and third weighted values ​​to obtain the photovoltaic operating state coefficient. The first equipment weight, second electrical weight, and third environmental weight are set as gradient-layered values, with the first equipment weight being greater than the second electrical weight, and the second electrical weight being greater than the third environmental weight.

[0049] The first device weight is a weighting coefficient preset by the server for the device anomaly score. Since device parameters such as inverter core temperature and operating efficiency are directly related to the physical safety of the hardware, any anomaly could lead to equipment shutdown or even burnout. Therefore, the first device weight has the highest value among the three weight categories. For example, the server sets the first device weight to 10. - ¹The order of magnitude (e.g., 0.1) allows it to dominate subsequent fusion calculations, ensuring that anomalies at the device level can significantly affect the final value of the photovoltaic operating state coefficient.

[0050] The second electrical weight is a weighting coefficient preset by the server for electrical anomaly scores. Electrical parameters such as output current, voltage, and power are direct bases for power grid dispatching and power control; anomalies in these parameters can affect power quality and grid stability, but generally do not immediately damage hardware. Therefore, the value of the second electrical weight falls between the first equipment weight and the third environmental weight. For example, the server sets the second electrical weight to 10. - On the order of 2 (e.g., 0.01).

[0051] The third environmental weight is a weighting coefficient preset by the server for environmental anomaly scores. Environmental parameters such as photovoltaic module surface temperature, total solar radiation intensity, and wind speed are mainly used for efficiency analysis and power generation prediction. Short-term deviations will not directly cause safety accidents or dispatch malfunctions; therefore, the third environmental weight has the lowest value among the three weight categories. For example, the server sets the third environmental weight to 10. - The order of magnitude of ³ (e.g., 0.001).

[0052] Gradient-layered numerical values ​​refer to a significant, step-like difference in the order of magnitude among the first equipment weight, the second electrical weight, and the third environmental weight. These three weights are not on the same order of magnitude, with the first equipment weight being significantly greater than the second electrical weight, and the second electrical weight significantly greater than the third environmental weight. This gradient-layered design ensures that the impact of the three types of data on the photovoltaic operating state coefficient strictly corresponds to their actual importance to grid security. Because the first equipment weight is on a much larger order of magnitude than the other two weights, even if all three types of data show anomalies simultaneously, the calculated photovoltaic operating state coefficient will still fall within the range corresponding to the equipment sensitivity, thus prioritizing the physical safety of the equipment.

[0053] The photovoltaic (PV) operating status coefficient is a comprehensive value obtained by multiplying the equipment anomaly score, electrical anomaly score, and environmental anomaly score by their respective weighting coefficients and then summing the results. This coefficient comprehensively reflects the overall degree of anomaly of the PV system across three dimensions: equipment health, electrical output, and environmental conditions.

[0054] For example, the server retrieves the first device weight, the second electrical weight, and the third environmental weight from the memory respectively, and performs a fusion calculation with the device anomaly score, electrical anomaly score, and environmental anomaly score calculated in step S202.

[0055] The server performs a multiplication operation: multiplying the first device weight by the device anomaly score to obtain the first weighted value; multiplying the second electrical weight by the electrical anomaly score to obtain the second weighted value; and multiplying the third environmental weight by the environmental anomaly score to obtain the third weighted value.

[0056] The server performs an addition operation: the first weighted value, the second weighted value, and the third weighted value are added together, and the result is the photovoltaic operating state coefficient.

[0057] The above calculation process can be expressed as a formula: Photovoltaic operating status coefficient = First equipment weight × Equipment anomaly score + Second electrical weight × Electrical anomaly score + Third environmental weight × Environmental anomaly score.

