An efficiency evaluation method for photovoltaic power generation and cold storage system based on big data analysis

Abstract

The present application provides an efficiency evaluation method for a photovoltaic power generation and cold storage system based on big data analysis, comprising: obtaining shadow distribution data on the surface of a photovoltaic module, extracting the change characteristics of the blocked area through an image processing method, and judging the dynamic change trend of the blocked area in combination with a time series analysis method; based on the dynamic change trend of the blocked area, using a regression model to predict the fluctuation characteristics of the power generation efficiency of the photovoltaic module, and establishing a mapping relationship between the power generation efficiency and the blocked area; applying a strategy adjustment scheme that meets the threshold conditions to the cold storage system, monitoring the change trend of the system efficiency in real time, and generating a cold storage system efficiency evaluation report in combination with a big data analysis method, wherein the evaluation report includes the correlation between the blocked area, power generation efficiency, cold storage and system efficiency.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an efficiency evaluation method for a photovoltaic power generation and cold storage system based on big data analysis. Background Art

[0002] Covering a cold storage system with photovoltaic panels can harness solar energy to generate electricity and power the system. The panels also provide shade, helping to reduce the system's energy consumption. However, in urban environments, due to the uneven heights of surrounding buildings, shadows cast by surrounding buildings can vary with the direction of the sun, causing localized shading of the photovoltaic panels above the cold storage system. This can lead to fluctuations in the panel's power generation efficiency. Because the area of ​​PV panels obscured by shadows changes dynamically over time, these fluctuations can affect the output power of the photovoltaic power generation system and, in turn, the operation of the coupled cold storage system. The cooling capacity of a photovoltaic-based cold storage system is closely related to the power generation efficiency of the PV panels. Therefore, the cold storage strategy of the cold storage system needs to be dynamically adjusted based on fluctuations in the panel's power generation efficiency. However, how to adjust the cold storage strategy of the cold storage system in real time when the obscured area changes dynamically, and how this adjustment affects the overall system's operating efficiency, remains unclear. Specifically, when a PV panel is partially shaded, its output power decreases, resulting in a reduction in the available power for the cold storage system. At this point, the cold storage system needs to decide whether to reduce the cooling capacity to match the real-time output of photovoltaic power generation, or to maintain the original cooling capacity and make up for the power gap by consuming stored energy. This decision needs to comprehensively consider multiple factors such as the forecast of photovoltaic power generation, the cooling load demand of the building, the energy storage capacity and efficiency of the cold storage system. Different decision-making strategies will have different effects on the operating efficiency of the overall system, but their internal mechanisms need further research. How to dynamically optimize and adjust the cold storage strategy of the cold storage system in the case of fluctuations in power generation efficiency caused by partial shading of photovoltaic panels, so as to maximize the overall operating efficiency of the cold storage system while ensuring the cooling needs of the building, is a technical problem that needs to be solved urgently. Summary of the Invention

[0003] The present invention provides an efficiency evaluation method for a photovoltaic power generation cold storage system based on big data analysis, which mainly includes:

[0004] Obtain the shadow distribution data on the surface of the photovoltaic module, extract the change characteristics of the shielding area through image processing methods, and judge the dynamic change trend of the shielding area by combining the time series analysis method; according to the dynamic change trend of the shielding area, use the regression model to predict the fluctuation characteristics of the power generation efficiency of the photovoltaic module, and establish a mapping relationship between the power generation efficiency and the shielding area; according to the fluctuation characteristics of the power generation efficiency, analyze the historical operation data and meteorological data of the photovoltaic power generation system, extract the change law of the cold storage demand of the cold storage system, and determine the adjustment content of the cold storage strategy. The adjustment content includes dynamic adjustment parameters, and the dynamic adjustment parameters include adjusting the cold storage time, cold storage power and cold storage temperature parameters; according to the dynamic adjustment parameters of the cold storage, combined with the performance parameters and operation constraints of the cold storage system, analyze the impact of the cold storage adjustment plan on the operation of the cold storage system through energy efficiency analysis methods. The influencing mechanism of efficiency includes the impact of the adjustment plan on the cold storage capacity, cold release capacity and energy consumption of the cold storage system, and the change characteristics of the system efficiency are obtained. The change characteristics include the system comprehensive energy efficiency, operating costs under peak and valley electricity prices, and carbon emission intensity; through the change characteristics of the system efficiency, it is judged whether the operating status of the cold storage system meets the preset threshold conditions. If the improvement of the system comprehensive energy efficiency exceeds the preset threshold, the reduction of the operating cost exceeds the preset threshold, and the reduction of the carbon emission intensity exceeds the preset threshold, it is judged that the threshold conditions are met and the current strategy adjustment plan is output; the strategy adjustment plan that meets the threshold conditions is applied to the cold storage system, and the changing trend of the system efficiency is monitored in real time. Combined with the big data analysis method, a cold storage system efficiency evaluation report is generated. The evaluation report includes the correlation between the shielding area, power generation efficiency, cold storage and system efficiency.

[0005] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0006] The present invention discloses an efficiency evaluation method for a photovoltaic power generation and cold storage system based on big data analysis. The method analyzes the dynamic changes in the shadow distribution on the surface of photovoltaic modules, establishes a mapping relationship between the blocked area and the power generation efficiency, and predicts the fluctuation characteristics of the power generation efficiency. In combination with historical operation and meteorological data, the changing pattern of the cold storage demand of the cold storage system is extracted, and the dynamic adjustment parameters of the cold storage strategy are determined. Through energy efficiency analysis, the impact of strategy adjustment on the system operation efficiency is evaluated, including comprehensive energy efficiency, operating cost and carbon emission intensity. When the preset threshold conditions are met, the optimization strategy is applied and the system efficiency is monitored in real time. The present invention realizes the coordinated optimization of photovoltaic power generation and cold storage systems, improves the overall energy utilization efficiency, reduces operating costs and carbon emissions, and provides a new technical solution for the integrated application of renewable energy and building energy conservation. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a flow chart of a method for evaluating the efficiency of a photovoltaic power generation and cold storage system based on big data analysis according to the present invention.

[0008] Figure 2 This is a schematic diagram of an efficiency evaluation method for a photovoltaic power generation and cold storage system based on big data analysis according to the present invention.

[0009] Figure 3 This is another schematic diagram of an efficiency evaluation method for a photovoltaic power generation and cold storage system based on big data analysis according to the present invention. DETAILED DESCRIPTION

[0010] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0011] like Figure 1-3 In this embodiment, a method for evaluating the efficiency of a photovoltaic power generation and cold storage system based on big data analysis may specifically include:

[0012] Step S101 , obtaining shadow distribution data on the surface of a photovoltaic module, extracting the change characteristics of the shielding area through image processing methods, and combining time series analysis methods to determine the dynamic change trend of the shielding area.

[0013] An image acquisition device is used to obtain a high-resolution image of the surface of a photovoltaic module, and a shadow area is divided according to a comparison result between the grayscale value of the pixel points of the high-resolution image and a preset reference grayscale value to obtain a first shadow area value; edge detection is performed on the shadow area to obtain an edge contour line, and the edge contour line is fitted with the least squares method to obtain an edge contour curve equation, and an autoregressive moving average model is established based on the edge contour curve equation to obtain a shadow area motion trajectory equation; temperature data is collected by a pre-deployed temperature sensor array to construct a temperature distribution matrix, and isotherms are extracted for the temperature distribution matrix. If the temperature value in the closed isotherm curve is lower than the temperature value of the surrounding area, it is determined that the area is shadowed, and a second shadow area value is obtained; the first shadow area value and the second shadow area value are fused using a weighted average method, and a discrete Fourier transform is performed on the fused shadow area value sequence, and frequency components with amplitudes greater than a normalized threshold are extracted based on the spectrum diagram of the discrete Fourier transform to obtain a shadow area change periodic sequence.

