A photovoltaic weather monitoring method and system based on multi-sensor cooperation

Abstract

The application discloses a kind of photovoltaic meteorological monitoring method and system based on multi-sensor cooperation, and initial signals such as irradiation, temperature and wind speed are collected by data acquisition equipment, deviation correction is carried out on initial signals using calibration model to obtain reliable parameter set, and multi-source data fusion is carried out based on the parameter set.If the deviation exceeds the threshold value during the fusion process, the abnormal points are automatically removed to form a high-quality fusion data set, then the fusion data set is efficiently sent from the perception layer to the application layer using the transmission protocol to form a complete data stream, the potential output power of photovoltaic power station is calculated by analyzing the meteorological change mode using the prediction model in the application layer, and a warning signal is triggered immediately when the predicted power is lower than the preset threshold value.Finally, the reliability verification mechanism is integrated to confirm the prediction result twice, ensuring data consistency, and finally outputting accurate monitoring report to provide scientific decision support for power station operation and maintenance.The application greatly improves the power generation efficiency and operation reliability of photovoltaic power station.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic meteorological monitoring, and particularly discloses a photovoltaic meteorological monitoring method and system based on multi-sensor cooperation. BACKGROUND

[0002] Photovoltaic meteorological monitoring is a basic field to ensure the efficient power generation and stable operation of photovoltaic power stations, which directly determines the adaptability of the power station to complex natural environment and the reliability of long-term benefits. In the outdoor environment, the meteorological conditions change dramatically, and accurate real-time meteorological parameters are of great significance to power prediction, fault diagnosis and operation and maintenance scheduling of the power station.

[0003] Although the current photovoltaic meteorological monitoring method has deployed multiple sensors, the main defect is that the data acquisition and processing process is easily affected by environmental interference and equipment limitations, resulting in that the parameter measurement accuracy is difficult to maintain stable in actual operation. The sensors are exposed to high temperature, dust, strong wind or extreme weather for a long time, and the measurement values will gradually deviate or produce noise, and the existing method often lacks timely identification and compensation mechanism for these disturbances, so that the reliability of the collected meteorological data is reduced, and then the subsequent application judgment is affected. These problems further converge into the core technical difficulty when multiple sensors work together, that is, how to ensure the high consistency and complementarity between data in the process of collecting different meteorological parameters by multiple sensors at the same time. Different sensors have different response characteristics to the same environmental factor, for example, the response speed and sensitivity of the irradiance sensor and the module backboard temperature sensor are not completely synchronized when the light changes rapidly, and the wind speed and direction sensor will be affected by local turbulence to produce instantaneous fluctuations. These differences lead to internal conflicts in multi-source data before fusion. If the data inconsistency caused by the difference in response characteristics of the sensors cannot be effectively solved, the system will face a prominent contradiction in actual business: when the light rises rapidly in the morning or a sudden gust of wind comes, the measurement values of parameters such as irradiance, temperature and wind speed will appear a short but significant deviation, and the fused meteorological information cannot accurately reflect the real affected state of the power station, resulting in that the power generation prediction deviates from the actual situation or the fault warning is delayed, and the operation and maintenance personnel are difficult to respond correctly in a timely manner.

[0004] Therefore, how to realize effective calibration and data coordination and consistency of the response characteristic difference in the process of multi-sensor cooperative perception, so as to obtain meteorological information with high reliability and truly reflecting the dynamic environmental changes of the power station, has become a key problem to improve the operation decision level of photovoltaic power stations.

[0004] Therefore, how to realize effective calibration and data coordination and consistency of the response characteristic difference in the process of multi-sensor cooperative perception, so as to obtain meteorological information with high reliability and truly reflecting the dynamic environmental changes of the power station, has become a key problem to improve the operation decision level of photovoltaic power stations. SUMMARY

[0005] The present application provides a photovoltaic meteorological monitoring method and system based on multi-sensor cooperation, which aims to solve at least one of the defects in the prior art.

[0006] An aspect of the present application relates to a photovoltaic weather monitoring method based on multi-sensor cooperation, comprising the following steps:

[0007] S100, acquiring initial collection signals by cooperatively collecting weather data through a data collection device, correcting deviations by processing the initial collection signals using a calibration model to obtain a calibrated parameter set, wherein the weather data includes irradiation parameters, temperature monitoring values, and wind speed parameters;

[0008] S200, performing data fusion operations according to the calibrated parameter set, fusing the irradiation parameters, temperature monitoring values, and wind speed parameters, and if the deviations detected during the fusion process exceed a preset threshold, eliminating the corresponding abnormal data points to determine a fused data group;

[0009] S300, using the fused data group to execute a transmission protocol in a network architecture, sending the fused data group from a perception layer to an application layer through a transmission layer to obtain a transmission completed data stream;

[0010] S400, analyzing weather change patterns through the transmission completed data stream, calculating potential output power of a photovoltaic power station using a prediction model, determining whether the potential output power of the photovoltaic power station is lower than a preset threshold, and if so, triggering a warning signal to obtain a prediction result set;

[0011] S500, integrating a reliability improvement mechanism according to the prediction result set, performing secondary verification on the prediction result set to confirm data consistency, and outputting a final weather monitoring report to support photovoltaic power station operation and maintenance decisions.

[0012] Further, step S100 comprises:

[0013] S110, cooperatively collecting weather data through a data collection device, setting different sampling frequencies for irradiation parameters, temperature monitoring values, and wind speed parameters, obtaining initial collection signals from multiple sensor nodes and performing digital processing to generate an original data set;

[0014] S120, correcting deviations using a calibration model to generate a calibrated parameter set.

[0015] Further, step S200 comprises:

[0016] S210, generating an initial fusion numerical sequence by preliminarily linearly combining the irradiation parameters, temperature monitoring values, and wind speed parameters in the calibrated parameter set using a weighted fusion algorithm;

[0017] S220, performing time series smoothing processing on the initial fusion numerical sequence using a sliding window mechanism to generate a smoothed fusion data stream;

[0018] S230, performing deviation detection on the smoothed fusion data stream according to a preset rule and removing abnormal points to generate a purified fusion data set;

[0019] S240, performing state estimation correction on the purified fusion data set, and outputting the fusion data group as a reliable fusion result of the multi-source meteorological parameters.

[0020] Further, step S300 includes:

[0021] S310, generating a packet unit by performing packet processing on the fusion data group according to a preset encoding mechanism at the perception layer;

[0022] S320, performing queue sorting according to the packet unit at the transmission layer using a preset transmission protocol to mark data priority;

[0023] S330, applying a dynamic routing selection mechanism to the sorted data queue at the transmission layer to plan a transmission path;

[0024] S340, distributing the sorted data queue to the application layer according to the transmission path and recombining to generate a complete transmission data stream.

[0025] Further, step S400 includes:

[0026] S410, extracting meteorological change key feature data from the complete transmission data stream, performing multi-dimensional analysis on the meteorological change key feature data using a preset meteorological analysis model to generate a meteorological change dynamic trend map, and obtaining a meteorological change quantitative result set;

[0027] S420, performing multi-parameter fitting analysis on the meteorological change quantitative result set combined with historical operation data of the photovoltaic power station using a preset power prediction model to determine a potential output power prediction value interval of the photovoltaic power station;

[0028] S430, obtaining real-time environmental variable data of the photovoltaic power station for the prediction value interval, and performing dynamic correction on the prediction value interval using a multi-source data fusion mechanism to obtain corrected power prediction data;

[0029] S440, if the corrected power prediction data is lower than a preset threshold range, automatically triggering an abnormal state identifier through a pre-warning signal generation module to generate a pre-warning signal data set and determine a pre-warning signal priority;

[0030] S450, according to the pre-warning signal priority, performing classification processing on the pre-warning signal data set using a hierarchical response mechanism to generate a hierarchical response instruction set and determine a prediction result set.

[0031] Further, step S500 includes:

[0032] S510, extracting reliability verification key data according to the prediction result set, adopting a preset consistency check rule to perform multi-level data comparison and analysis on the prediction result set, and obtaining a consistency deviation quantization result set;

[0033] S520, obtaining historical meteorological monitoring records of the photovoltaic power station for the consistency deviation quantization result set, tracing and positioning the deviation data through a time sequence correlation analysis mechanism, and obtaining a deviation traceability result set;

[0034] S530, according to the deviation traceability result set combined with the current meteorological real-time monitoring data, adopting a preset calibration compensation model to automatically correct the deviation data, and obtaining a corrected reliability improvement data set;

[0035] S540, if the corrected reliability improvement data set still has deviation exceeding the preset threshold, then the abnormal deviation part is recalculated through a secondary verification module, and a final unbiased reliability verification result set is obtained;

[0036] S550, generating a structured meteorological monitoring report through the final unbiased reliability verification result set, and outputting an operation and maintenance decision support report containing complete reliability confirmation information.