[0058] For example, suppose the server currently calculates a device anomaly score of 25, an electrical anomaly score of 15, and an environmental anomaly score of 8; the server's preset first device weight is 0.1 (10 - ¹Order of magnitude), the second electrical weight is 0.01 (10 - (on the order of magnitude 2), the third environment weight is 0.001 (10^2). - (On the order of magnitude of ³). Then the first weighted value = 0.1 × 25 = 2.5, the second weighted value = 0.01 × 15 = 0.15, the third weighted value = 0.001 × 8 = 0.008, and the photovoltaic operating state coefficient = 2.5 + 0.15 + 0.008 = 2.658.

[0059] S204. Determine the target sensitivity level based on the photovoltaic operating status coefficient.

[0060] The target sensitivity level can be determined as follows: based on the numerical distribution of historical photovoltaic operating state coefficients, determine multiple non-overlapping sensitivity intervals; match the photovoltaic operating state coefficients with the sensitivity intervals to determine the target sensitivity interval; and determine the target sensitivity level based on the target sensitivity interval.

[0061] The target sensitivity level refers to the sensitivity level determined by the server based on the current range of the photovoltaic operating status coefficient. For example, the sensitivity level is divided into three levels: Level 1 (highest, corresponding to abnormal equipment operating data), Level 2 (medium, corresponding to abnormal electrical parameter data), and Level 3 (lowest, corresponding to abnormal environmental monitoring data).

[0062] Sensitivity intervals refer to multiple non-overlapping numerical ranges divided by the server according to the numerical distribution patterns of historical photovoltaic operating state coefficients, with each interval corresponding to a sensitivity level. Since the first equipment weight, second electrical weight, and third environmental weight in step S203 are set as gradient-level values, the calculated photovoltaic operating state coefficients will naturally exhibit three order-of-magnitude stratifications based on different data sensitivity. The server will be at level 10. - The coefficients of the order of magnitude are classified into the first sensitivity interval (representing the highest sensitivity level), which will be in the range of 10. - Coefficients on the order of 2 fall into the second sensitivity range (representing a medium sensitivity level), and will be in the range of 10. - Coefficients on the order of ³ are classified as the third sensitivity interval (representing the lowest sensitivity level).

[0063] For example, the server retrieves pre-defined sensitivity ranges from memory. The boundary values ​​of these ranges are determined by the server during historical operation by analyzing the numerical distribution of a large number of photovoltaic operating state coefficients (e.g., the server collects all photovoltaic operating state coefficients generated in historical calculations, automatically clusters them according to their order of magnitude, and statistically analyzes 10... - ¹、10 - ²、10 - ³The lowest and highest values ​​within three orders of magnitude are used as the lower and upper limits of each sensitivity interval. For example, server statistics revealed that in the historical photovoltaic operating state coefficient, 10 - ¹The numerical values ​​are distributed on the order of magnitude between 0.12 and 0.85, 10 - The numerical values ​​on the order of ² range from 0.015 to 0.095, and 10 - If the numerical values ​​on the order of ³ are distributed between 0.001 and 0.009, then [0.12, 0.85] is determined as the first sensitivity interval, [0.015, 0.095] as the second sensitivity interval, and [0.001, 0.009] as the third sensitivity interval.

[0064] The server matches the current photovoltaic operating state coefficient calculated in step S203 with the aforementioned sensitivity intervals one by one: if the photovoltaic operating state coefficient falls into the first sensitivity interval, the target sensitivity interval is determined to be the first interval; if it falls into the second sensitivity interval, the target sensitivity interval is determined to be the second interval; if it falls into the third sensitivity interval, the target sensitivity interval is determined to be the third interval. The server determines the corresponding target sensitivity level based on the matched target sensitivity intervals, such as the first interval corresponding to the highest sensitivity level, the second interval corresponding to the medium sensitivity level, and the third interval corresponding to the lowest sensitivity level.

[0065] It should be noted that, because the weight of the first equipment is much larger than that of the second electrical weight and the third environmental weight, even in the extreme case where the equipment anomaly score, electrical anomaly score, and environmental anomaly score are all relatively high, the weighted photovoltaic operating state coefficient will still fall below 10. - Within the first sensitivity range of ¹, this design ensures that equipment operating data has absolute control over sensitivity level determination, prioritizing the physical safety of core hardware such as inverters.