[0014] Exemplarily, a high-resolution image is acquired from the surface of a photovoltaic module and grayscaled. The image is then demarcated into a shadow region and a non-shadow region based on pixel grayscale values ​​compared to a preset baseline grayscale value. The number of pixels in the shadow region is then counted to obtain a first shadow area value. Edge detection is performed on the shadow region to extract edge contours. The edge contour curve equation is fitted using the least squares method, and the coefficient difference between two adjacent sampling moments is calculated. Based on the sequence of coefficient differences in the edge contour curve equation, an autoregressive moving average model is established to calculate the velocity vector of the shadow region and obtain the equation for the motion trajectory of the shadow region on the photovoltaic module surface. Temperature data is collected using a temperature sensor array pre-placed on the photovoltaic module surface, and a temperature distribution matrix is ​​constructed. A two-dimensional interpolation of the temperature distribution matrix is ​​performed to obtain a continuous temperature distribution function. Isotherms are extracted from the temperature distribution function. If the temperature within the closed isotherm curve is lower than the temperature of the surrounding area, shadow occlusion is determined within the closed curve, and a second shadow area value is calculated. The first and second shadow area values ​​are fused using a weighted average method to obtain a combined shadow area value sequence, which is then subjected to a discrete Fourier transform. Frequency components with amplitudes greater than a normalized threshold are extracted from the Fourier transformed spectrum. The corresponding periodic values ​​for each frequency component are calculated to generate a periodic sequence of shadow area variations. Grayscale images of the PV panel surface are captured using an industrial camera with a 2048×2048 pixel resolution under natural lighting conditions. The grayscale value of each pixel in the image ranges from 0 to 255, where 0 represents complete black and 255 represents complete white. In practical applications, the grayscale value of shadow areas is typically below 100, while the grayscale value of non-shadow areas is typically above 200. Therefore, a preset baseline grayscale value of 150 is selected to distinguish shadow from non-shadow areas. Shadow edge detection uses the Sobel operator, calculating the grayscale gradients of the image in the horizontal and vertical directions to obtain a set of edge contour points. The coordinate accuracy of each edge point can reach 0.1 pixel. For a PV panel with an area of ​​1 square meter, 300 to 500 edge contour points can typically be extracted. The distribution of these points well reflects the shape characteristics of the shadow area. In practical applications, shadows cast on the surface of photovoltaic panels primarily come from obstructions such as surrounding buildings and trees, the movement of which exhibits a certain regularity. For example, the shadow cast by a swaying tree branch, at a wind speed of 3 m / s, has a swing period of approximately 2 seconds, and the corresponding displacement velocity of the shadow edge contour varies between 0.1 and 0.3 m / s. The surface temperature distribution of photovoltaic panels is measured using an 8×8 array of thermocouple sensors with a 0.1-meter spacing and a measurement accuracy of 0.1°C. Under standard test conditions, the temperature in non-shaded areas is typically between 45°C and 50°C, while the temperature in shadowed areas drops by 5 to 8°C due to reduced light intensity. Bicubic spline interpolation of the temperature data yields a continuous temperature distribution function with a resolution of 0.01 m.In the periodic analysis of the shadow area numerical series, a 512-point fast Fourier transform (FFT) of data with a sampling frequency of 10 Hz and a duration of 60 seconds can discern a frequency component of 0.02 Hz. In practical applications, the primary period of shadow area variation typically ranges from 1 to 10 seconds, and the corresponding frequency component amplitude is significantly higher than that of other frequency components. By setting the normalized amplitude threshold to 0.1, meaningful periodic components can be effectively extracted. When calculating the combined shadow area, the characteristics of the grayscale and temperature methods are taken into account, with weights of 0.7 and 0.3, respectively. This is because grayscale images have a higher spatial resolution and can more accurately reflect shadow boundaries. While temperature data has a lower resolution, it is not affected by ambient light and can serve as an effective supplement.

[0015] Step S102 : Based on the dynamic change trend of the shielding area, a regression model is used to predict the fluctuation characteristics of the power generation efficiency of the photovoltaic module, and a mapping relationship between the power generation efficiency and the shielding area is established.

[0016] The fluctuation component in the power generation efficiency sequence is extracted through a sliding time window to obtain a first power generation efficiency curve; a nonlinear mapping function is constructed based on the first power generation efficiency curve using the support vector regression method to obtain a first prediction function; for the first prediction function, the temperature correction coefficient is calculated based on the temperature coefficient to obtain a second prediction function; the second prediction function is used to process the real-time shading area data to obtain a second power generation efficiency curve, and the high-frequency component and low-frequency component in the second power generation efficiency curve are extracted through wavelet transform to obtain a third power generation efficiency curve; the third power generation efficiency curve is Fourier transformed to extract the spectral feature vector, and the environmental temperature and humidity data are integrated using the Bayesian regression method to predict the future power generation efficiency change trend curve.

[0017] For example, voltage and current data are collected from string photovoltaic modules. The generated power is calculated based on this data, and a first power generation efficiency sequence is obtained based on a standard light intensity of 1000 watts per square meter. The fluctuation component of the power generation efficiency sequence is extracted using a 60-second sliding time window to obtain a first power generation efficiency fluctuation curve. A nonlinear mapping function is constructed using the support vector regression method with a Gaussian kernel function for the shading area data sequence and the first power generation efficiency fluctuation curve. The corresponding relationship between the shading area change and the power generation efficiency fluctuation amplitude is extracted to obtain a first prediction function. The deviation between the mean temperature and the standard temperature of 25 degrees Celsius is extracted from the surface temperature distribution data of the photovoltaic modules. A temperature correction coefficient is calculated based on a temperature coefficient of -0.4% / degree Celsius. The first prediction function is then corrected to obtain a second prediction function. The second prediction function is then processed using the real-time shading area data to obtain a second power generation efficiency fluctuation curve. The high-frequency and low-frequency components of the fluctuation curve are extracted using a wavelet transform. The efficiency attenuation coefficient is calculated based on the ratio of the PV module's nameplate rated photoelectric conversion efficiency to the measured photoelectric conversion efficiency. This is combined with the high-frequency and low-frequency components of the second power generation efficiency fluctuation curve to generate a third power generation efficiency fluctuation curve. This third power generation efficiency fluctuation curve is Fourier transformed to extract spectral feature vectors. This is then integrated with ambient temperature and humidity data using a Bayesian regression method to predict future power generation efficiency fluctuation trends. The standard deviation of the power generation efficiency fluctuation trend curve is calculated. If the standard deviation exceeds a preset fluctuation threshold of 0.05, the power generation efficiency fluctuation is considered abnormal. The power generation efficiency of PV modules is closely related to environmental conditions, with shading on the module surface having a significant impact on power generation efficiency. In practice, a typical 60-cell module under standard lighting conditions has an output voltage of 36 volts and an output current of 9 amperes, corresponding to a power generation of 324 watts. When a module is partially shaded, the output power of the shaded cells drops sharply, causing fluctuations in the power generation efficiency of the entire string. Variations in the shaded area of ​​the module surface can result in different power generation efficiency fluctuation patterns. Taking dynamic shading caused by tree branches as an example, when the shaded area increases from 5% to 10%, power generation efficiency typically decreases by 8% to 12%. Processing power generation efficiency data using a 60-second sliding time window can effectively capture this fluctuation. Temperature also has a significant impact on the power generation efficiency of photovoltaic modules. For every 1°C increase in module surface temperature, power generation efficiency decreases by approximately 0.4%. Measured data shows that module conversion efficiency is 18% at 25°C, but drops to 16.6% when the temperature rises to 45°C. By introducing a temperature correction factor to calibrate the prediction model, the accuracy of power generation efficiency predictions is improved. The power generation efficiency fluctuations of photovoltaic modules exhibit multi-scale characteristics. Wavelet transforms can decompose these fluctuations into different frequency components: high-frequency components reflect instantaneous disturbances, such as short-term changes in sunlight caused by cloud movement; low-frequency components reflect long-term trends, such as efficiency drift caused by temperature changes.Measured data shows that under normal operating conditions, the amplitude of high-frequency fluctuations does not exceed 3%, and the amplitude of low-frequency fluctuations does not exceed 5%. Photovoltaic conversion efficiency gradually decreases with module age. The conversion efficiency of newly installed modules is 19.5%, which drops to 19% after one year and 18% after five years. The efficiency decay coefficient reflects the degree of module aging and is closely related to the fluctuation characteristics of power generation efficiency. The more severe the decay, the greater the efficiency fluctuation for the same change in shaded area. The spectral characteristics of power generation efficiency fluctuations contain rich diagnostic information. A Fourier transform of the fluctuation curve reveals abnormal spectral components in the 0.1 to 1 Hz frequency band, often indicating module shade issues. Actual operating data shows that under normal operating conditions, the standard deviation of power generation efficiency fluctuations is typically less than 0.05. Exceeding this threshold requires further investigation of module shade. Under standard testing conditions of an ambient temperature of 20°C and a relative humidity of 60%, the power generation efficiency fluctuations of photovoltaic modules exhibit relatively stable characteristics. Using a Bayesian regression method that comprehensively considers the impact of temperature and humidity changes on power generation efficiency, the average deviation between the predicted results and the measured data is kept within 2%.

