Plateau clean energy power generation amount prediction system and method based on high-altitude characteristics

Abstract

The present application relates to the technical field of monitoring systems, in particular to a plateau clean energy power generation capacity prediction system and method based on high-altitude characteristics. It comprises a multi-source data acquisition module configured to acquire frozen soil freeze-thaw cycle data, freeze-thaw depth data, ultraviolet radiation intensity data, canyon terrain wind field data, atmospheric pressure data, snow reflectivity data, and ground temperature gradient data; a data processing module configured to calculate frozen soil deformation coefficients, ultraviolet attenuation coefficients, wind field distortion coefficients, air thinning correction coefficients, thermal spot attenuation coefficients, foundation settlement coefficients, and fan aerodynamic correction coefficients based on multi-source data; and a prediction model construction module configured to construct a coupling prediction model containing the frozen soil deformation coefficients, ultraviolet attenuation coefficients, wind field distortion coefficients, air thinning correction coefficients, thermal spot attenuation coefficients, foundation settlement coefficients, and fan aerodynamic correction coefficients. The present application can adapt to the complex environment of the plateau and comprehensively consider the coupling influence of multiple factors on power generation capacity.

Description

Technical Field

[0001] This invention relates to the field of monitoring system technology, and specifically to a system and method for predicting clean energy power generation in high-altitude areas. Background Technology

[0002] In the field of clean energy development along plateau highways, power generation forecasting is a crucial link in achieving efficient energy management and dispatch. Existing clean energy power generation forecasting systems are mostly designed based on the environmental characteristics of conventional areas, relying primarily on single meteorological parameters such as wind speed and solar radiation intensity to construct forecasting models, without fully considering the synergistic effects of multiple factors under the unique plateau environment. Plateau regions such as the Sanjiangyuan region possess unique ecological and geographical characteristics: permafrost areas experience periodic freeze-thaw cycles, easily leading to micro-deformation of energy equipment foundations; strong ultraviolet radiation accelerates the aging of photovoltaic modules and wind turbine blades; canyon topography causes wind field distortion, compounded by interference from wildlife activity on energy equipment, forming a complex multi-factor coupling effect. Existing systems, because they do not incorporate these plateau-specific influencing factors and lack quantitative analysis of the interrelationships between these factors, result in significant deviations between forecast results and actual power generation, making it difficult to meet the precise dispatching requirements of clean energy systems along plateau highways.

[0003] Based on the above problems, there is an urgent need for a power generation prediction scheme that can adapt to the complex environment of the plateau and comprehensively consider the coupled effects of multiple factors. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and proposes a plateau clean energy power generation prediction system based on high-altitude characteristics, comprising:

[0005] The multi-source data acquisition module collects multi-source data, including freeze-thaw depth data, ultraviolet radiation intensity data, canyon topographic wind field data, atmospheric pressure data, snow reflectivity data, and geothermal gradient data.

[0006] The data processing module is configured to normalize the multi-source data and calculate the permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air thinning correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient.

[0007] The prediction model building module is configured to build a coupled prediction model that includes the permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air rarefaction correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient.

[0008] And a prediction execution module, configured to output a predicted value of plateau clean energy power generation based on high-altitude characteristics based on the coupled prediction model.

[0009] Preferably, the multi-source data acquisition module includes:

[0010] A distributed optical fiber sensor is configured to collect the frozen soil freeze-thaw cycle data and the freeze-thaw depth data.

[0011] An ultraviolet spectrometer is configured to collect the ultraviolet radiation intensity data.

[0012] A three-dimensional ultrasonic anemometer is configured to collect wind field data of the canyon topography, including wind speed data, wind direction data, and turbulence intensity data.

[0013] A barometric pressure sensor is configured to collect the atmospheric pressure data.

[0014] A spectrometer configured to collect the snow reflectance data;

[0015] A ground temperature sensor array is configured to collect the ground temperature gradient data.

[0016] More preferably, the data processing module includes:

[0017] The first calculation unit is configured to calculate the frozen soil deformation coefficient based on the frozen soil freeze-thaw cycle data and the freeze-thaw depth data, calculate the ultraviolet radiation attenuation coefficient based on the ultraviolet radiation intensity data, and calculate the wind field distortion coefficient based on wind speed data, wind direction data, turbulence intensity data, and the frozen soil deformation coefficient.

[0018] The second calculation unit is configured to calculate the air rarefaction correction coefficient based on the atmospheric pressure data and the snow reflectivity data, and to calculate the hot spot attenuation coefficient based on the air rarefaction correction coefficient.

[0019] The third calculation unit is configured to calculate the foundation settlement coefficient based on the geothermal gradient data and the atmospheric pressure data, and to calculate the wind turbine aerodynamic correction coefficient based on the foundation settlement coefficient and the atmospheric pressure data.

[0020] More preferably, the prediction model construction module includes:

[0021] The photovoltaic prediction unit is configured to construct a photovoltaic power generation prediction sub-model that includes the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the air rarefaction correction coefficient, and the hot spot attenuation coefficient.