[0066] Assume the server calculates the current photovoltaic operating state coefficient to be 0.2658 in step S203 (at level 10). - ¹Order of magnitude), after the server matches it with the sensitivity range, it finds that the value falls into the first sensitivity range (e.g., [0.12, 0.85]), then the server determines the target sensitivity level as the highest sensitivity level.

[0067] S205. Based on the target sensitivity level, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

[0068] One possible approach is to determine an encryption strategy based on a sensitivity level; wherein different encryption strategies correspond to different key specifications; generate an encryption key based on the encryption strategy; and encrypt the business data corresponding to the photovoltaic grid based on the encryption key to obtain an encrypted message.

[0069] The method for determining the encrypted message can be as follows: perform key expansion operation based on the encryption key to generate multiple sets of round encryption subkeys; perform encryption operation based on the encryption round in the key specification to obtain the encrypted message; wherein, the encryption operation includes initial subkey XOR, byte substitution, row shift, column obfuscation, and round key addition operation.

[0070] Business data refers to various application-layer data that needs to be transmitted to the dispatch platform or cloud platform via a secure access gateway during the operation of the photovoltaic power grid. This includes, but is not limited to, real-time operating status reports of inverters, sampling records of electrical parameters, equipment control commands, fault alarm information, and power generation statistics reports. This data faces security threats such as eavesdropping and tampering during transmission, and therefore requires encryption protection.

[0071] An encryption strategy refers to the encryption parameter scheme determined by the server based on the target sensitivity level. The server internally pre-sets three encryption strategies, each corresponding to one of the three sensitivity levels. For example, the highest sensitivity level corresponds to the first encryption strategy, using a 256-bit key and 14 encryption rounds; the medium sensitivity level corresponds to the second encryption strategy, using a 192-bit key and 12 encryption rounds; and the lowest sensitivity level corresponds to the third encryption strategy, using a 128-bit key and 10 encryption rounds. The selection of encryption strategies achieves an adaptive match between encryption strength and data sensitivity.

[0072] Key specifications refer to the parameters specifying the key length and number of encryption rounds in an encryption strategy. There are three types: 256 bits (corresponding to 14 rounds of encryption), 192 bits (corresponding to 12 rounds of encryption), and 128 bits (corresponding to 10 rounds of encryption). The longer the key length, the more encryption rounds, the greater the difficulty of cracking, and the higher the computational overhead and transmission bandwidth consumption.

[0073] An encryption key is the raw key generated by the server for the AES (Advanced Encryption Standard) algorithm according to the selected encryption strategy. The length of the encryption key is determined by the key specification in the encryption strategy, i.e., 256 bits, 192 bits, or 128 bits. After generating the encryption key, the server uses it as input to the AES encryption operation, and generates multiple rounds of encryption subkeys through key expansion operations.

[0074] An encrypted message is the ciphertext data output by the server after performing AES encryption on the business data. Its format conforms to the transmission protocol requirements of the secure access gateway. The encrypted message contains the encrypted business data and necessary encryption parameter information (such as the key specification identifier used), which the receiver can use to decrypt and restore the data.

[0075] Key expansion is the process in the AES algorithm that expands the original encryption key into multiple round encryption subkeys. The server generates N+1 subkeys (where N is the number of encryption rounds) from the original key according to the number of encryption rounds specified in the key specification, using a specific transformation rule. Each subkey is used for the round key addition operation in each round of encryption.

[0076] Round encryption subkeys are sets of keys derived by the server from the original encryption key through key expansion operations. Each round of encryption uses a corresponding set of subkeys. For example, a 128-bit key generates 11 sets of subkeys (16 bytes each), which are used for the initial round and the subsequent 10 rounds of encryption.

[0077] The initial subkey XOR is the starting operation of AES encryption. The server arranges the business data to be encrypted into a state matrix and performs a bitwise XOR operation with the 0th group of subkeys as the initial state for entering the main loop encryption.