[0037] Another aspect of the application relates to a photovoltaic meteorological monitoring system based on multi-sensor cooperation, used to execute the above-mentioned photovoltaic meteorological monitoring method based on multi-sensor cooperation, comprising:

[0038] The calibrated parameter set acquisition module is used for acquiring initial acquisition signals by cooperatively collecting meteorological data through a data acquisition device, correcting the deviation by processing the initial acquisition signals using a calibration model, and obtaining a calibrated parameter set, wherein the meteorological data includes irradiation parameters, temperature monitoring values and wind speed parameters.

[0039] The fusion data group determination module is used for performing data fusion operation according to the calibrated parameter set, fusing the irradiation parameters, temperature monitoring values and wind speed parameters, and if the deviation exceeds the preset threshold during the fusion process, the corresponding abnormal data points are removed to determine the fusion data group.

[0040] The transmission complete data stream acquisition module is used for executing a transmission protocol in a network architecture using the fusion data group, sending the fusion data group from the perception layer to the application layer through the transmission layer, and obtaining a transmission complete data stream.

[0041] The prediction result set acquisition module is used for analyzing the meteorological change mode through the transmission complete data stream, calculating the potential output power of the photovoltaic power station using a prediction model, judging whether the potential output power of the photovoltaic power station is lower than the preset threshold, triggering an early warning signal if it is lower, and obtaining a prediction result set.

[0042] The meteorological monitoring report output module is used for integrating a reliability promotion mechanism according to the prediction result set, performing secondary verification on the prediction result set to confirm data consistency, and outputting a final meteorological monitoring report to support photovoltaic power station operation and maintenance decision-making.

[0043] The present application has the following beneficial effects:

[0044] The photovoltaic meteorological monitoring method and system based on multi-sensor cooperation provided by the present application cooperatively collect meteorological initial signals such as irradiation, temperature and wind speed through data acquisition equipment, correct the deviation of the initial signals by using a calibration model to obtain a reliable parameter set, perform multi-source data fusion based on the parameter set, automatically remove abnormal points to form a high-quality fusion data set if the deviation exceeds a threshold value during the fusion process, then use a transmission protocol to efficiently send the fusion data set from the perception layer to the application layer to form a complete data stream, analyze the meteorological change mode by using a prediction model to calculate the potential output power of the photovoltaic power station at the application layer, trigger a warning signal immediately when the predicted power is lower than a preset threshold value, and finally integrate a reliability verification mechanism to perform secondary confirmation on the prediction result to ensure data consistency, and finally output an accurate monitoring report to provide scientific decision support for power station operation and maintenance. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The figure is a flowchart of an embodiment of the photovoltaic meteorological monitoring method based on multi-sensor cooperation of the present application.

[0046] Figure 2 The figure is a function block diagram of an embodiment of the photovoltaic meteorological monitoring system based on multi-sensor cooperation of the present application.

[0047] REFERENCE SIGNS:

[0048] 10, calibration parameter set acquisition module; 20, fusion data set determination module; 30, transmission complete data stream acquisition module; 40, prediction result set acquisition module; 50, meteorological monitoring report output module. DETAILED DESCRIPTION

[0049] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the drawings in the specification and specific embodiments.

[0050] As shown in the figure, the first embodiment of the present application proposes a photovoltaic meteorological monitoring method and system based on multi-sensor cooperation, which aims to solve at least one of the defects existing in the above-mentioned prior art. Figure 1 ​

[0051] One aspect of the present application relates to a photovoltaic weather monitoring method based on multi-sensor cooperation, comprising the following steps:

[0052] Step S100, acquiring initial collection signals by cooperatively collecting weather data through data collection equipment, processing the initial collection signals using a calibration model to correct deviations, and obtaining a calibrated parameter set.

[0053] Through the cooperative collection of weather data of photovoltaic power stations by multiple types of data collection equipment, initial collection signals containing irradiation parameters, temperature monitoring values, and wind speed parameters are obtained. A calibration model is introduced to correct the deviations of the initial collection signals, eliminating equipment errors and environmental interference errors in the collection link, and obtaining a calibrated parameter set with data consistency and accuracy.

[0054] Specifically, the multiple types of data collection equipment integrate irradiation sensors, temperature sensors, and wind speed sensors, and each sensor synchronously collects data to ensure the temporal consistency of the data. The irradiation parameters include real-time irradiance, cumulative irradiation duration, and other parameters directly related to the photoelectric conversion of photovoltaic modules. The temperature monitoring values include environmental temperature, photovoltaic module surface temperature, and other parameters affecting the heat dissipation and conversion efficiency of the modules. The wind speed parameters include instantaneous wind speed, period-averaged wind speed, and other parameters affecting the heat dissipation effect of the modules and the safety of the power station structure. The calibration model can use a linear calibration model based on the least squares method or an adaptive calibration model based on machine learning, which can eliminate sensor inherent errors, irradiation value deviations caused by dust obstruction, temperature jumps caused by electromagnetic interference, and wind speed measurement errors caused by installation angle deviation, etc., to ensure the accuracy of the calibrated parameter set. At the same time, the timestamps of the calibrated parameters are aligned to ensure the consistency of the data.

[0055] Step S200, performing data fusion operations based on the calibrated parameter set, fusing irradiation parameters, temperature monitoring values, and wind speed parameters, and if the deviation exceeds the preset threshold during the fusion process, the corresponding abnormal data points are removed to determine the fusion data set.

[0056] Based on the calibrated parameter set, multi-dimensional data fusion operations are performed to fuse the irradiation parameters, temperature monitoring values, and wind speed parameters. During the fusion process, it is determined whether the data deviation exceeds the preset threshold. If the deviation exceeds the threshold, the corresponding abnormal data points are removed, and finally the effective and abnormal fusion data set is determined.

[0057] Specifically, the data fusion operation adopts a weighted fusion algorithm, establishes a correlation mapping between various parameters according to the influence weight of each meteorological parameter on the photovoltaic output power (for example, the weight of the irradiation parameter is the highest, the weight of the temperature parameter is the second, and the weight of the wind speed parameter is the third), integrates the heterogeneous calibrated parameters into a fusion data prototype with internal logical correlation; the preset threshold is calibrated based on the fluctuation range of the historical normal meteorological data of the photovoltaic power station (for example, 3 times the standard deviation of the historical data is used as the threshold), and the deviation of each data point from the fusion data prototype is compared in real time during the fusion process. If the deviation of a certain data point exceeds the preset threshold, it is determined as an abnormal data point (such as a jump value caused by sensor failure or invalid collection value in extreme weather) and is directly excluded; the linear interpolation method is used to complete the missing data after excluding abnormal data, and finally an effective, abnormal-free, and highly correlated fusion data set is formed.

[0058] Step S300, using the fusion data set to execute a transmission protocol in a network architecture, sending the fusion data set from the perception layer to the application layer through the transmission layer, obtaining a transmission completed data stream.

[0059] Based on the fusion data set, a corresponding transmission protocol is executed in the preset network architecture, relying on the transmission protocol to upload the fusion data set from the perception layer of the network architecture, after completing data transfer and transmission through the transmission layer, pushing to the application layer of the network architecture, completing full-link data transmission and forming a transmission completed data stream.

[0060] Specifically, the preset network architecture is a three-layer architecture of "perception layer-transmission layer-application layer", wherein the perception layer is a field multi-type data acquisition device responsible for generating and outputting the fusion data set; the transmission layer deploys a wireless communication module (such as LoRa (Long Range Radio), 5G (5th Generation Mobile Communication Technology) module) or a wired communication module, responsible for data transfer and transmission; the application layer is a photovoltaic power station background monitoring platform, responsible for receiving and processing data. The transmission protocol adopts a lightweight transmission protocol (such as MQTT (Message Queuing Telemetry Transport) protocol) that adapts to the real-time and integrity requirements of meteorological data, and through data compression, CRC (Cyclic Redundancy Check) verification, breakpoint resume, and other mechanisms during the transmission process, reduces the transmission bandwidth occupation, avoids data packet loss and distortion, and ensures that the fusion data set is transmitted to the application layer completely and efficiently; after completing the full-link transmission of data, a transmission completed data stream containing fusion data, time stamp, and sensor location information is formed.

[0061] Step S400, analyze the weather change mode through the transmission complete data stream, calculate the potential output power of the photovoltaic power station by using the prediction model, judge whether the potential output power of the photovoltaic power station is lower than the preset threshold, if lower, trigger the early warning signal, and obtain the prediction result set.

[0062] Based on the transmission complete data stream, the analysis of the weather change mode of the photovoltaic power station site is carried out, and the preset prediction model is substituted into the weather data in the data stream to complete the calculation of the potential output power of the photovoltaic power station. Then, it is judged whether the calculated potential output power is lower than the preset threshold. If it is determined that the potential output power is lower than the preset threshold, an early warning signal is triggered in real time. Finally, a prediction result set containing the weather change mode, the potential output power value, and the early warning state is formed.