[0018] According to the dynamic change trend of the blocked area, a regression model is established with the blocked area as the independent variable and the power generation efficiency as the dependent variable. The fluctuation characteristics of the power generation efficiency of photovoltaic modules with the change of the blocked area are predicted, and the quantitative mapping relationship between the power generation efficiency and the blocked area is fitted, including the change range of the blocked area, the fluctuation amplitude of the power generation efficiency and the peak efficiency point, so as to predict the power generation efficiency change curve under different blocking scenarios.

[0019] Light intensity data is collected according to the light intensity sensor array, a light intensity distribution matrix is ​​constructed for the light intensity data, and a threshold segmentation method is used to process the light intensity distribution matrix to obtain a binary image of the occluded area; the pixel ratio of the occluded area in the binary image of the occluded area is counted to obtain a first numerical sequence of occluded area, Fourier transform is performed on the first numerical sequence of occluded area to extract spectral features, and trigonometric function superposition fitting is used to obtain a dynamic change function of the occluded area; voltage and current sampling data output by the photovoltaic component are obtained, the power generation value is calculated according to the voltage and current sampling data, and a fixed time window is used to perform sliding average processing on the power generation value to obtain a first power generation efficiency curve; the sampling value of the dynamic change function of the occluded area is used as an independent variable, and the corresponding time value of the first power generation efficiency curve is used as a dependent variable, and a first prediction function is obtained by training using a support vector regression method.

[0020] Exemplarily, light intensity data is collected using a pre-placed array of light intensity sensors on the surface of a photovoltaic module. A light intensity distribution matrix is ​​constructed based on the uniform distribution of the light intensity sensor array on a horizontal plane. A threshold segmentation is applied to the light intensity distribution matrix to generate a binary image of the obstructed area. The percentage of pixels in the binary image that are obstructed is calculated to obtain a first numerical sequence of obstructed area values. A fast Fourier transform is performed on the first numerical sequence of obstructed area values ​​to extract the first three frequency components with the largest amplitudes from the spectral features. A trigonometric function is then applied to obtain a dynamic variation function of the obstructed area. Power generation is calculated based on the sampled voltage and current data output by the photovoltaic module. A sliding average of the power generation values ​​is performed over a fixed time window to obtain a smoothed first power generation efficiency curve. The sampled values ​​of the dynamic variation function of the obstructed area are used as independent variables, and the corresponding time values ​​of the first power generation efficiency curve are used as dependent variables. A regression function is trained using the support vector regression method to obtain a first regression prediction function. The first regression prediction function is numerically differentiated to extract the boundary points between the increasing and decreasing ranges of the function value. The maximum and minimum power generation efficiency values ​​are determined to obtain the boundary values ​​of the power generation efficiency fluctuation range. The shading conditions are divided according to the boundary values ​​of the power generation efficiency fluctuation range. Within each operating condition, cubic spline interpolation is used to supplement the power generation efficiency values, resulting in a second power generation efficiency curve. Using this second power generation efficiency curve as training data, a gradient boosting tree algorithm is used to construct a second regression prediction function. The corresponding power generation efficiency output value is calculated based on the real-time shading area input value. The light intensity sensor array on the surface of the photovoltaic module is typically arranged in an 8×8 uniform pattern with a sensor spacing of 125 mm, covering the entire module surface. Each sensor collects real-time light intensity values. Normal light intensity ranges from 800 to 1000 watts per square meter. When shading occurs, the light intensity in the shaded area drops below 200 watts per square meter. Image segmentation is performed by setting a threshold of 400 watts per square meter, resulting in a binary image reflecting the distribution of the shading area. The dynamic changes in the shading area exhibit a clear periodicity. Fourier analysis of obstruction area data with a sampling frequency of 10 Hz and a sampling duration of 300 seconds revealed that the main frequency components were concentrated around 0.2, 0.4, and 0.8 Hz, corresponding to obstruction from various sources, such as swaying tree branches and cloud movement. The obstruction area variation function obtained by trigonometric function superposition fitting had a fitting error of less than 3% compared with the measured data. The power generation efficiency of photovoltaic modules is highly sensitive to obstruction. Under standard testing conditions, a 60-cell module with a rated power of 330 watts corresponds to a power generation efficiency of 19.5%. Smoothing the power generation data using a 30-second sliding time window effectively eliminates the impact of transient fluctuations. Measured data show that when the obstruction area increases from 0 to 5%, the power generation efficiency decreases by approximately 15%. The support vector regression method uses a radial basis kernel function to construct a nonlinear mapping relationship. 1000 sets of data corresponding to obstruction area and power generation efficiency were selected as training samples, and the cross-validation root mean square error was 0.8%.The derivative of the regression function reflects the rate of change of power generation efficiency with obstruction area, with an inflection point occurring at 3% obstruction, corresponding to the minimum power generation efficiency. The fluctuation range of power generation efficiency varies with obstruction conditions. Statistical analysis shows that under mild obstruction conditions (less than 5% obstruction), the power generation efficiency fluctuates between 17% and 19%; under moderate obstruction conditions (5% to 10% obstruction), the fluctuation range increases to 15% to 18%; and under severe obstruction conditions (greater than 10% obstruction), the fluctuation range further increases to 12% to 17%. The gradient boosting tree algorithm was trained using 500 decision trees, each with a maximum depth of 4. Input features included obstruction area, obstruction change rate, and obstruction duration, and the output was the predicted power generation efficiency value. Prediction accuracy exceeded 95% under all obstruction conditions, and the confidence interval width of the prediction results increased with increasing obstruction area, reflecting a positive correlation between prediction uncertainty and obstruction severity.

[0021] Step S103: Analyze the historical operating data and meteorological data of the photovoltaic power generation system based on the fluctuation characteristics of power generation efficiency, extract the changing pattern of the cold storage demand of the cold storage system, and determine the adjustment content of the cold storage strategy. The adjustment content includes dynamic adjustment parameters, and the dynamic adjustment parameters include adjustment of the cold storage time, cold storage power and cold storage temperature parameters.

[0022] Based on the photovoltaic power generation power sampling data, the fast Fourier transform method is used to process the sampling data to obtain the periodic characteristics and amplitude characteristics of the power generation power fluctuation; the periodic characteristics and amplitude characteristics are segmented, and the feature extraction method is used to obtain the meteorological feature vectors of light intensity, ambient temperature, and relative humidity from the segmented data to obtain a feature sequence; based on the feature sequence, the support vector machine clustering method is used to process the feature sequence to obtain a cold storage load prediction curve; for the cold storage load prediction curve, a linear programming solver is used to calculate the start and end points of the cold storage time period to obtain a cold storage duration curve; the cold storage duration curve is segmentedly integrated to calculate the cold storage power demand in each cold storage time period.