[0078] Byte substitution is a non-linear substitution operation in the main loop of AES encryption. The server maps each byte in the state matrix to another byte through the S-box (substitution table) to introduce a non-linear transformation and enhance encryption strength.

[0079] Row shifting is a permutation operation in the main loop of AES encryption. The server cyclically shifts each row of the state matrix to the left, with larger row numbers shifting more bits to spread the data's positional distribution.

[0080] Column obfuscation is a mixing operation in the main loop of AES encryption. The server treats each column of the state matrix as a polynomial over a finite field, multiplies it with a fixed polynomial, and mixes the four bytes in a column together to further spread the data.

[0081] Round key addition is a bitwise XOR operation performed in the main loop of AES encryption by combining the current state matrix with the subkey corresponding to the current round. This operation is included in every round of encryption.

[0082] For example, the server determines the corresponding encryption policy from a preset encryption policy mapping table based on the target sensitivity level. If the target sensitivity level is the highest, the server selects the first encryption policy with a key specification of 256 bits; if it is the medium level, it selects the second encryption policy with a key specification of 192 bits; if it is the lowest level, it selects the third encryption policy with a key specification of 128 bits.

[0083] The server generates an encryption key based on a defined encryption policy. The server can either call the system's built-in secure random number generator to produce a raw key of a specified length, or retrieve a preset key matching the policy from the key management module. This key serves as the initial input for subsequent key expansion operations.

[0084] The server processes the business data to be encrypted in blocks. The AES algorithm is a block cipher algorithm. The server divides the business data into groups of 128 bits (16 bytes). If the last group is not long enough, it is padded to make each group of data form a 4×4 state matrix.

[0085] The server performs key expansion and encryption operations on each data packet: First, the server inputs the original key into the key expansion module, which generates multiple sets of round encryption subkeys according to the number of encryption rounds specified in the key specification. Taking a 128-bit key as an example, the server generates 11 sets of subkeys (16 bytes each) through the key expansion algorithm, numbered as round 0 to round 10 subkeys respectively.

[0086] Secondly, the server performs encryption operations. The encryption operation begins with the initial round, where the server performs an XOR operation between the state matrix and the round 0 subkey. Then, it enters the main encryption loop: for a 128-bit key (10 rounds), the server sequentially executes rounds 1 through 9, each round performing byte substitution, row shifting, column obfuscation, and round key addition; the 10th round (the final round) performs byte substitution, row shifting, and round key addition, omitting the column obfuscation operation. For 192-bit or 256-bit key specifications, the corresponding encryption rounds are 12 and 14 respectively, with the same operation process, only the number of rounds increases.

[0087] Third, after the server completes the encryption operation on all data packets, it concatenates the ciphertext of each packet in sequence to form the final encrypted message. This encrypted message can be transmitted to the scheduling platform or cloud platform through a secure access gateway, and the receiver can decrypt and restore the original business data using the same key specification and AES algorithm.

[0088] Through the above encryption process, the server achieves an adaptive match between encryption strength and data sensitivity: data with higher sensitivity uses longer keys and more encryption rounds to ensure core security; data with lower sensitivity uses shorter keys and fewer encryption rounds to reduce computation and bandwidth consumption, thereby improving transmission efficiency while ensuring security.

[0089] Based on the above, the lightweight adaptive encryption method for photovoltaic power grid data achieves adaptive encryption protection for photovoltaic power grid business data by constructing a complete processing link including data acquisition, anomaly quantification, weighted fusion, level determination, and dynamic encryption. This method utilizes multi-dimensional anomaly assessment and gradient-layered weighted fusion of equipment operation data, electrical parameter data, and environmental monitoring data to ensure that the calculated photovoltaic operating state coefficient objectively reflects the sensitivity of the current data. Based on this, it dynamically matches encryption strategies with different key lengths: higher sensitivity requires longer keys and more encryption rounds, while lower sensitivity requires shorter keys and fewer encryption rounds. Therefore, this application employs lightweight encryption to reduce computational overhead and ensure transmission efficiency when data sensitivity is low, and automatically strengthens encryption to ensure security when data sensitivity is high, thus achieving adaptive dynamic adjustment of encryption strength. This solves the problem in the prior art where uniform high-strength encryption methods struggle to balance security and system performance.