[0063] Specifically, the weather change mode analysis is carried out through a time series analysis algorithm (such as trend fitting and period decomposition). The time series change law (such as the daily change trend of irradiance, the seasonal fluctuation characteristics of temperature) and the coupling relationship (such as the positive correlation between irradiance and environmental temperature, the negative correlation between wind speed and component surface temperature) of the irradiance parameter, the temperature monitoring value, and the wind speed parameter are mined to form the weather change mode of the photovoltaic power station site. The preset prediction model is a time series prediction model (such as an LSTM (Long Short-Term Memory) neural network model). The model takes historical weather data and photovoltaic output power data in the corresponding period as training samples. After training, real-time weather data in the transmission complete data stream is substituted into the model, and the potential output power of the photovoltaic power station can be accurately calculated. The preset threshold is based on the design output power of the photovoltaic power station or the operation and maintenance requirement (such as 80% of the design output power). If the calculated potential output power is lower than the preset threshold, it is determined that the power station has the risk of insufficient power generation efficiency, and an early warning signal (including one or more of platform pop-up warning, operation and maintenance personnel terminal SMS early warning, and on-site sound and light early warning) is triggered in real time. Finally, the weather change mode, the potential output power value, the early warning state, and the early warning trigger time are integrated to form the prediction result set.

[0064] Step S500, according to the prediction result set, integrate the reliability improvement mechanism, perform secondary verification on the prediction result set to confirm data consistency, and output the final weather monitoring report to support photovoltaic power station operation and maintenance decision.

[0065] According to the prediction result set, integrate the preset reliability improvement mechanism, perform comprehensive secondary verification operation on the prediction result set, verify and confirm the consistency and effectiveness of all data in the prediction result set, and finally output the final weather monitoring report which can directly support the photovoltaic power station operation and maintenance decision.

[0066] Specifically, the preset reliability improvement mechanism includes multi-model cross-validation and historical data backtracking verification. The multi-model cross-validation recalculates the potential output power by introducing different types of prediction models (such as a BP (Backpropagation) neural network model), compares the calculation results of different models with the potential output power values in the prediction result set, and verifies the data consistency. The historical data backtracking verification compares the current meteorological data and the potential output power value with the historical meteorological-power data of the same period, and verifies the rationality of the prediction result. Through the above secondary verification operation, the consistency and effectiveness of the meteorological change mode, the potential output power value, and the early warning state in the prediction result set are verified and confirmed. Based on the verified prediction result set, a final meteorological monitoring report is generated, which includes real-time meteorological parameters, meteorological change trend prediction (such as meteorological change in the next 24 hours), potential output power value, early warning information (including early warning level and early warning reason), and targeted operation suggestions (such as "insufficient irradiance intensity, suggest cleaning photovoltaic components" and "high temperature, suggest starting the component cooling system"). The report can directly support the operation and maintenance decision of the photovoltaic power station.

[0067] Further, the photovoltaic meteorological monitoring method and system based on multi-sensor cooperation provided by the embodiment include the following steps.

[0068] In step S110, the meteorological data is collected by multiple points through a data acquisition device. Different sampling frequencies are set for irradiation parameters, temperature monitoring values, and wind speed parameters, initial collection signals are obtained from multiple sensor nodes, and digital processing is performed to generate an original data set.

[0069] The different sampling frequencies of the irradiation parameters, temperature monitoring values, and wind speed parameters are set by the following formula:

[0070]

[0071] In formula (1), represents the sampling frequency of the i-th meteorological parameter, represents the sampling period of the i-th parameter, represents the sampling frequency of the i-th parameter, represents the sampling period of the i-th parameter, represents the sampling frequency of the i-th parameter, represents the basic time interval, represents the frequency adjustment coefficient of the i-th parameter. The control logic of formula (1) is based on the basic time interval and the frequency adjustment coefficient is used to scale the sampling frequency of different meteorological parameters. Different types of meteorological parameters (irradiation, temperature, and wind speed) are assigned corresponding , so that the sampling frequency of the parameter is calculated ​(or sampling period) Its core function is to customize differentiated sampling frequencies for different types of meteorological parameters (irradiance, temperature, wind speed)—because different meteorological parameters have different rates of change and monitoring needs (e.g., rapid changes in irradiance may require higher sampling frequencies, while slow changes in temperature can require lower frequencies). Adjustment can balance the efficiency and cost of data acquisition while ensuring monitoring accuracy.

[0072] The initial acquired signal is digitized using the following formula to achieve the conversion from analog to digital signal:

[0073] (2)

[0074] In formula (2), Indicates the first The digital output value of each sampling point Indicates the first The analog voltage value at each sampling point This represents the minimum voltage value of the analog signal. This represents the maximum voltage value of the analog signal. This represents the number of bits used in the digitization process. The control logic of formula (2) is to first process the first... Analog voltage at each sampling point ,pass Normalize to the range of 0 to 1, then multiply by The maximum quantization value of a bit digital signal Finally passed (Rounding) yields the corresponding numerical output value. Its core function is to achieve the quantization conversion from analog to digital signals: mapping continuous analog voltage signals (such as the electrical signals corresponding to meteorological parameters) to digital signals. The discrete digital values ​​corresponding to the binary bits complete the core quantization process of an analog-to-digital converter (ADC), enabling analog signals to be processed and stored by digital systems.

[0075] In a meteorological monitoring system of a solar power plant, multi-point collaborative collection is achieved by deploying data collection devices at different locations, which include multiple sensor nodes distributed around the periphery of a photovoltaic panel array and capable of capturing environmental changes in real time. Specifically, these data collection devices employ wireless sensor network technology to ensure that data is synchronously transmitted from each node to a central processing unit, avoiding data loss caused by single node failure. In one embodiment, for the collection of irradiance parameters, a high sampling frequency such as once per minute is set because irradiance intensity changes rapidly due to cloud cover, while temperature monitoring values are set to be sampled every 5 minutes to capture gradual trends, and wind speed parameters are set to be sampled every 2 minutes according to wind fluctuation characteristics, so that the setting of different frequencies helps to optimize data volume and reduce power consumption. In this way, the initial collection signals obtained from the sensor nodes are first digitized by an analog-to-digital converter, such as converting an analog voltage signal to a digital value, forming a raw data set containing a timestamp and parameter value, which includes hundreds of data points covering monitoring records within an hour.

[0076] Step S120, deviation correction of the raw data set is performed using a calibration model to generate a calibrated parameter set.

[0077] The basic transformation process of deviation correction of the raw data by the calibration model is described by the following formula:

[0078] (3)

[0079] In formula (3), represents the calibrated parameter set, represents the raw data set, represents the calibration model function, represents the calibration coefficient vector. The control logic of formula (3) is based on the raw data set , the calibration model function is combined with the calibration coefficient vector to calculate the deviation of the raw data (i.e. , and then subtract the deviation from the raw data to obtain the calibrated data . Its core role is to correct the systematic deviation of the raw data: the raw collected data may have deviations due to sensor errors, environmental interference, etc. Through the pre-determined calibration model and coefficients, the raw data is adjusted compensatorily to improve the accuracy and reliability of the data, making the data closer to the true physical quantity.

[0080] For the generated raw data set, a calibration model is used to correct for biases, eliminating the influence of inherent sensor errors or environmental interference. Specifically, the calibration model is built based on the least squares method. First, standard reference data is collected, such as benchmark irradiance values ​​measured using precision instruments. Then, the difference between the raw data and the benchmark value is calculated. Parameters are adjusted through a fitting function, for example, applying a linear correction formula to temperature data, where the correction coefficients are derived from historical data training. In one embodiment, assuming a sensor node reports an irradiance value of 800 W / m², but the benchmark value is 820 W / m², the calibration model calculates the bias and applies a correction factor such as 0.975, making the calibrated value approximately 780 W / m², ensuring accuracy. This correction process not only improves data reliability but also provides a more accurate basis for subsequent power generation prediction. For example, in the correction of wind speed parameters, if the original wind speed reading is too low due to the installation height, the model introduces a height compensation factor and generates a calibrated parameter set through iterative calculation. This set can be directly input into the energy management system to achieve optimized prediction of photovoltaic output power.

[0081] Furthermore, in the photovoltaic meteorological monitoring method and system based on multi-sensor collaboration provided in this embodiment, step S200 includes:

[0082] Step S210: Based on the irradiance parameters, temperature monitoring values, and wind speed parameters in the calibrated parameter set, perform a preliminary linear combination using a weighted fusion algorithm to generate an initial fused numerical sequence.

[0083] The initial fusion numerical sequence is obtained using the following formula:

[0084] (4)

[0085] In formula (4), Represents the first fused numerical sequence. Item value, The weighting coefficients representing the irradiation parameters, This indicates the irradiation parameters after calibration. This represents the weighting coefficient of the temperature monitoring values. This indicates the temperature monitoring value. This represents the weighting coefficient for the wind speed parameter. This represents the wind speed parameter. The control logic of formula (4) is based on the calibrated irradiance parameter. Temperature monitoring value Wind speed parameters These three types of meteorological parameters are each multiplied by their respective weighting coefficients. , , Then, the weighted results of these three parts are directly added together to obtain the first fused numerical sequence. Item value The core role of formula (4) is the weighted fusion of multiple meteorological parameters: the three types of independent meteorological parameters, i.e., irradiance, temperature, and wind speed, are linearly combined according to preset weights (reflecting the importance of different parameters) to integrate the dispersed single-dimensional parameters into an initial integrated sequence, thereby realizing the preliminary integration of multi-source meteorological data and providing uniform basic data for subsequent data analysis or model input.