[0022] The wind power prediction unit is configured to construct a wind power generation prediction sub-model that includes the wind field distortion coefficient, the ultraviolet attenuation coefficient, the foundation settlement coefficient, and the wind turbine aerodynamic correction coefficient.

[0023] The integration unit is configured to integrate the photovoltaic power generation prediction sub-model and the wind power generation prediction sub-model into the coupled prediction model.

[0024] More preferably, the photovoltaic power generation prediction sub-model is expressed as follows:

[0025]

[0026] in, For the predicted photovoltaic power generation, The photovoltaic power output is given by the figure of stars under standard operating conditions, and t represents the power generation time. The coefficient of permafrost deformation. Where is the ultraviolet attenuation coefficient, and H is the freeze-thaw depth. For reference freeze-thaw depth, R is the snow reflectivity. This is the hot spot attenuation coefficient. The air rarefaction correction factor; the permafrost deformation coefficient Represented as: , where T is the freeze-thaw cycle period of the frozen soil;

[0027] The ultraviolet attenuation coefficient Represented as Where U is the ultraviolet radiation intensity; the air rarefaction correction coefficient Represented as Where P is atmospheric pressure; the hot spot attenuation coefficient Represented as , where δ is an empirical constant.

[0028] More preferably, the wind power generation prediction sub-model is expressed as follows:

[0029]

[0030] in, The predicted wind power generation is given by P1, where P1 is the wind power output under standard operating conditions, and t is the generation time. The wind field distortion coefficient is denoted as . The ultraviolet attenuation coefficient is... This is the aerodynamic correction factor for the fan. The normalized air pressure fluctuation value. The basic settlement coefficient; the wind field distortion coefficient Represented as: ,in Where I is the wind direction and I is the turbulence intensity. The deformation coefficient of the frozen soil; the aerodynamic correction coefficient of the fan. Represented as: Where F is the number of air pressure fluctuations; the foundation settlement coefficient Represented as: , where G is the normalized geothermal gradient.

[0031] More preferably, the coupled prediction model is expressed as:

[0032]

[0033] in, For the predicted total power generation, For the predicted photovoltaic power generation, The predicted wind power generation; the coupled prediction model includes a coupling term between the permafrost deformation coefficient and the wind field distortion coefficient. The coupling term between the ultraviolet attenuation coefficient and the aerodynamic correction coefficient of the fan. The coupling term between the basic settlement coefficient and the normalized air pressure fluctuation value .

[0034] Further preferred options include:

[0035] An edge computing node is configured to be deployed along a plateau highway to preprocess the multi-source data and calculate the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air thinning correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the wind turbine aerodynamic correction coefficient. A communication network is configured to transmit the data processed by the edge computing node to a cloud server. The cloud server is configured to run the prediction model construction module and the prediction execution module to generate the predicted value of plateau clean energy power generation based on high-altitude characteristics and feed the predicted value back to the edge computing node.

[0036] More preferably, the edge computing node includes:

[0037] The microprocessor is configured to execute data preprocessing algorithms and coefficient calculation algorithms;

[0038] A memory configured to store the multi-source data, the preprocessing algorithm, and the coefficient calculation algorithm;

[0039] An analog-to-digital converter is configured to convert data from a distributed fiber optic sensor, an ultraviolet spectrometer, a three-dimensional ultrasonic anemometer, a barometer, a spectrometer, and a geothermal sensor array into a unified vector.

[0040] The communication interface is configured to interact with the cloud server via the communication network; wherein the microprocessor is connected to the analog-to-digital converter via an SPI bus, and the microprocessor transmits data with the cloud server via the communication interface.

[0041] Methods for predicting clean energy power generation on plateaus based on high-altitude characteristics include:

[0042] Collect data on the freeze-thaw cycle of permafrost, freeze-thaw depth, ultraviolet radiation intensity, canyon topography wind field, atmospheric pressure, snow reflectivity, and geothermal gradient.

[0043] Based on the multi-source data, the permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air rarefaction correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient were calculated.

[0044] Construct a coupled prediction model that includes the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air rarefaction correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the wind turbine aerodynamic correction coefficient;

[0045] The coupled prediction model outputs a predicted value for clean energy power generation on the plateau based on the characteristics of high altitude.

[0046] Technical effects:

[0047] This invention captures plateau-specific environmental parameters such as permafrost freeze-thaw cycles, ultraviolet radiation, canyon wind fields, and wildlife activity through a multi-source data acquisition module. A data processing module calculates multi-dimensional correction coefficients, and a prediction model construction module forms a multi-factor coupled prediction model. This solves the prediction bias problem caused by existing technologies failing to consider the synergistic effects of multiple factors in the plateau environment. Its innovation lies in incorporating the interplay of geological, climatic, and ecological factors in the unique plateau environment into the prediction system, achieving accurate prediction of clean energy power generation, meeting the efficient dispatch requirements of plateau highway energy systems, and adapting to practical application scenarios in complex environments such as the Three-River-Source Region. Attached Figure Description

[0048] Figure 1 This is a block diagram of the plateau clean energy power generation prediction system based on high-altitude characteristics, as described in this application.