[0090] The above text combined Figures 1 to 2 The lightweight adaptive encryption method for photovoltaic power grid data provided in the embodiments of this application has been described in detail. The apparatus and equipment provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0091] This application also provides a lightweight adaptive encryption device for photovoltaic power grid data, such as... Figure 3 As shown in the figure, this is a structural diagram of a lightweight adaptive encryption device for photovoltaic power grid data provided in an embodiment of this application. The device includes: The acquisition module 301 is used to acquire equipment operation data, electrical parameter data and environmental monitoring data corresponding to the photovoltaic grid; The calculation module 302 is used to perform anomaly calculation on equipment operation data based on a first equipment reference range to obtain an equipment anomaly score; perform anomaly calculation on electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score; perform anomaly calculation on environmental monitoring data based on a third environmental reference range to obtain an environmental anomaly score; and perform fusion calculation on the equipment anomaly score, electrical anomaly score, and environmental anomaly score based on the first equipment weight, the second electrical weight, and the third environmental weight to obtain the photovoltaic operating state coefficient. The encryption module 303 is used to determine the target sensitivity level based on the photovoltaic operating status coefficient; and to encrypt the business data corresponding to the photovoltaic grid based on the target sensitivity level to obtain encrypted messages.

[0092] In some possible implementations, the computing module 302 is specifically used for: For each sub-indicator in the equipment operation data, the value of the sub-indicator is compared with a first equipment reference range. If the value of the sub-indicator deviates from the first equipment reference range, the absolute difference between the value of the sub-indicator and the median value of the first equipment reference range is taken as the equipment anomaly value corresponding to the sub-indicator value. If the value of the sub-indicator is within the first equipment reference range, the equipment anomaly value corresponding to the sub-indicator value is zero. All equipment anomalies are summed to obtain an equipment anomaly score. For each sub-indicator in the electrical parameter data, the value of the sub-indicator is compared with a second electrical reference range. If the value of the sub-indicator deviates from the second electrical reference range, the absolute difference between the value of the sub-indicator and the median value of the second electrical reference range is taken as the equipment anomaly value. The value is taken as the electrical anomaly value corresponding to the sub-index value; if the sub-index value is within the range of the second electrical reference, the electrical anomaly value corresponding to the sub-index value is zero; all electrical anomaly values ​​are accumulated to obtain the electrical anomaly score; for each sub-index in the environmental monitoring data, the sub-index value is compared with the range of the third environmental reference; if the sub-index value deviates from the range of the third environmental reference, the absolute difference between the sub-index value and the median value of the range of the third environmental reference is taken as the environmental anomaly value corresponding to the sub-index value; if the sub-index value is within the range of the third environmental reference, the environmental anomaly value corresponding to the sub-index value is zero; all environmental anomaly values ​​are accumulated to obtain the environmental anomaly score.

[0093] In some possible implementations, the computing module 302 is specifically used for: Multiply the first equipment weight by the equipment anomaly score to obtain the first weighted value; Multiply the second electrical weight by the electrical anomaly score to obtain the second weighted value; Multiply the third environmental weight by the environmental anomaly score to obtain the third weighted value; The photovoltaic operating state coefficient is obtained by summing the first weighted value, the second weighted value, and the third weighted value. The first equipment weight, the second electrical weight, and the third environmental weight are set as gradient-layered values, with the first equipment weight being greater than the second electrical weight, and the second electrical weight being greater than the third environmental weight.