[0086] For the irradiance parameter, temperature monitoring value, and wind speed parameter in the calibrated parameter set, the preliminary linear combination process through the weighted fusion algorithm is a data integration method, wherein the weighted fusion algorithm is essentially a calculation method based on weight distribution, which superimposes different parameters according to the preset importance ratio. Specifically, in the monitoring system of a solar power station, these parameters come from multiple sensor nodes, for example, the irradiance parameter represents the solar intensity, the temperature monitoring value reflects the environmental heat change, and the wind speed parameter captures the air flow speed. The weighted fusion algorithm assigns weights to each parameter, such as an irradiance parameter weight of 0.5, a temperature monitoring value of 0.3, and a wind speed parameter of 0.2. Then, they are added together through a linear combination formula to generate an initial integrated numerical sequence, which is a continuous numerical list representing the preliminary quantification of comprehensive meteorological influences. For example, in actual operation, if the irradiance parameter at a certain moment is 900 W / ㎡, the temperature monitoring value is 25℃, and the wind speed parameter is 5 m / s, then the linear combination generates a fusion value such as 620, which is used for subsequent processing. This method ensures the preliminary unification of multi-source data and avoids single-parameter dominant bias.

[0087] Step S220: Time series smoothing processing is performed on the initial integrated numerical sequence using a sliding window mechanism to generate a smoothed integrated data stream.

[0088] The smoothed integrated data stream value is obtained by the following formula:

[0089]

[0090] In formula (5), represents the time at which the smoothed integrated data stream value is obtained, represents the sliding window size. The control logic of formula (5) is to select a sliding window with a length of from the current time t as the end point (i.e., containing the fusion data from to at this time , calculate the arithmetic mean of these data, and take the average value as the smoothed integrated data stream value at time t ​Its core function is to smooth and denoise the fused data stream: through the mean calculation of the sliding window, the influence of random fluctuations or sudden noise in the fused data is weakened, making the data stream more stable and continuous, and improving the stability of the data and the reliability of subsequent analysis.

[0091] In the application scenario of a wind farm, when the initial fused numerical sequence is processed by the sliding window mechanism for time series smoothing, the sliding window mechanism is a time series processing technology that reduces noise by defining a fixed-size window that moves over the sequence and calculates the average or median of the data within the window. Specifically, this sliding window mechanism sets the window size to 10 data points, and slides point by point on the sequence, for example, the initial fused numerical sequence contains a series of values such as 620, 615, 630, etc. The window takes the average of the first 10 points as the first smoothed point, then moves one step to take the average of the next 10 points, generating a smoothed fused data stream. This data stream more smoothly reflects the trend of weather changes, avoiding sudden fluctuations.

[0092] Step S230, detect the deviation of the smoothed fused data stream by a preset rule and remove abnormal points to generate a purified fused data set.

[0093] The process of detecting the deviation of the smoothed fused data stream by a preset rule and removing abnormal points to generate a purified fused data set, the preset rule is a judgment standard based on threshold or statistical method, for example, set a deviation threshold of the average value of the data stream plus or minus twice the standard deviation, if a point exceeds this range it is considered abnormal and removed. Specifically, in the urban environment monitoring project, the smoothed fused data stream shows a series of fused values such as 618, 620, 850, 622, among which 850 is significantly higher, which is removed by rule detection, and the remaining points form a purified fused data set. This purification ensures the reliability of the data and provides a clean basis for subsequent analysis.

[0094] Step S240, state estimation correction is performed on the purified fused data set, and the fused data group is output as a reliable fusion result of the multi-source weather parameters.

[0095] The optimal information fusion based on covariance inverse weighting is represented by the following formula to realize the state estimation correction of the purified fused data set:

[0096]

[0097] In formula (6), represents the reliable fusion result after state estimation correction, represents the state estimation of the th purified data source, represents the covariance matrix of the th data source, denotes the fused covariance matrix, denotes the number of data sources. The control logic of formula (6) is to first calculate the sum of the inverse matrices of all the purified data source covariance matrices , then take the inverse of the sum to obtain the fused covariance matrix ; then calculate the sum of the product of each data source covariance inverse matrix and the state estimation of itself, and then multiply by , and finally obtain the reliable fusion result of the state estimation after correction . The core role is to perform high-precision weighted fusion on multiple data sources: taking the inverse of the covariance matrix (reflecting the uncertainty of the data) as the weight (the smaller the uncertainty of the data source, the greater the weight), and performing weighted fusion on the state estimation of multiple purified data sources, which not only integrates multi-source information but also reduces the influence of data uncertainty, thereby improving the accuracy and reliability of state estimation.

[0098] When the state estimation correction is performed on the purified fused data set and the fused data set is output as the reliable fusion result of the multi-source meteorological parameter, the state estimation correction is an optimization technique, and the principle of Kalman filter is often used to estimate the true state. It adjusts the values in the data set to correct potential errors through iteration. Specifically, in the photovoltaic power generation optimization business, the purified fused data set is applied to correction, for example, the initial data set has values such as 620, 618, 622, and the state estimation considers the historical state and measurement noise to gradually correct to a more accurate set such as 619, 617, 621, and output as the fused data set. This correction improves the overall accuracy and brings more accurate power generation prediction results in business, supporting decision-making for energy management.

[0099] Further, the photovoltaic meteorological monitoring method and system based on multi-sensor collaboration provided in the embodiment, step S300 comprises:

[0100] Step S310, according to the characteristics of the fused data set, the package processing is performed through the preset encoding mechanism in the perception layer to generate a package unit.

[0101] The following formula is used for the package processing of the perception layer according to the characteristics of the fused data set:

[0102] (7)

[0103] In formula (7), denotes the generated th package unit, denotes the preset encoding mechanism, denotes the fused data set, denotes the number of packages. The control logic of formula (7) is to generate a package unit according to the preset encoding mechanism The fusion data set is split into corresponding sub-packet units According to the number of sub-packets According to the requirements, it is split into corresponding sub-packet units That is, a complete fusion data set is encoded and divided into Parts). Its core role is to adapt to the transmission / storage requirements of the perception layer: according to the characteristics of the fusion data set, the data is split into appropriate size units through encoding and sub-packet processing, which facilitates the efficient transmission, storage or subsequent processing of the perception layer, and avoids the transmission pressure or storage inconvenience caused by large volume data.

[0104] For the characteristics of the fusion data set, the preset encoding mechanism is a structured encoding method for data packets when sub-packet processing is performed in the perception layer. It divides the fusion data set into smaller units according to size and type to adapt to network transmission requirements. Specifically, in the monitoring system of a solar power station, the fusion data set contains integrated value sequences of irradiance, temperature and wind speed, such as a data set with hundreds of point values. First, the encoding mechanism defines the packet header, including data type identification, length field and check code, then the data set is uniformly divided, for example, a 1000 byte data set is divided into 10 100 byte sub-packet units, each unit carries an independent serial number to ensure reconstruction in transmission. This sub-packet processing reduces the risk of packet loss caused by large single packets, supporting efficient perception layer data acquisition.

[0105] Step S320, according to the sub-packet units, queue sorting is performed in the transmission layer using a preset transmission protocol, and data priority is marked.

[0106] The data packets are queue sorted by the following formula:

[0107] (8)

[0108] In formula (8), represents the transmission layer queue sorting result, represents the data packet set, represents the preset transmission protocol, represents the queue sorting operation of the data packet according to the protocol rules of the preset transmission protocol. The control logic of formula (8) is to perform sorting operation on the data packet set according to the rules defined by the preset transmission protocol (such as priority, data type, timing, etc.), and finally obtain the queue sorting result of the transmission layer. Its core role is to standardize the transmission order of data packets: sort data packets according to the rules of the transmission protocol (such as high priority data transmission first), so that the data packet queue of the transmission layer conforms to the communication specification, and guarantees the order, efficiency or priority requirements of data transmission.

[0109] In the application scenario of a wind power plant, according to the packet unit, when queue sorting is performed in the transport layer using a preset transport protocol, the preset transport protocol is a custom protocol based on TCP (Transmission Control Protocol) or UDP (User Datagram Protocol), which realizes the ordered arrangement of data through queue management. Specifically, this process first places the packet unit into a buffer queue, and then sorts it according to protocol rules such as FIFO (First In First Out) or priority queue, while marking the data priority, for example, marking real-time wind speed related units as high priority and historical temperature units as medium priority, and ensuring that high priority data is processed first by using the priority field in the protocol, such as the value of 0-3. This sorting mechanism can prioritize the transmission of critical meteorological data in the business, avoiding the impact of delay on power generation control.