[0023] Exemplarily, a time series is constructed based on sampled photovoltaic power data. The periodic and amplitude characteristics of power fluctuations are extracted using a fast Fourier transform (FFT) method. Combined with temperature curve data, the power fluctuation trend is smoothed using a Kalman filter to obtain a first power fluctuation curve and fluctuation period. The first power fluctuation curve is segmented according to the fluctuation period, and meteorological feature vectors representing three dimensions, namely, light intensity, ambient temperature, and relative humidity, are extracted for each time period to obtain a first feature sequence. A support vector machine is used to cluster the first feature sequence. The mapping relationship between meteorological feature combinations and cooling load is extracted from the clustering results to calculate a first cooling load prediction curve. Based on the first cooling load prediction curve, a set of enthalpy balance equations for the cooling device is constructed. A linear programming solver is used to calculate the start and end points of the cooling time period to obtain a first cooling duration curve. The first cooling duration curve is segmented and integrated to calculate the cooling power demand for each cooling time period to obtain a first cooling power curve. The kernel density estimation method was used to process the inlet and outlet water temperature data of the cold storage device. The peak and trough points of the kernel density curve were determined, and the upper and lower limits of the cold storage temperature were obtained. Based on the first cold storage load prediction curve, the first cold storage duration curve, and the first cold storage power curve, the weighted average method was used to update the cold storage control parameter values. The fluctuation of photovoltaic power generation has obvious time series characteristics. At a sampling frequency of 1 Hz, the collected power data exhibits multi-scale fluctuation characteristics: short-term fluctuations have a period between 60 and 300 seconds, mainly affected by cloud movement; medium-term fluctuations have a period between 1800 and 3600 seconds, mainly affected by ambient temperature changes. After Kalman filtering, the noise level of the power fluctuation curve was reduced by 90%. Meteorological characteristics show a significant correlation with cold storage load. Under typical summer operating conditions, when the ambient temperature rises from 25°C to 35°C, the cold storage load increases by approximately 40%. Every 10% increase in relative humidity increases the cold storage load by approximately 5%. The growth rate of the cold storage load increases significantly when the light intensity exceeds 800 watts / square meter. The key to determining the cold storage time lies in enthalpy balance calculations. The inlet water temperature of a cold water energy storage device is typically controlled between 5 and 7 degrees Celsius, and the outlet water temperature is controlled between 12 and 15 degrees Celsius. For a 1000 kilowatt cold storage device, a complete cold storage cycle requires between 4 and 6 hours. Through linear programming optimization, the cold storage process can be divided into 3 to 5 time periods. Cold storage power demand varies significantly with the seasons. Under typical summer operating conditions, the demand fluctuates between 800 and 1000 kilowatts during the daytime, dropping to 400 to 600 kilowatts during the nighttime. A piecewise integral calculation calculates the cumulative cooling capacity within each cold storage time period, thereby determining the average cold storage power for that period. Controlling the cold storage temperature significantly impacts system performance. Kernel density estimation results show that the optimal control range for the inlet water temperature is 6.5 ± 0.5 degrees Celsius, and the optimal control range for the outlet water temperature is 13.5 ± 0.5 degrees Celsius.For every 0.1°C improvement in temperature control accuracy, cold storage efficiency increases by approximately 1%. Dynamic adjustment of cold storage control parameters requires comprehensive consideration of multiple factors. For a 500-kW cold storage system, for example, the cold storage duration parameter values ​​under summer conditions are 5 hours, the cold storage power parameter value is 850 kW, and the cold storage temperature parameter value is 7°C. When the PV power fluctuation amplitude exceeds 20%, the cold storage duration is extended to 6 hours, the cold storage power value is reduced to 700 kW, and the cold storage temperature is increased to 8°C. Parameter updates are performed using a weighted average method, with the cold storage load forecast value weighted at 0.5, the cold storage duration weighted at 0.3, and the cold storage power weighted at 0.2. By dynamically adjusting the weight coefficients, timely system response is ensured while avoiding frequent parameter fluctuations. Actual operational data shows that this method improves the operating efficiency of the cold storage system by over 15%.

[0024] The changing patterns of cooling demand of the cold storage system over time and weather in historical operation and meteorological data are explored to identify key parameters affecting cooling storage demand, extract intraday fluctuations and seasonal trends of load demand, and determine the optimization space of cooling storage strategy based on the changes in cooling demand. The action space of cooling storage operation parameters is adjusted, including the adjustable time period range, upper and lower power limits, and temperature setting allowable range, to form the boundary of dynamic optimization of cooling storage strategy parameters.

[0025] Based on the cooling load sequence and meteorological parameter sequence, a long short-term memory network is used to extract the intraday fluctuation pattern and seasonal variation characteristics of the cooling load to obtain a first load fluctuation curve; wavelet transform processing is performed on the first load fluctuation curve to obtain a second load fluctuation curve by extracting high-frequency fluctuation components and low-frequency variation trends; a decision tree regressor is used to process the second load fluctuation curve and the meteorological parameter sequence, and the influence of temperature, humidity, and light intensity on load changes is calculated to obtain a load influence parameter sequence; the cold storage device operation data is classified according to the load influence parameter sequence, and the boundary points of the cold storage period are identified by the hierarchical clustering method of Euclidean distance to obtain the cold storage operation segmentation result; Fourier transform is performed on the inlet and outlet water temperature data sequence in each cold storage operation segment to extract the temperature fluctuation range corresponding to the main frequency component to obtain the upper and lower limits of the cold storage temperature; the thermal enthalpy difference is calculated based on the upper and lower limits of the cold storage temperature, and combined with the rated capacity of the cold storage device to obtain the cold storage power adjustment range.