[0049] Figure 2 This is a flowchart of the plateau clean energy power generation prediction method based on high-altitude characteristics proposed in this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0051] Traditional technical solutions have the following technical problems: existing plateau clean energy power generation prediction systems mostly rely on single meteorological parameters or general models, are not designed for the special environment of the Sanjiangyuan region, do not adequately consider plateau-specific factors such as permafrost freeze-thaw, strong ultraviolet radiation, and canyon wind fields, and have not established a multi-factor linkage mechanism, resulting in a large deviation between prediction results and reality, and failing to provide accurate data support for highway energy management. At the same time, the data collection dimensions are limited, making it difficult to capture the cross-influence of ecological factors and physical environment.

[0052] Based on this, please refer to Figure 1 This embodiment provides a plateau clean energy power generation prediction system based on high-altitude characteristics, comprising: a multi-source data acquisition module configured to acquire permafrost freeze-thaw cycle data, freeze-thaw depth data, ultraviolet radiation intensity data, canyon topographic wind field data, atmospheric pressure data, snow reflectivity data, and geothermal gradient data; a data processing module configured to calculate permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air thinning correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient based on the multi-source data; a prediction model construction module configured to construct a coupled prediction model including the permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air thinning correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient; and a prediction execution module configured to output a plateau clean energy power generation prediction value based on high-altitude characteristics based on the coupled prediction model.

[0053] This solution breaks through the limitations of traditional single-parameter prediction by working in collaboration with multiple modules. The multi-source data acquisition module covers diverse factors unique to the plateau, such as permafrost, ultraviolet radiation, and wind fields. The data processing module calculates various correction coefficients to capture the implicit correlations between factors. The prediction model construction module integrates multiple coefficients into a coupled model to achieve accurate mapping of complex environments. This solves the problem of insufficient adaptability of traditional models to the special environment of the plateau, making the prediction results more consistent with the actual power generation situation on the plateau, and providing a reliable basis for the scheduling, maintenance, and optimization of highway clean energy systems.

[0054] Traditional technical solutions have the following technical problems: existing data acquisition devices mostly use general sensor combinations, which are not customized for plateau highway scenarios. The sensor types are limited, making it impossible to collect special parameters such as permafrost freeze-thaw cycles. Furthermore, the sampling accuracy and spatial coverage are insufficient, resulting in missing or distorted key environmental data, which affects the accuracy of subsequent coefficient calculations and model construction. At the same time, the sensor layout lacks specificity and is difficult to adapt to complex terrains such as canyons and permafrost areas.

[0055] Based on this, the multi-source data acquisition module includes: a distributed fiber optic sensor configured to acquire the frozen soil freeze-thaw cycle data and the freeze-thaw depth data; an ultraviolet spectrometer configured to acquire the ultraviolet radiation intensity data; a three-dimensional ultrasonic anemometer configured to acquire the canyon topographic wind field data, which includes wind speed data, wind direction data, and turbulence intensity data; a barometric pressure sensor configured to acquire the atmospheric pressure data; a spectrometer configured to acquire the snow reflectance data; and a ground temperature sensor array configured to acquire the ground temperature gradient data.

[0056] This solution addresses the issues of comprehensiveness and accuracy in data acquisition through a customized sensor suite. Distributed fiber optic sensors are adapted to the long-term monitoring needs of permafrost regions, accurately capturing the periodic changes and depth information of permafrost freeze-thaw cycles. An ultraviolet spectrometer specifically captures the characteristics of strong ultraviolet radiation, providing a basis for subsequent attenuation coefficient calculations. A three-dimensional ultrasonic anemometer refines the dimensions of wind field data, simultaneously acquiring wind speed, wind direction, and turbulence intensity, adapting to the wind field characteristics of canyon terrain. Other sensors correspond to specific factors such as atmospheric pressure, snow reflectivity, and ground temperature gradient, ensuring accurate acquisition of each key parameter.

[0057] Its technical effectiveness is reflected in the accurate capture of diverse environmental parameters along the plateau highway. The sensor type is highly matched with the monitoring object, ensuring the integrity and accuracy of key data such as permafrost, ultraviolet radiation, and wind field, providing high-quality input for subsequent data processing and model building. At the same time, it adapts to the complex terrain and ecological environment of the plateau, avoiding data loss or errors caused by unsuitable sensors.

[0058] Traditional technical solutions have the following technical problems: existing data processing methods mostly use a single algorithm to process all data, without considering the characteristics of different factors in the plateau environment. They handle the linkage between factors such as permafrost and wind field, ultraviolet radiation and hot spots in a simplistic way, and the coefficient calculation lacks specificity, resulting in a large deviation between the correction coefficient and the actual environment. This makes it impossible to accurately reflect the degree of influence of each factor on power generation and affects the reliability of the prediction model.