[0110] Step S330, according to the sorted data queue, a dynamic routing mechanism is applied in the transport layer to plan the transmission path.

[0111] The following formula is used to dynamically select a transmission path for each data item by minimizing the sum of the costs of all links on the path:

[0112]

[0113] In formula (9), represents the optimal transmission path selected for the th data item in the sorted data queue, represents the set of all paths, represents the current dynamic cost of link , represents that this rule covers every data item in the data queue . The control logic of formula (9) is to traverse all the available transmission path set for each data item in the data queue , calculate the sum of the dynamic costs of all links on each path , and select the path with the smallest total link cost as the optimal transmission path for the data item. Its core function is to optimize the cost of data transmission: dynamically match the transmission path with the lowest link cost for each data item, minimize resource consumption (such as bandwidth, delay, etc.) in the transmission process while ensuring data transmission, and improve the resource utilization efficiency of the transmission system.

[0114] According to the sorted data queue, when the transmission layer applies the dynamic routing mechanism to plan the transmission path, the dynamic routing mechanism is a strategy that adjusts the path in real time according to the network state, which selects the path by evaluating the link load, delay and bandwidth. Specifically, in the photovoltaic power generation optimization system, the mechanism is applied to the sorted queue. First, the network node state is monitored. For example, if congestion is detected on the main path, switch to the backup path. For example, there are high-priority packet units in the queue. The mechanism calculates the path cost, considers the delay weight 0.6 and the bandwidth weight 0.4 using a simple weighted formula, and selects the path with the lowest cost. This planning ensures efficient data flow in complex networks and supports multi-site data synchronization in business.

[0115] Step S340, according to the transmission path, the sorted data queue is distributed to the application layer and recombined to generate a complete data stream.

[0116] The complete data stream is obtained by the following formula:

[0117] (10)

[0118] In formula (10), represents the complete data stream generated by recombination, represents the data queue distributed to the application layer, represents the recombination operation on the distributed data packet in the application layer to restore the complete original data stream. The control logic of formula (10) is to perform the recombination operation on the data queue distributed to the application layer to splice and integrate the scattered data packets previously packaged and transmitted, and finally obtain the complete data stream . Its core function is to restore the original complete data stream: offset the data fragmentation caused by the packaging in the perception layer and the distribution in the transmission layer, restore the scattered data packet to the original complete data stream, and ensure that the application layer can obtain continuous and complete effective data.

[0119] When the sorted data queue is distributed to the application layer and recombined to generate a complete data stream according to the transmission path, this process involves data forwarding under path guidance and application layer reconstruction. Specifically, in the urban energy monitoring project, the queue is distributed along the planned path, such as being forwarded to the application server through the router, and then being recombined in the application layer according to the packet sequence number and check code. For example, after receiving the original packet units 1-10, they are spliced back into a fused data group in sequence to form a complete data stream such as a continuous irradiation temperature sequence. This recombination ensures the integrity of the data, which can provide reliable input for the prediction model in business and support energy distribution decisions.

[0120] Further, the photovoltaic weather monitoring method and system based on multi-sensor cooperation provided by the embodiment, step S400 comprises:

[0121] Step S410: Extract key feature data of meteorological changes by transmitting the data stream, use a preset meteorological analysis model to perform multi-dimensional analysis of the key feature data of meteorological changes, generate a dynamic trend map of meteorological changes, and obtain a set of quantitative results of meteorological changes.

[0122] The quantitative results set of meteorological changes are obtained using the following formula:

[0123]

[0124] In formula (11), Indicates the time span, This represents the time series of the analysis results. This represents the set of quantitative results of meteorological changes. Indicates cumulative trend, Indicates extreme value characteristics, This indicates volatility. The control logic of formula (11) is based on the time span. Within, the time series of meteorological analysis results Simultaneously, three key indicators—cumulative trend, extreme value characteristics, and volatility—are calculated, and these three indicators are ultimately integrated into a set of quantitative results for meteorological changes. Its core function is to quantify meteorological change characteristics in multiple dimensions: from the perspectives of cumulative trend, extreme values, and fluctuations, it comprehensively extracts key information from meteorological time series, transforming continuous meteorological changes into a quantifiable set of features, which facilitates subsequent analysis of the patterns or impacts of meteorological changes.

[0125] When extracting key meteorological change features from a transmitted data stream, the process first involves filtering out core meteorological indicators, such as irradiance fluctuation rate, temperature gradient, and wind speed variation coefficient. These features are obtained by parsing the time series data in the data stream. Specifically, the pre-defined meteorological analysis model is a hybrid model based on statistics and machine learning, including principal component analysis and time series decomposition components. The key feature data is first input into the model, and then subjected to multi-dimensional analysis, such as decomposition of time, space, and correlation dimensions. For example, when analyzing irradiance, the meteorological analysis model separates seasonal trends from random noise, and then generates a dynamic trend map of meteorological changes. This is a visual representation, such as a line chart combined with a heat map, ultimately yielding a quantitative set of meteorological change results, including numerical trend indicators such as average rate of change and peak deviation.

[0126] Step S420: Based on the quantitative results set of meteorological changes and the historical operation data of the photovoltaic power station, a multi-parameter fitting analysis is performed using a preset power prediction model to determine the range of potential output power prediction values ​​for the photovoltaic power station.

[0127] The potential output power prediction value interval of the photovoltaic power station is determined by the following formula:

[0128]

[0129] In formula (12), and represent the lower limit and the upper limit of the potential output power prediction value interval, represents the prediction power mean, represents the statistical quantity corresponding to the confidence level, represents the prediction standard deviation based on the historical data and the meteorological quantity. The control logic of formula (12) is centered on the prediction power mean , combined with the statistical quantity corresponding to the confidence level and the prediction standard deviation , to calculate the deviation range ; the lower limit of the interval is obtained by subtracting the deviation from the mean, and the upper limit of the interval is obtained by adding the deviation to the mean, so as to determine the prediction interval of the potential output power. The core function is to quantify the uncertainty range of the power prediction: instead of giving only a single prediction power value, the possible fluctuation range of the photovoltaic power station output power is reflected in the form of the confidence interval, so that the prediction result is more in line with the actual situation (considering the uncertainty of meteorological factors), and the power station can make more reasonable power scheduling or risk assessment.

[0130] When the set of quantified results based on meteorological changes is combined with the historical operation data of the photovoltaic power station, the preset power prediction model is a neural network-based model, such as a long short-term memory network, which integrates the quantified indicators in the result set and historical data such as the power generation in the past year and environmental records through multi-parameter fitting analysis. Specifically, this fitting process first normalizes the data, then uses the input layer of the preset power prediction model to receive multi-parameters such as the quantified values of irradiance and temperature, adjusts the weights in the hidden layer to fit the non-linear relationship, and finally outputs the potential output power prediction value interval of the photovoltaic power station, for example, an interval such as 800-1200 kilowatt-hours, which supports early planning of energy output in business.

[0131] In step S430, real-time environmental variable data of the photovoltaic power station is obtained for the prediction value interval, and the prediction value interval is dynamically corrected through a multi-source data fusion mechanism to obtain corrected power prediction data.

[0132] The corrected power prediction data is obtained by the following formula:

[0133] (13)

[0134] In formula (13), represents the corrected power prediction data, This represents the power prediction value corresponding to the original prediction range. This represents the dynamic correction amount calculated based on real-time environmental variables. The control logic of formula (13) uses the power prediction value corresponding to the original prediction value range. Based on this, plus dynamic corrections calculated based on real-time environmental variables. The corrected power prediction data were obtained. Its core function is to optimize power prediction accuracy by combining real-time environmental data: the original power prediction may be based on historical / predictive quantitative data, and by introducing dynamic correction values ​​corresponding to real-time environmental variables, the original prediction value is adjusted to offset the prediction deviation caused by changes in the real-time environment and improve the real-time accuracy of power prediction.

[0135] When acquiring real-time environmental variable data for photovoltaic power plants within the predicted range, this data includes current humidity, cloud cover, etc. Dynamic correction is performed through a multi-source data fusion mechanism. This mechanism is a strategy that combines weighted averaging and Kalman filtering. It first collects real-time data sources such as satellite imagery and ground sensors, and then applies correction to the predicted range. For example, if the real-time irradiance is lower than expected, the mechanism will adjust the lower limit of the range, ultimately obtaining corrected power prediction data accurate to 950 kWh.

[0136] Step S440: If the corrected power prediction data is lower than the preset threshold range, the abnormal state indicator is automatically triggered by the warning signal generation module to generate a warning signal dataset and determine the priority of the warning signal.