[0026] For example, based on the cooling load sequence and meteorological parameter sequence in historical operating data, a long-short-term memory network is used to extract the intraday fluctuation patterns and seasonal variation characteristics of the cooling load. The load fluctuation mean and variance are calculated using an hourly sliding time window to obtain a first load fluctuation curve. A wavelet transform is applied to the first load fluctuation curve to extract high-frequency fluctuation components and low-frequency variation trends, resulting in a second load fluctuation curve. Based on the second load fluctuation curve and meteorological parameter sequence, a decision tree regressor is constructed to extract the impact of temperature, humidity, and light intensity on load variation. The weight coefficients of each parameter are calculated to obtain a load influence parameter sequence. Based on the load influence parameter sequence, the cold storage device operating data is classified, and a hierarchical clustering method using Euclidean distance is used to identify the boundaries of the cold storage period, resulting in a cold storage operation segmentation result. A Fourier transform is performed on the inlet and outlet water temperature data series within each cold storage operation segment to extract the temperature fluctuation range corresponding to the main frequency component, resulting in the upper and lower limits of the cold storage temperature. The enthalpy difference is calculated based on the upper and lower limits of the cold storage temperature, and combined with the rated capacity of the cold storage device, the cold storage power adjustment range is obtained. The kernel density estimation method was used to process cold storage data from cold storage devices. A fixed bandwidth parameter was used to extract the cold storage density distribution curve and determine the cold storage capacity boundary. A cold storage strategy parameter constraint matrix was constructed based on the cold storage operation segmentation results, the upper and lower limits of the cold storage temperature, the cold storage power adjustment range, and the cold storage capacity boundary. Cooling load typically exhibits typical intraday fluctuations and seasonal variations. Under summer operating conditions, hourly sampled cooling load data showed that load peaks occurred between 2:00 PM and 4:00 PM, and load valleys occurred between 4:00 AM and 6:00 AM, with a peak-to-valley ratio of 2.5. The mean of load fluctuations processed using a 3-hour sliding window ranged from 500 kW to 800 kW, with a variance between 50 kW and 100 kW. Wavelet transforms can effectively separate high-frequency fluctuations from low-frequency trends in the load curve. The high-frequency component reflects short-term load fluctuations, with a period of one to four hours and an amplitude that accounts for 15% to 25% of the total load. Low-frequency components reflect seasonal variations. From spring to summer, the average daily load increases by 40%, while from summer to autumn, it decreases by 35%. Meteorological parameters vary in their impact on cooling load. Decision tree regression analysis shows that for every 1°C increase in outdoor temperature, the cooling load increases by approximately 8%, and for every 10% increase in relative humidity, the cooling load increases by approximately 3%. The cooling load growth rate increases significantly when sunlight intensity exceeds 600 watts / square meter. The weighting ratio of temperature, humidity, and light intensity is approximately 5:2:3. Cooling storage operation periods are categorized based on load characteristics and environmental conditions. Using a hierarchical clustering method using Euclidean distance, the 24-hour day is divided into four operating periods: the late night cooling storage period from 11:00 PM to 5:00 AM, the morning cooling period from 6:00 AM to 11:00 AM, the midday peak load period from 12:00 PM to 5:00 PM, and the night transition period from 6:00 PM to 10:00 PM.The control range of the cold storage temperature varies with the operating time. The inlet water temperature is maintained at 5-7°C during the late-night cold storage period and is allowed to rise to 8-10°C during the cooling period. The outlet water temperature is controlled at 12-14°C during the late-night cold storage period and can rise to 15-17°C during the cooling period. Analysis of the main frequency components shows that the main period of temperature fluctuation is 6 hours. The adjustment range of the cold storage power is related to the device capacity. For a 1000 kW cold storage device with an inlet and outlet water temperature difference of 8°C under standard operating conditions, the lower limit of the cold storage power is 400 kW and the upper limit is 800 kW. Enthalpy difference calculations indicate that approximately 0.15 cubic meters of chilled water are required for each kilowatt-hour of cold storage. Kernel density estimation was used to analyze the cold storage data, selecting a bandwidth parameter of 50 kilowatt-hours. The resulting density distribution curve exhibits a bimodal characteristic. The main peak corresponds to the daily cooling capacity, which is located at 75% of the rated capacity; the secondary peak corresponds to the cooling capacity during the high-load period, which is located at 90% of the rated capacity. This distribution feature provides an important basis for determining the boundary of the cooling storage capacity.

[0027] In step S104, based on the dynamic adjustment parameters of cold storage, combined with the performance parameters and operating constraints of the cold storage system, the energy efficiency analysis method is used to analyze the impact mechanism of the cold storage adjustment scheme on the operating efficiency of the cold storage system. The impact mechanism includes the impact of the adjustment scheme on the cold storage capacity, cold release capacity and energy consumption of the cold storage system, and the change characteristics of the system efficiency are obtained. The change characteristics include the comprehensive energy efficiency of the system, the operating cost under peak and valley electricity prices, and the carbon emission intensity.

[0028] Based on the cooling capacity parameters, cooling capacity parameters and power consumption parameters, an adaptive weighted regression method is used for coupling calculation to obtain a cooling coefficient curve; a piecewise linear fitting is performed on the cooling coefficient curve, the slope and intercept of each segment are extracted, and a cooling coefficient prediction function is constructed to obtain an energy efficiency prediction value; a random forest algorithm is used to process the cooling coefficient curve and peak and valley electricity price data to obtain a power consumption cost value; based on the power consumption cost value and the grid carbon emission factor data, the carbon emissions per unit time are calculated in combination with the unit power consumption curve to form a carbon emission curve.

[0029] Exemplarily, based on the operating parameter data series of the cold storage device, an adaptive weighted regression method is used to couple the cold storage capacity, cold discharge capacity, and power consumption, constructing a thermodynamic process balance equation to obtain a first cooling coefficient curve. A piecewise linear fit is performed on the first cooling coefficient curve, extracting the slope and intercept of each segment to construct a cooling coefficient prediction function, resulting in a first energy efficiency prediction value. Real-time peak and valley electricity prices and time-of-use electricity price period data are sampled, and an operating cost prediction function is constructed using a random forest algorithm. The first power consumption cost is calculated by inputting the cold storage duration, cold storage power, and cold storage temperature parameters. Based on the first power consumption cost and the grid carbon emission factor, combined with the unit power consumption curve, the carbon emissions per unit time are calculated to obtain a first carbon emission curve. Using the cold storage device's inlet and outlet water temperature and flow parameters, combined with the water pump power curve, a thermal enthalpy calculation function for the cold storage process is constructed to calculate the ratio of cold storage capacity to cold discharge capacity per unit time. Based on this ratio of cold storage capacity to cold discharge capacity per unit time, a cooling efficiency calculation function is constructed to obtain a second energy efficiency prediction value. The first and second energy efficiency prediction values, the first electricity cost value, and the first carbon emission curve were normalized, and the indicator weight coefficients were calculated using the analytic hierarchy process. The normalized indicator values ​​and weight coefficients were then weighted and summed to obtain the overall energy efficiency evaluation value. The cooling coefficient of a cold storage device represents the ratio of cooling capacity to power consumption. Under standard operating conditions, with a cooling capacity of 1,000 kWh, power consumption of 200 kW, and cooling capacity of 800 kWh, the device's cooling coefficient is 4. Using adaptive weighted regression to process operational data, it was found that the cooling coefficient exhibits a segmented variation. Within the cold storage temperature range of 5 to 7 degrees Celsius, the cooling coefficient decreases with increasing temperature, with a slope of -0.5 per degree Celsius. The time-of-use electricity price structure significantly impacts operating costs. The peak-to-valley price ratio is typically 3:1, with peak-period electricity prices at 1.2 yuan per kilowatt-hour and off-peak prices at 0.4 yuan per kilowatt-hour. A random forest algorithm predicts that, at the same cold storage temperature, shifting the cold storage period from peak to off-peak hours can reduce operating costs by 65%. The grid's carbon emission factor varies by time of year, with a carbon emission factor of 0.8 kg per kilowatt-hour during nighttime off-peak hours and 0.6 kg per kilowatt-hour during daytime peak hours. For a cold storage device with a rated power of 300 kW, carbon emissions are 180 kg per hour during peak hours and 240 kg per hour during off-peak hours. The change in enthalpy during the cold storage process is closely related to water temperature. When the inlet water temperature is 5°C and the outlet water temperature is 12°C, the enthalpy difference per unit mass of water is 29.3 kilojoules per kilogram. At a circulating water flow rate of 50 cubic meters per hour, the cold storage rate is 420 kilowatts and the cooling rate is 380 kilowatts. The pump power curve shows that for every 10 cubic meters per hour increase in flow rate, power consumption increases by 5 kilowatts. The analytic hierarchy process assigns weights to different indicators, with the cooling coefficient weighted as 0.4, the operating cost weighted as 0.35, and the carbon emission weighted as 0.25.When the cooling coefficient increases from 3.5 to 4.0, operating costs decrease by 20%, and carbon emissions increase by 10%, the comprehensive energy efficiency evaluation value increases by 15%. This multi-index evaluation system reflects the comprehensive performance of the cold storage device in terms of energy conservation, emission reduction, and economy. Through dynamic adjustment of operating parameters, the cold storage device exhibits different performance characteristics. Under summer operating conditions, when the cold storage temperature drops from 7 degrees Celsius to 5 degrees Celsius, the cooling coefficient decreases by 0.8, but the cold storage capacity increases by 25%. In the transition season, the cold storage temperature is maintained at 6 degrees Celsius, and the cold storage time is adjusted from 6 hours to 8 hours, and the comprehensive energy efficiency evaluation value increases by 12%.