[0059] Based on this, the data processing module includes: a first calculation unit configured to calculate the permafrost deformation coefficient based on the permafrost freeze-thaw cycle data and the freeze-thaw depth data, calculate the ultraviolet radiation attenuation coefficient based on the ultraviolet radiation intensity data, and calculate the wind field distortion coefficient based on the wind speed data, the wind direction data, the turbulence intensity data, and the permafrost deformation coefficient; a second calculation unit configured to calculate the air rarefaction correction coefficient based on the atmospheric pressure data and the snow reflectivity data, and calculate the hot spot attenuation coefficient based on the air rarefaction correction coefficient; and a third calculation unit configured to calculate the foundation settlement coefficient based on the ground temperature gradient data and the atmospheric pressure data, and calculate the wind turbine aerodynamic correction coefficient based on the foundation settlement coefficient and the atmospheric pressure data.

[0060] This scheme addresses the problem of insufficient inter-factor linkage by processing different types of data in separate units. The first calculation unit focuses on the correlation calculation of permafrost, ultraviolet radiation, and wind field. For example, when calculating the wind field distortion coefficient, it considers not only wind speed, wind direction, and turbulence intensity, but also incorporates the permafrost deformation coefficient to reflect the indirect impact of permafrost changes on wind field distribution. The second calculation unit focuses on the interaction between atmospheric pressure and snow reflectivity. It calculates the air thinning correction coefficient through the joint calculation of the two and further derives the hot spot attenuation coefficient to reflect the combined effect of low air pressure on plateau and snow cover on the hot spot effect of photovoltaic modules. The third calculation unit processes the correlation between ground temperature gradient, atmospheric pressure, foundation settlement, and wind turbine aerodynamic performance to ensure that the foundation settlement coefficient and wind turbine aerodynamic correction coefficient can reflect the synergistic influence of geological and atmospheric factors.

[0061] Its technical effectiveness is reflected in the refined processing of complex environmental factors. Each computing unit optimizes the algorithm for specific factor combinations to ensure the accuracy of correction coefficients such as permafrost deformation coefficient and wind field distortion coefficient, accurately reflect the influence mechanism of different factors on power generation, provide reliable parameter support for prediction models, and improve the adaptability of models to plateau environments.

[0062] Traditional technical solutions have the following technical problems: existing prediction models mostly use a single model to predict total power generation, without distinguishing the characteristics of photovoltaic power generation and wind power generation, and without modeling the influencing factors of each separately. This results in insufficient targeting of photovoltaic and wind power, and an inability to accurately capture the patterns of their respective influence by environmental factors. At the same time, the model structure is simple and lacks hierarchical integration of multiple factors, which affects the prediction accuracy.

[0063] Based on this, the prediction model construction module includes: a photovoltaic prediction unit, configured to construct a photovoltaic power generation prediction sub-model including the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the air rarefaction correction coefficient, and the hot spot attenuation coefficient; a wind power prediction unit, configured to construct a wind power generation prediction sub-model including the wind field distortion coefficient, the ultraviolet attenuation coefficient, the foundation settlement coefficient, and the wind turbine aerodynamic correction coefficient; and an integration unit, configured to integrate the photovoltaic power generation prediction sub-model and the wind power generation prediction sub-model into the coupled prediction model.

[0064] This solution addresses the shortcomings of traditional models by separating and then integrating sub-models. The photovoltaic (PV) prediction sub-model focuses on core factors affecting PV power generation, such as changes in PV panel support angles caused by permafrost deformation, component degradation caused by strong ultraviolet radiation, the impact of thin air on light absorption, and the attenuation effect of hot spot effects, accurately mapping the power generation patterns of PV systems in high-altitude environments. The wind power prediction sub-model focuses on the impact of wind field distortion on wind speed capture, the effect of thin air on wind turbine aerodynamic performance, changes in wind turbine structural stability caused by foundation settlement, and the adjustment of output power by wind turbine aerodynamic correction coefficients, accurately reflecting the characteristics of wind power generation. The integration unit organically combines the two sub-models through a reasonable algorithm to form a coupled prediction model covering the wind-solar hybrid system.

[0065] Its technical effectiveness is reflected in improving the relevance and accuracy of the prediction model. The photovoltaic and wind power models are adapted to their respective environmental influencing factors, accurately reflecting the power generation patterns of different energy forms. The integrated coupled model takes into account the characteristics of both, fully covering the power generation scenarios of clean energy on plateau highways, making the prediction results more consistent with the actual power generation situation, and providing more detailed reference for energy dispatch.