[0137] The following formula is used to define the triggering conditions for an abnormal status indicator:

[0138] (14)

[0139] In formula (14), Indicates an abnormal status indicator. This indicates the lower limit of the preset threshold range. As an indicator function, when the corrected power prediction data Below the lower limit of the preset threshold range hour, The value is 1 if it is set to 1, and 0 otherwise. The control logic of formula (14) is achieved through an indicator function. Determine the corrected power prediction data Is it below the lower limit of the preset threshold range? —If it is lower than that, an abnormal status is indicated. 1; otherwise, 0. Its core role is to identify the abnormally low state of power prediction: when the corrected power prediction is lower than the preset lower limit (which may correspond to the risk of abnormal power plant output, power shortage, etc.), trigger the abnormal identification, so as to timely alarm and take subsequent processing measures.

[0140] If the corrected power prediction data is lower than the preset threshold range, such as lower than 700 kilowatts, the warning signal generation module automatically triggers the abnormal state identification. This warning signal generation module is a rule engine that generates a warning signal data set based on threshold comparison, including signal types such as low power warning, and determines the priority through severity scoring such as 1-5 levels.

[0141] Step S450, according to the warning signal priority, a hierarchical response mechanism is adopted to classify and process the warning signal data set, generate a hierarchical response instruction set, and determine the prediction result set.

[0142] The hierarchical response instruction set is obtained by the following formula:

[0143] (15)

[0144] In formula (15), represents the hierarchical response instruction set, represents the warning signal priority, represents the warning signal data set, represents the mapping function for classifying and processing the data set according to the priority. The control logic of formula (15) is to classify and process the warning signal data set by combining the priority of the warning signal, and finally generate the hierarchical response instruction set . Its core role is to realize the hierarchical response of the warning: according to the priority difference of the warning signal, classify and process the warning data set, match the corresponding response instruction, so that different severity of the warning corresponds to different level of response measures, improve the pertinence and efficiency of the response.

[0145] The prediction result set is obtained by the following formula:

[0146] (16)

[0147] In formula (16), represents the prediction result set, represents the function for determining the final prediction result based on the hierarchical response instruction set. The control logic of formula (16) is to determine the final prediction result by the function based on the hierarchical response instruction set As input, based on the hierarchical rules or processing logic in the instruction set, determine and output the corresponding final prediction result set. Its core function is to link response instructions with final predictions: it transforms the processing logic in the hierarchical response instruction set into specific prediction results, so that the decision of early warning response can be implemented into an output set of prediction results, ensuring the consistency between prediction results and response strategies.

[0148] When a graded response mechanism is adopted based on the priority of early warning signals, this graded response mechanism is a hierarchical processing framework. It classifies the dataset, such as high priority for immediate response and medium priority for scheduling and inspection, generates a graded response instruction set, such as notifying the maintenance team or adjusting the load, and finally determines the prediction result set. This ensures timely intervention in business to maintain the stable operation of the power plant.

[0149] Furthermore, in the photovoltaic meteorological monitoring method and system based on multi-sensor collaboration provided in this embodiment, step S500 includes:

[0150] Step S510: Extract key data for reliability verification based on the prediction result set, and perform multi-level data comparison and analysis on the prediction result set using preset consistency verification rules to obtain a consistency deviation quantification result set.

[0151] The consistency deviation quantification result set is obtained using the following formula:

[0152] (17)

[0153] In formula (17), This represents the result set of consistency deviation quantification. Indicates the first The quantified value of the deviation of each prediction result. This indicates the preset consistency check threshold. This represents the total number of prediction result sets, and the consistency deviation quantification result set only includes deviation values ​​exceeding the threshold. The control logic of formula (17) is to traverse all... Quantitative value of the deviation of each prediction result Filter out those that meet the deviation quantification value Greater than the preset consistency check threshold Those values, those deviations exceeding the threshold are grouped into a set. The core function of formula (17) is to focus on significant deviations: from all the deviations of the prediction results, only the part that exceeds the preset threshold is extracted, and the acceptable small deviations are filtered out, so as to identify the consistency deviation items that need to be focused on and dealt with, which is convenient for subsequent targeted analysis or correction.

[0154] No. The quantified value of the deviation of each prediction result is obtained by the following formula:

[0155] (18)

[0156] In formula (18), represents the total number of comparison levels, represents the weight of the th level, represents the prediction value of the th prediction result at the th level, represents the reference value or key data value of the th prediction result at the th level. The control logic of formula (18) is that for the th prediction result, first calculate the absolute difference value between the prediction value and the reference value at each comparison level (i.e. ), then assign the absolute difference value of each level with the corresponding weight and multiply, and finally sum up the weighted results of all levels to get the deviation quantization value of the prediction result. The core role of formula (18) is multi-dimensional weighted quantization of deviation: considering the importance of prediction results at different levels (dimensions) is different, through weight distribution, the deviation degree of multiple comparison levels is comprehensively considered, and a quantization value reflecting the overall deviation is obtained, so that the deviation evaluation is more comprehensive and conforms to the actual focus.

[0157] When extracting reliability verification key data for the prediction result set, this process mainly focuses on filtering out data indicators directly related to reliability evaluation from the prediction result set, such as predicted power value, weather condition parameters, and historical comparison data, etc. Specifically, the extraction process will eliminate redundant information in the original prediction result set through data cleaning and feature selection mechanism, and retain core fields such as daily irradiance change rate and temperature fluctuation amplitude for subsequent consistency verification. For example, in the business scenario of a certain photovoltaic power station, assuming that the prediction result set contains 24 hours of power prediction data in the past, the extraction will preferentially focus on the matching degree index of predicted value and actual operation data, to ensure that the data can reflect the true running state.

[0158] When performing multi-level data comparison analysis on the prediction result set using the preset consistency check rule, it should be noted that the consistency check rule is usually a logical framework based on multi-dimensional comparison, covering time dimension, space dimension, and parameter correlation dimension, etc. For example, in the time dimension, the prediction data is compared with the historical data of the same period to analyze whether there is a significant deviation; in the space dimension, the prediction data of multiple photovoltaic power stations in the same region is compared to determine whether there is a regional anomaly. Specifically, in a certain analysis, assuming that the predicted power value of a certain power station is high in a certain time period, while the historical data and the data of the neighboring power stations in the same period show low power output, then this deviation will be recorded, and its degree will be quantified as part of the consistency deviation quantification result set, such as deviation percentage or absolute difference.

[0159] Step S520, for the consistency deviation quantification result set, obtain the historical meteorological monitoring records of the photovoltaic power station, trace and locate the deviation data through the time sequence correlation analysis mechanism, and obtain the deviation trace result set.

[0160] The deviation trace result set is obtained by the following formula:

[0161] (19)

[0162] In formula (19), represents the deviation trace result set, represents the meteorological record with the highest time sequence correlation with the th deviation , represents the time sequence correlation analysis function, represents the meteorological feature vector of the time point . The control logic of formula (19) is to calculate the correlation between the th deviation and the meteorological feature vector of different time points through the time sequence correlation analysis function , find the meteorological record corresponding to the time point with the maximum correlation, and all such composes the deviation trace result set . The core role of formula (19) is to locate the associated meteorological factors of the deviation: through time sequence correlation analysis, find the meteorological record most related to each deviation, and thus trace the potential meteorological inducement of the deviation, providing basis for subsequent analysis of the source of the deviation and optimization of data quality.

[0163] The consistency deviation quantification result set obtains historical meteorological monitoring records of the photovoltaic power station and traces and locates through a time sequence correlation analysis mechanism. The time sequence correlation analysis mechanism is an analysis tool based on time sequence data mining, and is used to find the root cause of the deviation. For example, in the business of a certain photovoltaic power station, it is found that the predicted power deviation is large. Through the time sequence correlation analysis mechanism, the historical meteorological records are traced back, and it is found that the deviation is caused by the sudden change of cloud coverage rate in a certain period of time which is not fully considered, and then the specific time point and meteorological factors are located to form a deviation traceability result set. This process helps the operation and maintenance team to clarify the root cause of the problem and provides a basis for subsequent calibration.

[0164] In step S530, according to the deviation traceability result set combined with the current meteorological real-time monitoring data, a preset calibration compensation model is used to automatically correct the deviation data to obtain a corrected reliability improvement data set.

[0165] The corrected reliability improvement data set is obtained by the following formula:

[0166] (20)

[0167] In formula (20), represents the corrected reliability improvement data set, represents a preset weight of the deviation traceability result set, represents the current meteorological real-time monitoring data, represents a preset weight of the meteorological real-time monitoring data, represents the deviation data, represents a preset weight of the deviation data. The control logic of formula (20) is that the deviation traceability result set , the current meteorological real-time monitoring data , and the deviation data are multiplied by the respective preset weights , , , the weighted results of the three are summed, and then divided by the sum of the weights (achieving weighted average), and finally the corrected reliability improvement data set is obtained. The core function of formula (20) is to fuse multiple source data to optimize reliability: combining the correlation information of deviation traceability, real-time meteorological data, and original deviation data, and distributing the weights to reflect the importance of different data, and correcting the data by weighted fusion, which not only retains the effective information, but also weakens the influence of deviation, and improves the reliability of the final data set.