[0094] In some possible implementations, the encryption module 303 is specifically used for: Based on the numerical distribution of historical photovoltaic operating state coefficients, multiple non-overlapping sensitivity intervals are determined. The photovoltaic operating state coefficient is matched with the sensitivity interval to determine the target sensitivity interval; The target sensitivity level is determined based on the target sensitivity range.

[0095] In some possible implementations, the encryption module 303 is specifically used for: Encryption strategies are determined based on sensitivity levels; different encryption strategies correspond to different key specifications. Generate encryption keys based on the encryption strategy; Based on the encryption key, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

[0096] In some possible implementations, the encryption module 303 is specifically used for: Based on the encryption key, perform key expansion operations to generate multiple sets of round encryption subkeys; Encryption operations are performed based on the encryption rounds specified in the key specification to obtain encrypted messages; the encryption operations include initial subkey XOR, byte substitution, row shifting, column obfuscation, and round key addition.

[0097] The photovoltaic grid data lightweight adaptive encryption device according to the embodiments of this application can correspond to the execution of the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the photovoltaic grid data lightweight adaptive encryption device are respectively for implementing Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0098] This application also provides a computing device. For example... Figure 4 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0099] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0100] Processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0101] Communication interface 403 is used for communication with external devices.

[0102] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0103] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned photovoltaic grid data lightweight adaptive encryption method.

[0104] Specifically, in achieving Figure 3 In the case of the illustrated embodiment, and Figure 3 When the modules or units of the photovoltaic grid data lightweight adaptive encryption device described in the embodiment are implemented through software, the following steps are performed: Figure 3 The software or program code required for the functions of each module / unit can be partially or entirely stored in memory 404. Processor 402 executes the program code corresponding to each unit stored in memory 404, and executes the aforementioned photovoltaic grid data lightweight adaptive encryption method.

[0105] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the aforementioned photovoltaic grid data lightweight adaptive encryption method.

[0106] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0107] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0108] When the computer program product is executed by a computer, the computer executes any of the aforementioned lightweight adaptive encryption methods for photovoltaic power grid data. The computer program product can be a software installation package; when any of the aforementioned lightweight adaptive encryption methods for photovoltaic power grid data needs to be used, the computer program product can be downloaded and executed on the computer.

[0109] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0110] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A lightweight adaptive encryption method for photovoltaic power grid data, characterized in that, The method includes: Acquire equipment operation data, electrical parameter data, and environmental monitoring data corresponding to the photovoltaic power grid; Based on the first equipment reference range, anomaly calculations are performed on the equipment operation data to obtain an equipment anomaly score; based on the second electrical reference range, anomaly calculations are performed on the electrical parameter data to obtain an electrical anomaly score; based on the third environmental reference range, anomaly calculations are performed on the environmental monitoring data to obtain an environmental anomaly score. Based on the first equipment weight, the second electrical weight, and the third environmental weight, the equipment anomaly score, electrical anomaly score, and environmental anomaly score are fused and calculated to obtain the photovoltaic operating state coefficient. The sensitivity level of the target is determined based on the photovoltaic operating status coefficient; Based on the target sensitivity level, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

2. The method according to claim 1, characterized in that, The system calculates anomalies in equipment operating data based on a first equipment reference range to obtain an equipment anomaly score; and calculates anomalies in electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score. Based on the third environmental baseline range, anomaly calculations are performed on environmental monitoring data to obtain environmental anomaly scores, including: For each sub-indicator in the equipment operation data, the value of the sub-indicator is compared with the first equipment reference range. If the value of the sub-indicator deviates from the first equipment reference range, the absolute difference between the value of the sub-indicator and the median value of the first equipment reference range is taken as the equipment anomaly value corresponding to the sub-indicator value. If the value of the sub-indicator is within the first equipment reference range, the equipment anomaly value corresponding to the sub-indicator value is zero. All the equipment anomaly values ​​are accumulated to obtain the equipment anomaly score. For each sub-index within the electrical parameter data, the value of the sub-index is compared with the second electrical reference range. If the value of the sub-index deviates from the second electrical reference range, the absolute difference between the value of the sub-index and the median value of the second electrical reference range is taken as the electrical anomaly value corresponding to the sub-index value. If the value of the sub-index is within the second electrical reference range, the electrical anomaly value corresponding to the sub-index value is zero. All electrical anomaly values ​​are summed to obtain the electrical anomaly score. For each sub-indicator in the environmental monitoring data, the value of the sub-indicator is compared with the third environmental benchmark range. If the value of the sub-indicator deviates from the third environmental benchmark range, the absolute difference between the value of the sub-indicator and the median value of the third environmental benchmark range is taken as the environmental anomaly value corresponding to the value of the sub-indicator. If the value of the sub-indicator is within the third environmental benchmark range, the environmental anomaly value corresponding to the value of the sub-indicator is zero. All environmental anomaly values ​​are accumulated to obtain the environmental anomaly score.