[0066] Traditional technical solutions suffer from the following problems: Existing photovoltaic power generation prediction formulas are mostly based on general environmental parameters, failing to consider special factors such as photovoltaic panel deformation caused by permafrost freeze-thaw in high-altitude areas, module degradation caused by strong ultraviolet radiation, and the synergistic effects of thin air and snow reflection. The formulas lack quantitative expressions and coordinated processing of these factors, resulting in significant prediction errors in high-altitude areas and an inability to accurately reflect the actual power generation capacity of the photovoltaic system. Therefore, the proposed photovoltaic power generation prediction sub-model is expressed as follows:

[0067]

[0068] in, For the predicted photovoltaic power generation, The photovoltaic power output is given by the figure of stars under standard operating conditions, and t represents the power generation time. The coefficient of permafrost deformation. Where is the ultraviolet attenuation coefficient, and H is the freeze-thaw depth. For reference freeze-thaw depth, R is the snow reflectivity. This is the hot spot attenuation coefficient. The air rarefaction correction factor; the permafrost deformation coefficient Represented as: , where T is the freeze-thaw cycle period of the frozen soil;

[0069] The ultraviolet attenuation coefficient Represented as: Where U is the ultraviolet radiation intensity; the air rarefaction correction coefficient Represented as: Where P is atmospheric pressure; the hot spot attenuation coefficient Represented as: , where δ is an empirical constant.

[0070] This formula is a specialized prediction model for photovoltaic power generation on plateau highways. Its core lies in quantifying the comprehensive impact of the unique plateau environment on photovoltaic modules through multi-dimensional correction coefficients. Specifically, the permafrost deformation coefficient α reflects the impact of the periodic freeze-thaw cycles of permafrost on the micro-deformation of the photovoltaic panel support and its effect on the light-receiving angle; the ultraviolet attenuation coefficient β reflects the attenuation effect of strong ultraviolet radiation on the light transmittance of the photovoltaic module glass.

[0071] The impact of increased freeze-thaw depth on soil stability was quantified, indirectly correcting for deviations in photovoltaic panel installation angles; a correction coefficient for thin air was also applied. It reflects both the reduced heat dissipation efficiency of photovoltaic panels caused by low air pressure at high altitudes and the enhanced effect of snow reflection on the irradiance received by the modules.

[0072] The negative effects of quantifying snow reflectance separately; hot spot attenuation coefficient The system corrects for hot spot effects caused by factors such as thin air, and the empirical constant δ is determined based on the influence of local biological activities on the power generation process. Its technical effectiveness lies in accurately capturing the complex impact of the plateau environment on photovoltaic power generation, with each coefficient corresponding to the mechanism of action of different environmental factors.

[0073] The formula can dynamically reflect the impact of real-time changes in special factors such as permafrost thawing, ultraviolet radiation, and snow accumulation on power generation, making the photovoltaic power generation prediction results closer to the actual situation and providing accurate data support for the optimized operation and maintenance of photovoltaic systems.

[0074] Traditional technical solutions suffer from the following problems: Existing wind power generation prediction models are mostly designed based on the characteristics of wind fields in plains areas, failing to fully consider special factors such as wind field distortion caused by plateau and canyon terrain, foundation settlement caused by freeze-thaw cycles in permafrost, and the impact of low-pressure environments on wind turbine aerodynamic performance. Furthermore, they lack quantitative analysis of the correlation between ultraviolet radiation and wind turbine material aging, and the relationship between air pressure fluctuations and wind turbine operational stability. This results in significant prediction biases in plateau environments, failing to accurately reflect the actual output capacity of wind power generation equipment. Therefore, the proposed wind power generation prediction sub-model is as follows:

[0075]

[0076] in, The predicted wind power generation is given by P1, where P1 is the wind power output under standard operating conditions, and t is the generation time. The wind field distortion coefficient is denoted as . The ultraviolet attenuation coefficient is... This is the aerodynamic correction factor for the fan. The normalized air pressure fluctuation value. The basic settlement coefficient; the wind field distortion coefficient Represented as: ,in Where I is the wind direction and I is the turbulence intensity. The deformation coefficient of the frozen soil; the aerodynamic correction coefficient of the fan. Represented as: Where F is the number of air pressure fluctuations; the foundation settlement coefficient Represented as: , where G is the normalized geothermal gradient.

[0077] This sub-model, tailored to the characteristics of wind power in high-altitude areas, quantifies the comprehensive impact of environmental factors through multi-coefficient synergy. Wind field distortion coefficient. Integrating the correlation between wind direction, turbulence intensity, and permafrost deformation, this study reflects the superimposed effect of canyon topography and permafrost changes on wind field distribution; ultraviolet attenuation coefficient. The model incorporates the effects of strong ultraviolet radiation on the aging of wind turbine blade materials, indirectly correcting the output power; the wind turbine aerodynamic correction coefficient... By combining foundation settlement and the number of air pressure fluctuations, the combined effect of geological stability and atmospheric disturbance on the aerodynamic performance of wind turbines is quantified; foundation settlement coefficient. By multiplying the geothermal gradient by the number of air pressure fluctuations, the foundation subsidence effect jointly caused by geothermal changes and air pressure disturbances can be accurately captured.