[0168] When automatically correcting deviation data using a pre-set calibration compensation model based on the deviation source tracing results set and current real-time meteorological monitoring data, the calibration compensation model is typically a dynamic adjustment framework that combines historical and real-time data. Its aim is to reduce prediction deviations through parameter compensation. For example, in actual operations, if the source tracing results show that cloud cover is the main source of deviation, the calibration compensation model will adjust the predicted power value downwards based on the cloud cover ratio in the real-time meteorological monitoring data, generating a corrected reliability-enhanced dataset. This process ensures that the predicted data more closely reflects the actual operating environment.

[0169] Step S540: If the corrected reliability improvement dataset still has deviations exceeding the preset threshold, the abnormal deviation part is recalculated through the secondary verification module to obtain the final unbiased reliability verification result set.

[0170] The following formula is used to define the judgment criteria for abnormal deviations:

[0171] (twenty one)

[0172] In formula (21), Indicates the first Does each sample belong to the abnormal deviation portion? Indicates the first A revised reliability value, Indicates a reference reliability value. Indicates the preset threshold. A value of 1 indicates that this part is an abnormal deviation and requires secondary verification. The control logic of formula (21) is for the first... Calculate the corrected reliability value for each sample. Compared with reference reliability value The absolute difference, if the difference is greater than a preset threshold Then mark (Identified as an abnormal deviation); otherwise marked. (Judged as normal). The core function of formula (21) is to identify abnormal deviation samples: by comparing the difference between the corrected reliability value and the reference value, samples with deviations exceeding the threshold are selected and marked as abnormal items that need to be verified a second time, so as to facilitate subsequent targeted verification of data quality.

[0173] The final unbiased reliability verification result set is obtained through the following formula:

[0174] (twenty two)

[0175] In formula (22), This represents the final unbiased reliability verification result set. This indicates the result obtained by recalculating the abnormal deviation portion. a mask matrix representing abnormal deviation parts, represents point-by-point multiplication of elements, and the formula realizes targeted replacement of abnormal deviation parts. The control logic of formula (22) is to combine the two parts of data point by point by means of the abnormal deviation mask matrix (wherein the position corresponding to the abnormal deviation is 1, and the normal position is 0). The core function is to accurately correct the abnormal deviation: only the abnormal deviation part marked before is replaced by the reliable result recalculated, and the normal part is kept as the original data, which not only repairs the abnormal problem, but also avoids unnecessary modification of effective data, and efficiently obtains the unbiased reliability verification result.

[0176] The mask matrix of the abnormal deviation part is obtained by the following formula:

[0177] (23)

[0178] In formula (23), a mask matrix representing abnormal deviation parts, a deviation distribution of the corrected data set, a preset threshold, an indicator function, an absolute value of deviation, when the absolute value of deviation exceeds the preset threshold , the corresponding position is 1, otherwise 0; the formula is used to locate the abnormal deviation part that needs secondary verification. The control logic of formula (23) is to judge whether the absolute value of the deviation value of each position in the deviation distribution of the corrected data set exceeds the preset threshold by means of the indicator function . If it exceeds, the mask matrix element corresponding to the position is set to 1; otherwise, it is set to 0, and finally the mask matrix is obtained. The core function is to locate the specific position of the abnormal deviation: mark the position of the deviation exceeding the threshold in the corrected data set as 1, and clearly indicate which part belongs to the abnormal deviation that needs secondary verification, to provide accurate position identification for the subsequent.

[0179] If the corrected reliability improvement data set still has deviation exceeding the preset threshold, when the secondary verification module is used for targeted recalculation, the secondary verification module is an auxiliary tool for processing abnormal data, which usually combines more fine-grained analysis rules and backup data sources to reevaluate. For example, in a certain business operation, if the corrected power prediction value still exceeds the threshold range, the secondary verification module will call additional meteorological satellite data to recalculate the prediction value of the abnormal time period, and finally generate an unbiased reliability verification result set to ensure data accuracy.

[0180] Step S550, generate a structured weather monitoring report through the final unbiased reliability verification result set, and output an operation and maintenance decision support report containing complete reliability confirmation information.

[0181] The operation and maintenance decision support report is calculated by weighted summation using the following formula:

[0182]

[0183] In formula (24), represents the operation and maintenance decision support level, represents the candidate decision scheme, represents the number of types of reliability confirmation information in the report, represents the decision The compatibility score under the first class information, represents the weight of the first class information. The control logic of formula (24) is to calculate the product sum (i.e. weighted summation) of the compatibility score of each candidate decision scheme under the class reliability confirmation information and the corresponding information weight , and then select the scheme with the maximum weighted sum from all candidate schemes, and the corresponding level is the optimal operation and maintenance decision support level . The core function of formula (24) is to screen the optimal operation and maintenance decision scheme: combine the weights of different types of reliability information (reflecting the importance of information), calculate the comprehensive compatibility score of each candidate decision, and select the operation and maintenance decision that best matches the current reliability information by maximizing the score, to improve the rationality and support of the decision.

[0184] When generating a structured weather monitoring report through the final unbiased reliability verification result set, it should be noted that this report is usually presented in a standardized format, containing reliability confirmation information, bias correction records, and weather condition summaries. For example, in the operation and maintenance scenario of a certain photovoltaic power station, the generated structured weather monitoring report will list the predicted power value, correction process and final confirmed reliability index of each time period in detail, and will also include a brief analysis of the weather conditions in the next 24 hours, output as an operation and maintenance decision support report, providing data support for power station management.

[0185] See Figure 2 The embodiment provides a photovoltaic weather monitoring system based on multi-sensor cooperation, which is used to execute the above-mentioned photovoltaic weather monitoring method based on multi-sensor cooperation, and comprises a calibrated parameter set acquisition module 10, a fusion data group determination module 20, a transmission completed data stream acquisition module 30, a prediction result set acquisition module 40, a reliability verification result set acquisition module 50, and a structured weather monitoring report generation module 60. The taking module 40 and the weather monitoring report output module 50, wherein the calibrated parameter set acquisition module 10 is configured to acquire initial acquisition signals by cooperatively collecting weather data through a data acquisition device, and corrects the bias by processing the initial acquisition signals using a calibration model to obtain a calibrated parameter set, wherein the weather data includes irradiation parameters, temperature monitoring values, and wind speed parameters; the fusion data group determination module 20 is configured to perform data fusion operations according to the calibrated parameter set, fuse the irradiation parameters, the temperature monitoring values, and the wind speed parameters, and if the bias exceeds a preset threshold during the fusion process, the corresponding abnormal data points are removed to determine a fusion data group; the transmission completed data stream acquisition module 30 is configured to execute a transmission protocol in a network architecture using the fusion data group, and send the fusion data group from a perception layer to an application layer through a transmission layer to obtain a transmission completed data stream; the prediction result set acquisition module 40 is configured to analyze weather change patterns by the transmission completed data stream, calculate potential output power of a photovoltaic power station using a prediction model, determine whether the potential output power of the photovoltaic power station is lower than a preset threshold, and if so, trigger a warning signal to obtain a prediction result set; and the weather monitoring report output module 50 is configured to integrate a reliability improvement mechanism according to the prediction result set, perform secondary verification on the prediction result set to confirm data consistency, and output a final weather monitoring report to support photovoltaic power station operation and maintenance decisions.

[0186] Compared with the prior art, the photovoltaic weather monitoring method and system based on multi-sensor cooperation provided in the embodiment cooperatively collect initial signals such as irradiation, temperature, and wind speed through a data acquisition device, correct the bias of the initial signals using a calibration model to obtain a reliable parameter set, perform multi-source data fusion based on the parameter set, automatically remove abnormal points to form a high-quality fusion data group if the bias exceeds a threshold during the fusion process, then use a transmission protocol to efficiently send the fusion data group from a perception layer to an application layer to form a complete data stream, analyze weather change patterns and calculate potential output power of a photovoltaic power station through a prediction model in the application layer, immediately trigger a warning signal when the predicted power is lower than a preset threshold, finally integrate a reliability verification mechanism to perform secondary verification on the prediction result to ensure data consistency, and finally output an accurate monitoring report to provide scientific decision support for power station operation and maintenance. The embodiment effectively solves the problems of inaccurate power prediction and delayed warning caused by weather data bias, abnormal interference, and unstable transmission of the photovoltaic power station, realizes precise control of the whole link from data collection, calibration, fusion, transmission to prediction of weather data, and greatly improves the power generation efficiency and operation reliability of the photovoltaic power station.

[0187] ​While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims include all such variations and modifications as fall within the scope of the present application. It is apparent that those skilled in the art can modify and adapt the present application in various ways without departing from the spirit and scope of the present application. It is therefore intended that the present application encompass all such modifications and variations as fall within the scope of the claims and their equivalents.