3. The method according to claim 1, characterized in that, The photovoltaic operating state coefficient is obtained by fusing the equipment anomaly score, electrical anomaly score, and environmental anomaly score based on the first equipment weight, the second electrical weight, and the third environmental weight, including: Multiply the first equipment weight by the equipment anomaly score to obtain the first weighted value; Multiply the second electrical weight by the electrical anomaly score to obtain the second weighted value; Multiply the third environmental weight by the environmental anomaly score to obtain the third weighted value; The photovoltaic operating state coefficient is obtained by summing the first weighted value, the second weighted value, and the third weighted value. The first equipment weight, the second electrical weight, and the third environmental weight are set as gradient-layered values, with the first equipment weight being greater than the second electrical weight, and the second electrical weight being greater than the third environmental weight.

4. The method according to claim 1, characterized in that, The determination of the target sensitivity level based on the photovoltaic operating state coefficient includes: Based on the numerical distribution of historical photovoltaic operating state coefficients, multiple non-overlapping sensitivity intervals are determined. The photovoltaic operating state coefficient is matched with the sensitivity interval to determine the target sensitivity interval; The target sensitivity level is determined based on the target sensitivity range.

5. The method according to claim 1, characterized in that, The encryption process, based on sensitivity levels, of the business data corresponding to the photovoltaic power grid to obtain encrypted messages includes: Encryption strategies are determined based on sensitivity levels; different encryption strategies correspond to different key specifications. Generate encryption keys based on the encryption strategy; Based on the encryption key, the business data corresponding to the photovoltaic grid is encrypted to obtain encrypted messages.

6. The method according to claim 5, characterized in that, The process of encrypting the business data corresponding to the photovoltaic power grid based on the encryption key to obtain encrypted messages includes: Based on the encryption key, perform key expansion operations to generate multiple sets of round encryption subkeys; Encryption operations are performed based on the encryption rounds specified in the key specification to obtain encrypted messages; the encryption operations include initial subkey XOR, byte substitution, row shifting, column obfuscation, and round key addition.

7. A lightweight adaptive encryption device for photovoltaic power grid data, characterized in that, The device includes: The acquisition module is used to acquire equipment operation data, electrical parameter data, and environmental monitoring data corresponding to the photovoltaic power grid; The calculation module is used to perform anomaly calculation on equipment operation data based on a first equipment reference range to obtain an equipment anomaly score; perform anomaly calculation on electrical parameter data based on a second electrical reference range to obtain an electrical anomaly score; perform anomaly calculation on environmental monitoring data based on a third environmental reference range to obtain an environmental anomaly score; and perform fusion calculation on the equipment anomaly score, electrical anomaly score, and environmental anomaly score based on the first equipment weight, the second electrical weight, and the third environmental weight to obtain the photovoltaic operating state coefficient. The encryption module is used to determine the target sensitivity level based on the photovoltaic operating status coefficient; based on the target sensitivity level, it encrypts the business data corresponding to the photovoltaic grid to obtain encrypted messages.

8. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes one or more computer instructions that, when executed by a computer, perform the method as described in any one of claims 1 to 6.

Images