[0078] The method directly corrects the negative impact of the coupling between air pressure fluctuations and foundation settlement on power generation. Its technical effect is reflected in the accurate prediction of wind power generation in the complex environment of the plateau. The linkage design between various coefficients accurately reflects the synergistic effect mechanism of factors such as wind field, permafrost, ultraviolet radiation, and air pressure. The model can dynamically respond to changes in plateau environmental parameters, making the prediction results more consistent with the actual operating status of wind power equipment, and providing a reliable basis for wind power system scheduling optimization and equipment maintenance.

[0079] The item will include the ultraviolet attenuation coefficient. Introducing a wind power model to demonstrate the aging effects of strong ultraviolet radiation on wind turbine blade materials: The smaller the value (the stronger the ultraviolet radiation), the more significant the correction of power by this item, reflecting the decline in aerodynamic performance caused by blade surface aging, and indirectly correcting the power generation output.

[0080] This is the aerodynamic correction factor for the fan. F represents the number of air pressure fluctuations, combined with the foundation settlement coefficient. The combined effects of geological subsidence and atmospheric disturbance on the verticality of wind turbine towers were quantified by the number of air pressure fluctuations: the more severe the foundation settlement and the more frequent the air pressure fluctuations, the greater the aerodynamic resistance during wind turbine operation. The smaller the value, the lower the power generation efficiency.

[0081] Traditional technical solutions have the following technical problems: existing total power generation prediction models mostly adopt the method of simply superimposing the prediction results of photovoltaic and wind power, without considering the coupling relationship between the two in the plateau environment, such as the simultaneous impact of permafrost deformation on photovoltaic panel supports and wind turbine foundations, the simultaneous effect of ultraviolet radiation on photovoltaic modules and wind turbine blades, and the common impact of air pressure fluctuations on wind and solar equipment. As a result, the total power generation prediction ignores the synergistic effect between factors and cannot fully reflect the actual output characteristics of the overall power generation system.

[0082] Based on this, the coupled prediction model is expressed as:

[0083]

[0084] Where P is the predicted total power generation. For the predicted photovoltaic power generation, The predicted wind power generation; the coupled prediction model includes a coupling term between the permafrost deformation coefficient and the wind field distortion coefficient. The coupling term between the ultraviolet attenuation coefficient and the aerodynamic correction coefficient of the fan. The coupling term between the foundation settlement coefficient and the normalized air pressure fluctuation value .

[0085] This model integrates photovoltaic and wind power prediction sub-models and highlights key coupling terms to achieve a comprehensive prediction of total power generation. The coupling term between the permafrost deformation coefficient and the wind field distortion coefficient is also included. This reflects the synergistic effect of permafrost changes on the photovoltaic panel support and the wind field around the wind turbine; the coupling of the ultraviolet attenuation coefficient and the aerodynamic correction coefficient of the wind turbine. The combined effect of strong ultraviolet radiation on the aerodynamic performance of photovoltaic modules and wind turbines; the coupling term between the foundation settlement coefficient and the normalized air pressure fluctuation value. This reflects the combined effect of geological subsidence and atmospheric disturbance on the stability of wind and solar equipment foundations.

[0086] The models are not simply added together, but rather the core parameters and coupling terms in each sub-model are retained to ensure that the total power generation forecast can reflect the common and specific impacts of environmental factors on the entire clean energy system.

[0087] Its technical effectiveness is reflected in the comprehensive capture of the synergistic mechanism of photovoltaic and wind power systems in the plateau environment. The design of the coupling term enables the model to accurately reflect the impact of multiple factors on the total power generation, avoiding the prediction bias caused by the traditional superposition method. The total power generation prediction results are more in line with the actual output of the plateau highway clean energy system, providing comprehensive and reliable data support for overall energy dispatch, capacity planning and system optimization.

[0088] Traditional technical solutions have the following technical problems: Existing prediction systems mostly adopt a centralized data processing architecture, which directly transmits all sensor data to the cloud server for processing and model calculation. However, the network coverage along the plateau highway is poor and the data transmission latency is high. The remote transmission of a large amount of raw data can easily lead to data loss or delay, and the cloud server is overloaded, making it difficult to achieve real-time prediction. At the same time, there is a lack of edge-side preprocessing, and noise and redundant information in the raw data directly enter the model, affecting the prediction accuracy and efficiency.

[0089] Based on this, it also includes: an edge computing node configured to be deployed along the plateau highway, which preprocesses the multi-source data and calculates the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air thinning correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the wind turbine aerodynamic correction coefficient; a communication network configured to transmit the data processed by the edge computing node to a cloud server; and a cloud server configured to run the prediction model construction module and the prediction execution module, generate the predicted value of plateau clean energy power generation based on high-altitude characteristics, and feed the predicted value back to the edge computing node.