Claims

1. A photovoltaic meteorological monitoring method based on multi-sensor collaboration, characterized in that, The method comprises the following steps: S100, acquiring initial collection signals by cooperatively collecting meteorological data through a data collection device, processing the initial collection signals by using a calibration model to correct deviations, and obtaining a calibrated parameter set, wherein the meteorological data comprises irradiation parameters, temperature monitoring values, and wind speed parameters; S200, performing a data fusion operation according to the calibrated parameter set, fusing the irradiation parameters, the temperature monitoring values, and the wind speed parameters, and if a deviation exceeding a preset threshold is detected in the fusion process, removing corresponding abnormal data points and determining a fused data group; S300, using the fused data group to execute a transmission protocol in a network architecture, sending the fused data group from a perception layer to an application layer through a transmission layer, and obtaining a transmission completed data stream; S400, analyzing a meteorological change mode through the transmission completed data stream, calculating potential output power of a photovoltaic power station by using a prediction model, judging whether the potential output power of the photovoltaic power station is lower than a preset threshold, triggering a warning signal if it is lower than the preset threshold, and obtaining a prediction result set; S500, integrating a reliability improvement mechanism according to the prediction result set, performing secondary verification on the prediction result set to confirm data consistency, and outputting a final meteorological monitoring report to support photovoltaic power station operation and maintenance decision-making; Step S500 comprises: S510, extracting reliability verification key data according to the prediction result set, performing multi-level data comparison and analysis on the prediction result set by using a preset consistency check rule, and obtaining a consistency deviation quantification result set; The consistency deviation quantification result set is obtained through the following formula: wherein, represents a set of consistency deviation quantification results, represents a deviation quantification value of a th prediction result, represents a preset consistency check threshold value, represents a total number of the set of prediction results, and the set of consistency deviation quantification results only contains deviation values exceeding the threshold value; The bias quantization value of the first prediction result is obtained by the following formula: bias quantization value = (prediction result - actual result) / (actual result) wherein, represents the total number of levels, represents the weight of the level, represents the prediction value of the prediction result at the level, represents the reference value or key data value of the prediction result at the level; S520, obtaining historical meteorological monitoring records of the photovoltaic power station for the consistency deviation quantification result set, tracing and positioning deviation data through a time sequence correlation analysis mechanism, and obtaining a deviation traceability result set; The deviation traceability result set is obtained through the following formula: wherein, denotes a set of deviation provenance results, denotes a deviation between a first meteorological record with highest temporal correlation, denotes a temporal correlation analysis function, denotes a time point meteorological feature vector; S530, according to the deviation traceability result set and in combination with current meteorological real-time monitoring data, automatically modifying the deviation data by using a preset calibration compensation model, and obtaining a modified reliability improvement data set; S540, if the modified reliability improvement data set still has a deviation exceeding a preset threshold, performing targeted recalculation on the abnormal deviation part through a secondary verification module, and obtaining a final unbiased reliability verification result set; S550, generating a structured meteorological monitoring report through the final unbiased reliability verification result set, and outputting an operation and maintenance decision-making support report containing complete reliability confirmation information.

2. The multi-sensor collaboration based photovoltaic weather monitoring method according to claim 1, characterized in that, Step S100 comprises: S110, cooperatively collecting meteorological data through a data collection device, setting different sampling frequencies for irradiation parameters, temperature monitoring values, and wind speed parameters, obtaining initial collection signals from multiple sensor nodes and performing digital processing, and generating an original data set; S120, correcting deviations of the original data set by using a calibration model, and generating a calibrated parameter set.

3. The multi-sensor collaboration based photovoltaic weather monitoring method according to claim 1, wherein, Step S200 comprises: S210, according to the irradiation parameters, the temperature monitoring values, and the wind speed parameters in the calibrated parameter set, performing preliminary linear combination through a weighted fusion algorithm, and generating an initial fusion numerical sequence; S220, a sliding window mechanism is used to perform time sequence smoothing processing on the initial fusion value sequence to generate a smoothed fusion data stream; S230, the smoothed fusion data stream is detected for deviation by a preset rule, and abnormal points are removed to generate a purified fusion data set; S240, state estimation correction is performed on the purified fusion data set, and a fusion data group is output as a reliable fusion result of the multi-source meteorological parameters.

4. The multi-sensor synergy based photovoltaic weather monitoring method according to claim 1, wherein, Step S300 includes: S310, for the characteristics of the fusion data group, the sensing layer is packaged by a preset encoding mechanism to generate a package unit; S320, according to the package unit, a queue is sorted in the transmission layer using a preset transmission protocol to mark the data priority; S330, according to the sorted data queue, a dynamic routing mechanism is applied in the transmission layer to plan a transmission path; S340, according to the transmission path, the sorted data queue is distributed to the application layer and recombined to generate a complete transmission data stream.

5. The multi-sensor synergy based photovoltaic weather monitoring method according to claim 1, wherein, Step S400 includes: S410, the transmission complete data stream is used to extract meteorological change key feature data, a preset meteorological analysis model is used to perform multi-dimensional analysis on the meteorological change key feature data to generate a meteorological change dynamic trend graph, and a meteorological change quantitative result set is obtained; S420, according to the meteorological change quantitative result set and the historical operation data of the photovoltaic power station, a preset power prediction model is used for multi-parameter fitting analysis to determine the potential output power prediction value interval of the photovoltaic power station; S430, real-time environmental variable data of the photovoltaic power station is obtained for the prediction value interval, and the prediction value interval is dynamically corrected by a multi-source data fusion mechanism to obtain corrected power prediction data; S440, if the corrected power prediction data is lower than a preset threshold range, an abnormal state identifier is automatically triggered by a pre-warning signal generation module, a pre-warning signal data set is generated, and a pre-warning signal priority is determined; S450, according to the pre-warning signal priority, a hierarchical response mechanism is used to classify and process the pre-warning signal data set to generate a hierarchical response instruction set and determine a prediction result set.

6. The multi-sensor synergy based photovoltaic weather monitoring method according to claim 1, wherein, In step S530, the corrected reliability improvement data set is obtained by the following formula: wherein, represents the modified reliability enhancement dataset, represents a preset weight of the deviation traceability result set, represents the current meteorological real-time monitoring data, represents a preset weight of the meteorological real-time monitoring data, represents the deviation data, represents a preset weight of the deviation data.

7. The multi-sensor synergy based photovoltaic weather monitoring method according to claim 6, wherein, In step S540, the following formula is used to define the judgment condition of the abnormal deviation part: wherein, represents whether the first sample belongs to the abnormal deviation part, represents the first corrected reliability value, represents the reference reliability value, represents the preset threshold value, is 1, indicating that the part is an abnormal deviation and needs to be verified again.​​ The final unbiased reliability verification result set is obtained by the following formula: wherein, represents the final unbiased reliability verification result set, represents the result recalculated for the abnormal deviation part, represents the mask matrix of the abnormal deviation part, represents point-by-point multiplication of elements, and the formula realizes targeted replacement for the abnormal deviation part. The mask matrix of the abnormal deviation part is obtained by the following formula: wherein, a mask matrix representing abnormal deviation parts, a deviation distribution of the modified data set, a preset threshold value, an indicator function, an absolute value of the deviation, when the absolute value of the deviation is greater than the preset threshold value , the corresponding position is 1, otherwise 0; this formula is used to locate abnormal deviation parts that need to be verified again.

8. The multi-sensor collaboration based photovoltaic weather monitoring method according to claim 7, characterized in that, In step S550, the following formula is used to calculate the operation and maintenance decision support report by weighted summation: wherein, represents the operation and maintenance decision support level, represents the candidate decision scheme, represents the number of types of reliability confirmation information in the report, represents the decision In the first compatibility score under the class information, represents the weight of the first class information.

9. A multi-sensor synergy based photovoltaic meteorological monitoring system for performing the multi-sensor synergy based photovoltaic meteorological monitoring method according to any one of claims 1 to 8, characterized in that, It includes: The calibrated parameter set acquisition module is used to acquire initial acquisition signals by collecting meteorological data through a data acquisition device and correcting deviations by processing the initial acquisition signals with a calibration model to obtain a calibrated parameter set, wherein the meteorological data includes irradiation parameters, temperature monitoring values, and wind speed parameters; The fusion data group determination module is used to perform data fusion operation according to the calibrated parameter set, fuse the irradiation parameters, the temperature monitoring values, and the wind speed parameters, and remove corresponding abnormal data points if the deviation exceeds a preset threshold during the fusion process to determine a fusion data group; The transmission completion data stream acquisition module is configured to adopt the fusion data set to execute a transmission protocol in a network architecture, send the fusion data set from a perception layer to an application layer through a transmission layer, and obtain a transmission completion data stream; The prediction result set acquisition module is configured to analyze a meteorological change mode through the transmission completion data stream, calculate a potential output power of the photovoltaic power station by using a prediction model, determine whether the potential output power of the photovoltaic power station is lower than a preset threshold, trigger a warning signal if the potential output power is lower than the preset threshold, and obtain a prediction result set; The meteorological monitoring report output module is configured to integrate a reliability improvement mechanism according to the prediction result set, perform secondary verification on the prediction result set to confirm data consistency, and output a final meteorological monitoring report to support photovoltaic power station operation and maintenance decision-making.

Images