[0030] In step S105, the operating status of the cold storage system is judged to determine whether it meets the preset threshold conditions based on the changing characteristics of the system efficiency. If the improvement in the system's comprehensive energy efficiency exceeds the preset threshold, the reduction in operating costs exceeds the preset threshold, and the reduction in carbon emission intensity exceeds the preset threshold, it is judged that the threshold conditions are met and the current strategy adjustment plan is output.

[0031] The indicator change rate within each sampling period is calculated based on the comprehensive energy efficiency value, operating cost value and carbon emission intensity value to obtain an indicator change rate sequence; the indicator change rate sequence is segmented using a sliding time window, and the change amplitude of adjacent sampling moments is calculated for the data in each time window to obtain an efficiency change sequence; the gradient descent method is applied to the efficiency change sequence, and the mean square error is used as the optimization objective function to calculate the time series change trend of the efficiency improvement amplitude, cost reduction amplitude and emission reduction amplitude; a three-dimensional feature vector is constructed based on the time series change trend, and the distance value from the feature vector to the preset threshold plane is calculated through the radial basis kernel function of the support vector machine to obtain a time interval sequence that meets the threshold condition.

[0032] For example, based on the comprehensive energy efficiency, operating cost, and carbon emission intensity values ​​in the real-time operating data series, the rate of change of the indicators within each sampling period is calculated to obtain a first indicator change rate sequence. The first indicator change rate sequence is segmented using a sliding time window with a fixed length of 24 hours. For the data within each time window, the magnitude of change between two adjacent sampling moments is calculated to obtain a first efficiency change sequence. A gradient descent method is applied to the first efficiency change sequence, using the mean square error as the optimization objective function, to calculate the time-series trend of efficiency improvement, cost reduction, and emission reduction. A three-dimensional feature vector is constructed based on the time-series trend, and the radial basis kernel function of a support vector machine is used to calculate the distance between the feature vector and a preset threshold plane. The forward projection distance of the preset threshold plane is filtered to obtain a time interval sequence that meets the threshold condition. Within the time interval that meets the threshold condition, sampled values ​​of the cooling storage duration parameter, cooling storage power parameter, and cooling storage temperature parameter are extracted. Outlier detection is performed on the extracted parameter sample values, and abnormal data points outside the preset range are removed to obtain the parameter optimization sequence. Kernel density estimation was used to fit the probability distribution of the parameter optimization sequence, extracting the parameter combination corresponding to the maximum probability density. The evaluation of cold storage system operating indicators involves multiple dimensions. With a 5-minute sampling frequency, the comprehensive energy efficiency value fluctuated between 3.5 and 4.5, the operating cost varied between 0.8 and 1.2 yuan per kilowatt-hour, and the carbon emission intensity ranged from 0.6 to 0.9 kilograms per kilowatt-hour. By calculating the difference between adjacent sampling points, the energy efficiency improvement ranged from 0.02 to 0.05 per sampling period. A 24-hour sliding window reflects the diurnal characteristics of indicator changes. The operating cost change rate is positive during daytime and negative during nighttime, reflecting the impact of peak and off-peak electricity prices. Carbon emission intensity decreases significantly during photovoltaic power generation, with a change rate of -0.05 kilograms per kilowatt-hour per hour. The comprehensive energy efficiency value increases most rapidly during the cooler early morning hours, with a change rate of 0.08 per hour. The distance between the three-dimensional feature vector and the preset threshold plane reflects the degree of operational optimization. The threshold plane is determined by three critical values: an energy efficiency improvement of 0.3, a cost reduction of 20%, and a carbon emission reduction of 15%. When the forward projection distance of the eigenvector is greater than 0.1, it indicates that the operating parameter adjustment direction is reasonable. Actual operating data shows that the time period that meets the threshold conditions is mainly distributed between 11 PM and 5 AM the next day. Outliers in the cold storage parameters are defined based on physical constraints. The cold storage duration ranges from 2 to 8 hours, the cold storage power ranges from 300 to 900 kW, and the cold storage temperature ranges from 4 to 8 degrees Celsius. Data points outside this range are marked as outliers. Statistics show that outliers account for 3% of the total sample and mainly occur during equipment startup and shutdown. The probability distribution of the parameter optimization sequence exhibits multimodal characteristics. The kernel density estimation uses a Gaussian kernel function with a bandwidth of 0.5. The main peak of the distribution curve corresponds to the parameter combination of 6 hours of cold storage duration, 600 kW of cold storage power, and 6 degrees Celsius of cold storage temperature.The parameter combination corresponding to the sub-peak reflects the seasonal differences in operating conditions. The summer operating conditions correspond to a cooling storage time of 4 hours, a cooling storage power of 800 kilowatts, and a cooling storage temperature of 5 degrees Celsius. The optimal parameter combination shows good adaptability in different operating scenarios. Under standard operating conditions, this parameter combination improves the overall energy efficiency by 0.4, reduces operating costs by 25%, and reduces carbon emissions by 18%. Under partial load conditions, similar optimization effects were maintained by adjusting the cooling storage time to 5 hours. In the transition season, the cooling storage temperature was appropriately increased to 7 degrees Celsius, and the improvement trend of various indicators was still maintained.

[0033] In step S106, the strategy adjustment scheme that meets the threshold conditions is applied to the cold storage system, and the changing trend of the system efficiency is monitored in real time. A cold storage system efficiency evaluation report is generated by combining the big data analysis method. The evaluation report includes the correlation between the shielding area, power generation efficiency, cold storage and system efficiency.

[0034] A time series predictor is constructed based on the monitored data using a long short-term memory network. The time series predictor extracts time series features from each indicator to obtain an indicator sequence. A sliding correlation window is constructed for the indicator sequence. The sliding correlation window calculates the Pearson correlation coefficient between indicators to obtain a correlation coefficient matrix. An indicator mapping function is constructed based on the correlation coefficient matrix using a random forest regression algorithm. The indicator mapping function calculates the one-way influence intensity between each indicator to obtain an influence intensity matrix. An indicator transfer network is constructed based on the influence intensity matrix using a eigenvector sequence. The indicator transfer network calculates the in-degree value and out-degree value of each node to obtain an indicator influence intensity ranking. A hierarchical indicator association diagram is generated based on the indicator influence intensity ranking, and the transmission path from the blocked area to the comprehensive efficiency is extracted to generate a performance evaluation report containing indicator association relationships, influence levels, and response characteristics.