[0090] This solution addresses the drawbacks of centralized processing through an edge-cloud collaborative architecture. Edge computing nodes are deployed on-site to collect and preprocess data locally, filtering noise, compressing redundant information, and simultaneously performing coefficient calculations, reducing the amount of data uploaded and adapting to the limited network bandwidth at high altitudes. The communication network is responsible for transmitting the processed, streamlined data, reducing transmission pressure and latency. The cloud server focuses on complex model building and prediction calculations, using powerful computing capabilities to generate prediction results and provide feedback, forming a closed loop. The division of labor between edge nodes and the cloud is clear: the edge focuses on real-time preprocessing and coefficient calculations, while the cloud focuses on global model calculations. Together, they improve system response speed and reliability.

[0091] Its technical advantages are reflected in significantly improved system real-time performance and stability. Localized processing at edge computing nodes reduces data transmission volume, lowers dependence on network quality, and avoids delays and data loss during remote transmission of raw data. The preprocessing stage improves input data quality, laying the foundation for subsequent model calculations. The cloud server focuses on core model operations, improving prediction efficiency and accuracy. The overall architecture adapts to the unique environment of high-altitude highways, ensuring that power generation predictions can serve energy dispatch and equipment maintenance needs in real-time and accurately.

[0092] Traditional technical solutions have the following technical problems: the hardware configuration of existing edge computing nodes lacks specificity and does not take into account the characteristics of diverse sensor types and inconsistent data interfaces in high-altitude environments, resulting in unstable sensor data acquisition; at the same time, the processor performance and storage capacity are mismatched, the preprocessing algorithm and coefficient calculation algorithm have low operating efficiency, and the data conversion and communication interface have poor compatibility, which cannot meet the continuous and reliable data processing requirements in high-altitude scenarios.

[0093] Based on this, the edge computing node includes: a microprocessor configured to execute a data preprocessing algorithm and a coefficient calculation algorithm; a memory configured to store the multi-source data, the preprocessing algorithm, and the coefficient calculation algorithm; an analog-to-digital converter configured to connect the distributed fiber optic sensor, the ultraviolet spectrometer, the three-dimensional ultrasonic anemometer, the barometric pressure sensor, the spectrometer, and the geothermal sensor array; and a communication interface configured to interact with the cloud server via the communication network. The microprocessor is connected to the analog-to-digital converter via an SPI bus, and the microprocessor transmits data to the cloud server via the communication interface.

[0094] This solution addresses the compatibility and efficiency issues of edge nodes through customized hardware configuration and interface design. The microprocessor, as the core, is responsible for algorithm execution, ensuring efficient preprocessing and coefficient calculation. The memory provides ample space to store data and algorithms, supporting offline processing capabilities. The analog-to-digital converter (ADC) uniformly interfaces with various sensors, converting analog signals to digital signals and resolving interface inconsistencies. The SPI bus connects the microprocessor and ADC, ensuring high-speed and stable data transmission. The communication interface is adapted to high-altitude communication networks, guaranteeing data interaction with the cloud. The selection and connection methods of the hardware components are optimized for high-altitude, multi-sensor, and low-network environments, ensuring stable node operation.

[0095] Its technical advantages are reflected in the efficient and stable operation of edge computing nodes. The matching of microprocessors and memory ensures rapid algorithm execution and improves data processing efficiency. The design of analog-to-digital converters and SPI buses solves the compatibility problem of multi-sensor data acquisition, ensuring accurate conversion and transmission of various environmental parameters. The communication interface ensures reliable interaction with the cloud and adapts to the complex network environment of high-altitude areas. The targeted configuration of edge node hardware provides solid hardware support for the real-time performance and reliability of the entire prediction system, ensuring stable data acquisition, processing, and participation in the prediction process even in harsh high-altitude environments.

[0096] Traditional technical solutions have the following technical problems: existing power generation prediction methods have vague steps, do not clearly define the scope and standards for collecting data unique to plateaus, lack a unified process for coefficient calculation, and the model construction does not reflect the multi-factor coupling logic, resulting in poor operability of the methods and difficulty for those skilled in the art to reproduce them; at the same time, the steps are loosely connected, and the logical chain of data collection, processing, modeling and prediction is incomplete, which cannot ensure the consistency and accuracy of prediction results.

[0097] Based on this, a method for predicting clean energy power generation in high-altitude plateaus, applied to any of the aforementioned systems, is characterized by comprising: collecting data on permafrost freeze-thaw cycles, freeze-thaw depths, ultraviolet radiation intensity, canyon topographic wind fields, atmospheric pressure, snow reflectivity, and geothermal gradients; calculating permafrost deformation coefficients, ultraviolet attenuation coefficients, wind field distortion coefficients, air thinning correction coefficients, hot spot attenuation coefficients, foundation settlement coefficients, and wind turbine aerodynamic correction coefficients based on the multi-source data; constructing a coupled prediction model including the permafrost deformation coefficient, ultraviolet attenuation coefficient, wind field distortion coefficient, air thinning correction coefficient, hot spot attenuation coefficient, foundation settlement coefficient, and wind turbine aerodynamic correction coefficient; and outputting predicted values ​​for clean energy power generation in high-altitude plateaus based on the coupled prediction model.