[0035] For example, based on online monitoring data, shaded area, power generation efficiency, cold storage capacity, and overall efficiency values ​​are collected, with a sampling period of 5 minutes. A long-short-term memory network is used to construct a time series predictor, extracting the time series characteristics of each indicator to obtain a first indicator sequence. Time series correlation analysis is performed on the first indicator sequence, and a sliding correlation window is constructed to calculate the Pearson correlation coefficient between indicators, resulting in a first correlation coefficient matrix. Significantly correlated items are extracted from the first correlation coefficient matrix. An indicator mapping function is constructed using the random forest regression algorithm, and the one-way influence strength between indicators is calculated to obtain a first influence strength matrix. Singular value decomposition is performed on the first influence strength matrix to extract the main eigenvectors, and the eigenvalue contribution rate is calculated to obtain a first eigenvector sequence. An indicator transfer network is constructed using the first eigenvector sequence, and the in-degree and out-degree values ​​of each node in the network are calculated to obtain a ranking of indicator influence strengths. Based on the ranking of indicator influence strengths, a hierarchical indicator association diagram is generated, and the association strength values ​​are annotated to obtain a first association structure diagram. Path analysis is performed on the first association structure diagram to extract the key transfer paths from shaded area to overall efficiency, generating a transfer chain diagram. A transfer chain diagram was used to quantitatively evaluate the current operating strategy, generating a performance evaluation report that included indicator relationships, impact levels, and response characteristics. The operating indicators of the photovoltaic cold storage system exhibited significant temporal correlation. Using a 5-minute sampling period, as the shaded area increased from 5% to 10%, the power generation efficiency decreased by 15%, resulting in a 12% decrease in cold storage power, and ultimately an 8% decrease in overall efficiency. Long-short-term memory network prediction results showed that changes in shaded area preceded changes in power generation efficiency by approximately 10 minutes, and changes in power generation efficiency preceded changes in cold storage by approximately 15 minutes. When the sliding correlation window was set to 1 hour, the Pearson correlation coefficients between the various indicators showed significant characteristics. The correlation coefficient between shaded area and power generation efficiency was -0.85, indicating a strong negative correlation; the correlation coefficient between power generation efficiency and cold storage was 0.78, indicating a strong positive correlation; and the correlation coefficient between cold storage and overall efficiency was 0.82, also showing a strong positive correlation. Random forest regression analysis revealed quantitative influence relationships between indicators: for every 1 percentage point increase in shaded area, power generation efficiency decreased by 1.5 percentage points; for every 1 percentage point decrease in power generation efficiency, cold storage decreased by 0.8 percentage points; and for every 1 percentage point decrease in cold storage, overall efficiency decreased by 0.6 percentage points. This chain-like transmission characteristic was further clarified after singular value decomposition. Eigenvalue analysis showed that the first principal component contributed 75%, and the corresponding eigenvector reflected the dominance of the shaded area effect. In the indicator transmission network, the shaded area node had the highest out-degree value of 3; the power generation efficiency node had both an out-degree and in-degree value of 2; the cold storage node and the overall efficiency node had in-degree values ​​of 2 and 3, respectively. The hierarchical indicator association diagram clearly illustrates the performance transmission path. The main path is that the increase in shaded area leads to reduced sunlight, which in turn causes a decrease in power generation, which in turn reduces cold storage capacity, ultimately affecting overall efficiency.Secondary pathways include the impact of shaded area on power generation efficiency through temperature effects, and power generation efficiency affecting cold storage through peak-valley regulation. Quantitative evaluation results show that under standard operating conditions, by optimizing the cold storage strategy, when the shaded area increases by 10%, the decline in power generation efficiency is reduced from 15% to 12%, and the reduction in cold storage capacity is reduced from 12% to 9%. The overall efficiency decline is controlled from 8% to less than 6%. This improvement is particularly evident when the shade lasts for more than two hours.

[0036] Obviously, those skilled in the art may make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include such modifications and variations.

Claims

1. A method for evaluating the efficiency of a photovoltaic power generation and cold storage system based on big data analysis, characterized in that: The method comprises: Obtain shadow distribution data on the surface of photovoltaic modules, extract the changing characteristics of the blocked area through image processing methods, and combine time series analysis methods to determine the dynamic change trend of the blocked area; Based on the dynamic change trend of the shaded area, a regression model is used to predict the fluctuation characteristics of the power generation efficiency of photovoltaic modules, and a mapping relationship between power generation efficiency and shaded area is established; Based on the fluctuation characteristics of power generation efficiency, the historical operating data and meteorological data of the photovoltaic power generation system are analyzed to extract the changing pattern of the cold storage demand of the cold storage system. The adjustment content of the cold storage strategy is determined, including dynamic adjustment parameters. The dynamic adjustment parameters include adjustment of cold storage time, cold storage power and cold storage temperature parameters. Based on the dynamic adjustment parameters of cold storage, combined with the performance parameters and operating constraints of the cold storage system, and using energy efficiency analysis methods, the impact mechanism of the cold storage adjustment scheme on the operating efficiency of the cold storage system is analyzed. The impact mechanism includes the impact of the adjustment scheme on the cold storage capacity, cold discharge capacity, and energy consumption of the cold storage system. The change characteristics of the system efficiency are obtained, including the system's comprehensive energy efficiency, operating costs under peak and valley electricity prices, and carbon emission intensity. Based on the changing characteristics of system efficiency, determine whether the operating status of the cold storage system meets the preset threshold conditions. If the improvement in the system's comprehensive energy efficiency exceeds the preset threshold, the reduction in operating costs exceeds the preset threshold, and the reduction in carbon emission intensity exceeds the preset threshold, then it is determined that the threshold conditions are met and the current strategy adjustment plan is output; The strategy adjustment plan that meets the threshold conditions is applied to the cold storage system, and the changing trend of the system efficiency is monitored in real time. Combined with big data analysis methods, an efficiency evaluation report of the cold storage system is generated. The evaluation report includes the correlation between the blocked area, power generation efficiency, cold storage and system efficiency.

2. The method according to claim 1, characterized in that The method of obtaining shadow distribution data on the surface of the photovoltaic module, extracting the change characteristics of the blocked area by an image processing method, and determining the dynamic change trend of the blocked area by combining a time series analysis method includes: Acquire a high-resolution image of the surface of the photovoltaic module using an image acquisition device, divide the shadow area according to a comparison result of the grayscale value of the pixel points of the high-resolution image with a preset reference grayscale value, and obtain a first shadow area value; Performing edge detection on the shadow area to obtain an edge contour line, fitting the edge contour line using the least squares method to obtain an edge contour curve equation, establishing an autoregressive moving average model based on the edge contour curve equation, and obtaining a motion trajectory equation of the shadow area; A temperature distribution matrix is ​​constructed by collecting temperature data through a pre-deployed temperature sensor array, and isotherms are extracted from the temperature distribution matrix. If the temperature value within the closed isotherm curve is lower than the temperature value of the surrounding area, it is determined that the area is shadowed, and a second shadow area value is obtained; The weighted average method is used to fuse the first shadow area value and the second shadow area value, and the discrete Fourier transform is performed on the fused shadow area value sequence. The frequency components with amplitudes greater than the normalization threshold are extracted according to the spectrum diagram of the discrete Fourier transform to obtain a shadow area change periodic sequence.

3. The method according to claim 1, characterized in that The method uses a regression model to predict the fluctuation characteristics of the power generation efficiency of the photovoltaic module based on the dynamic change trend of the blocked area, and establishes a mapping relationship between the power generation efficiency and the blocked area, including: Extracting the fluctuation component in the power generation efficiency sequence through a sliding time window to obtain a first power generation efficiency curve; According to the first power generation efficiency curve, a nonlinear mapping function is constructed using a support vector regression method to obtain a first prediction function; For the first prediction function, calculating a temperature correction coefficient according to the temperature coefficient to obtain a second prediction function; Processing the real-time blocked area data using the second prediction function to obtain a second power generation efficiency curve, and extracting high-frequency components and low-frequency components from the second power generation efficiency curve through wavelet transform to obtain a third power generation efficiency curve; Performing Fourier transform on the third power generation efficiency curve to extract the spectrum feature vector, fusing the ambient temperature and humidity data using a Bayesian regression method to predict the future power generation efficiency change trend curve; It also includes: according to the dynamic change trend of the blocked area, establishing a regression model with the blocked area as the independent variable and the power generation efficiency as the dependent variable, predicting the fluctuation characteristics of the photovoltaic module power generation efficiency as the blocked area changes, and fitting the quantitative mapping relationship between power generation efficiency and blocked area, including the change range of the blocked area, the fluctuation amplitude of power generation efficiency and the peak efficiency point, so as to predict the power generation efficiency change curve under different blocking scenarios.

4. The method according to claim 3, characterized in that Based on the dynamic change trend of the shielding area, a regression model is established with the shielding area as the independent variable and the power generation efficiency as the dependent variable. The fluctuation characteristics of the photovoltaic module power generation efficiency as the shielding area changes are predicted, and a quantitative mapping relationship between power generation efficiency and shielding area is fitted, including the change range of the shielding area, the fluctuation amplitude of power generation efficiency and the peak efficiency point, so as to predict the power generation efficiency change curve under different shielding scenarios, including: Collecting light intensity data according to a light intensity sensor array, constructing a light intensity distribution matrix for the light intensity data, and processing the light intensity distribution matrix using a threshold segmentation method to obtain a binary image of the occluded area; Counting the pixel ratios of the occluded area in the occluded area binary image to obtain a first occluded area numerical sequence, performing Fourier transform on the first occluded area numerical sequence to extract spectral features, and using trigonometric function superposition fitting to obtain an occluded area dynamic change function; Acquiring voltage and current sampling data output by the photovoltaic module, calculating a power generation value based on the voltage and current sampling data, and performing a sliding average process on the power generation value using a fixed time window to obtain a first power generation efficiency curve; The sampling value of the shielding area dynamic change function is used as the independent variable, the corresponding time value of the first power generation efficiency curve is used as the dependent variable, and the first prediction function is obtained by training through the support vector regression method.

5. The method according to claim 1, wherein The above method analyzes the historical operation data and meteorological data of the photovoltaic power generation system based on the fluctuation characteristics of power generation efficiency, extracts the changing pattern of the cold storage demand of the cold storage system, and determines the adjustment content of the cold storage strategy. The adjustment content includes dynamic adjustment parameters, and the dynamic adjustment parameters include adjustment of the cold storage time, cold storage power and cold storage temperature parameters, including: Based on the photovoltaic power generation power sampling data, the sampling data is processed by a fast Fourier transform method to obtain the period characteristics and amplitude characteristics of the power generation power fluctuation; Segment processing is performed on the periodic characteristics and amplitude characteristics, and a feature extraction method is used to obtain meteorological feature vectors of light intensity, ambient temperature and relative humidity from the segmented data to obtain a feature sequence; According to the characteristic sequence, a support vector machine clustering method is used to process the characteristic sequence to obtain a cold storage load prediction curve; Based on the cold storage load prediction curve, a linear programming solver is used to calculate the start and end points of the cold storage time period to obtain a cold storage duration curve; Perform segmented integration on the cooling time curve to calculate the cooling power requirement in each cooling time period; It also includes: mining the changing patterns of cooling demand of the cold storage system over time and weather in historical operation and meteorological data, identifying key parameters that affect cooling storage demand, extracting intraday fluctuations and seasonal trends in load demand, and determining the optimization space of the cooling storage strategy based on changes in cooling demand. It also adjusts the action space of cooling storage operation parameters, including the adjustable time period range, upper and lower power limits, and temperature setting allowable range, to form the boundaries of dynamic optimization of cooling storage strategy parameters.

6. The method according to claim 5, characterized in that The method mines historical operation and meteorological data to identify the changing patterns of the cooling demand of the cold storage system over time and weather, identifies key parameters that affect the cooling storage demand, extracts the intraday fluctuations and seasonal trends of the load demand, determines the optimization space of the cooling storage strategy based on the changes in cooling demand, and adjusts the action space of the cooling storage operation parameters, including the adjustable time range, upper and lower power limits, and temperature setting allowable range, to form the boundaries of the dynamic optimization of the cooling storage strategy parameters, including: According to the cooling load sequence and meteorological parameter sequence, the long short-term memory network is used to extract the daily fluctuation pattern and seasonal variation characteristics of the cooling load, and the first load fluctuation curve is obtained. Performing wavelet transform processing on the first load fluctuation curve to obtain a second load fluctuation curve by extracting high-frequency fluctuation components and low-frequency change trends; Using a decision tree regressor to process the second load fluctuation curve and the meteorological parameter sequence, and obtaining a load influence parameter sequence by calculating the influence of temperature, humidity, and light intensity on load changes; The cold storage device operation data is classified according to the load impact parameter sequence, and the boundary points of the cold storage period are identified by a hierarchical clustering method of Euclidean distance to obtain the cold storage operation segmentation results; Perform Fourier transform on the inlet and outlet water temperature data sequence in each cold storage operation segment, extract the temperature fluctuation range corresponding to the main frequency component, and obtain the upper and lower limits of the cold storage temperature; The thermal enthalpy difference is calculated based on the upper and lower limits of the cold storage temperature, and combined with the rated capacity of the cold storage device, the cold storage power adjustment range is obtained.

7. The method according to claim 1, characterized in that Based on the dynamic adjustment parameters of cold storage, combined with the performance parameters and operating constraints of the cold storage system, the energy efficiency analysis method is used to analyze the impact mechanism of the cold storage adjustment scheme on the operating efficiency of the cold storage system. The impact mechanism includes the impact of the adjustment scheme on the cold storage capacity, cold discharge capacity and energy consumption of the cold storage system, and the change characteristics of the system efficiency are obtained. The change characteristics include the system's comprehensive energy efficiency, operating costs under peak and valley electricity prices, and carbon emission intensity, including: According to the parameters of cooling capacity, cooling capacity and power consumption, the adaptive weighted regression method is used for coupling calculation to obtain the cooling coefficient curve. Perform piecewise linear fitting on the cooling coefficient curve, extract the slope and intercept of each segment, construct the cooling coefficient prediction function, and obtain the energy efficiency prediction value; A random forest algorithm is used to process the cooling coefficient curve and peak-valley electricity price data to obtain an electricity consumption cost value; The carbon emissions per unit time are calculated based on the electricity consumption cost value and the grid carbon emission factor data in combination with the unit electricity consumption power curve to form a carbon emission curve.

8. The method according to claim 1, characterized in that The system determines whether the operating state of the cold storage system meets the preset threshold conditions based on the change characteristics of the system efficiency. If the improvement in the system's comprehensive energy efficiency exceeds the preset threshold, the reduction in operating costs exceeds the preset threshold, and the reduction in carbon emission intensity exceeds the preset threshold, the threshold conditions are determined to be met, and the current strategy adjustment plan is output, including: The index change rate within each sampling period is calculated based on the comprehensive energy efficiency value, operating cost value and carbon emission intensity value to obtain the index change rate sequence; The index change rate sequence is segmented using a sliding time window, and the change amplitude of adjacent sampling moments is calculated for the data in each time window to obtain the efficiency change sequence; Applying the gradient descent method to the efficiency change sequence, and using the mean square error as the optimization objective function to calculate the time series change trend of the efficiency improvement, cost reduction, and emission reduction; A three-dimensional feature vector is constructed according to the time series variation trend, and the distance value from the feature vector to a preset threshold plane is calculated by the radial basis kernel function of the support vector machine to obtain a time interval sequence that meets the threshold condition.

9. The method according to claim 1, characterized in that The strategy adjustment scheme that meets the threshold conditions is applied to the cold storage system, and the changing trend of the system efficiency is monitored in real time. A cold storage system efficiency evaluation report is generated by combining the big data analysis method. The evaluation report includes the correlation between the shielding area, power generation efficiency, cold storage and system efficiency, including: A time series predictor is constructed using a long short-term memory network based on the monitored data, and the time series predictor extracts time series features of each indicator to obtain an indicator sequence; Constructing a sliding correlation window for the indicator sequence, wherein the sliding correlation window calculates the Pearson correlation coefficient between the indicators to obtain a correlation coefficient matrix; An indicator mapping function is constructed using a random forest regression algorithm according to the correlation coefficient matrix, wherein the indicator mapping function calculates the unidirectional influence intensity between the indicators to obtain an influence intensity matrix; An indicator transfer network is constructed based on the influence intensity matrix using a eigenvector sequence. The indicator transfer network calculates the in-degree value and out-degree value of each node to obtain an indicator influence intensity ranking. A hierarchical indicator correlation diagram is generated based on the ranking of indicator impact intensity, the transmission path from the blocked area to the comprehensive efficiency is extracted, and a performance evaluation report containing indicator correlation, impact degree and response characteristics is generated.

Images