[0098] This method breaks down the process into clear steps, forming a complete logical chain from data collection and coefficient calculation to model building and prediction output, specifically addressing the ambiguity and inoperability of traditional methods. The first step involves clearly identifying and collecting environmental parameters specific to the plateau environment to ensure data comprehensiveness. The second step calculates specific correction coefficients based on the collected data to quantify the impact of environmental factors. The third step constructs a coupled model, integrating multiple coefficients to reflect the synergistic effects of various factors. The fourth step outputs prediction results through the model, forming a closed loop. Each step is tightly integrated, with a clear data flow, and each step serves the goal of accurate prediction under the plateau environment.

[0099] Its technical effectiveness is reflected in providing an operable and reproducible prediction method, with clear steps to guide those skilled in the art to implement the process, ensuring prediction consistency in different scenarios; the data acquisition stage focuses on plateau-specific parameters, providing high-quality input for subsequent processing; the coefficient calculation and model building steps embody multi-factor coupling logic, ensuring that the prediction results reflect the real impact of the plateau environment; the overall method is compatible with system hardware, forming a complete technical solution from data to prediction, improving the practicality and reliability of the method, and providing a standardized implementation path for predicting clean energy power generation on plateau highways.

[0100] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A plateau clean energy power generation amount prediction system based on high altitude characteristics, characterized by, The method comprises the following steps: a multi-source data acquisition module configured to acquire multi-source data; wherein the multi-source data comprises frozen soil freeze-thaw cycle period data, freeze-thaw depth data, ultraviolet radiation intensity data, canyon terrain wind field data, atmospheric pressure data, snow reflectivity data, and geothermal gradient data; a data processing module configured to normalize the multi-source data and calculate frozen soil deformation coefficients, ultraviolet attenuation coefficients, wind field distortion coefficients, air thinning correction coefficients, hot spot attenuation coefficients, foundation settlement coefficients, and fan aerodynamic correction coefficients; a prediction model construction module configured to construct a coupled prediction model containing the frozen soil deformation coefficients, the ultraviolet attenuation coefficients, the wind field distortion coefficients, the air thinning correction coefficients, the hot spot attenuation coefficients, the foundation settlement coefficients, and the fan aerodynamic correction coefficients; a prediction execution module configured to output a high-altitude plateau clean energy power generation prediction value based on high-altitude characteristics based on the coupled prediction model; The coupling prediction model is represented as: wherein P is the predicted total power generation, is the predicted photovoltaic power generation, is the predicted wind power generation; the coupling prediction model comprises a coupling term of the basic settlement coefficient and the normalized air pressure fluctuation value ; is the photovoltaic power under the standard working condition, and t is the power generation time, is the frozen soil deformation coefficient, is the ultraviolet attenuation coefficient, and H is the freezing-thawing depth, is the reference freezing-thawing depth, and R is the snow reflectivity, is the hot spot attenuation coefficient, is the air thinning correction coefficient; the frozen soil deformation coefficient is represented as wherein T is the frozen soil freezing-thawing cycle period; the ultraviolet attenuation coefficient is expressed as is expressed as where P is the atmospheric pressure; the hot spot attenuation coefficient is expressed as where δ is an empirical constant determined based on the influence of local biological activities on the power generation process; P1 is the wind power under standard working conditions, is the wind field distortion coefficient, is the wind turbine aerodynamic correction coefficient, is the normalized air pressure fluctuation value, is the basic deposition coefficient; the wind field distortion coefficient is expressed as where is the wind direction, I is the turbulence intensity; the wind turbine aerodynamic correction coefficient is expressed as where F is the air pressure fluctuation frequency; the basic deposition coefficient is expressed as where G is the normalized geothermal gradient.​ 2. The highland clean energy power generation amount prediction system based on high altitude characteristics according to claim 1, characterized by, the multi-source data acquisition module comprises: a distributed optical fiber sensor configured to acquire the frozen soil freeze-thaw cycle period data and the freeze-thaw depth data; an ultraviolet spectrometer configured to acquire the ultraviolet radiation intensity data; a three-dimensional ultrasonic anemometer configured to acquire the canyon terrain wind field data, which includes wind speed data, wind direction data, and turbulence intensity data; an air pressure sensor configured to acquire the atmospheric pressure data; a spectrometer configured to acquire the snow reflectivity data; a geothermal sensor array configured to acquire the geothermal gradient data. 3.The highland clean energy power generation amount prediction system based on high altitude characteristics according to claim 1, wherein, The data processing module comprises: a first calculation unit configured to calculate the frozen soil deformation coefficients based on the frozen soil freeze-thaw cycle period data and the freeze-thaw depth data, calculate the ultraviolet attenuation coefficients based on the ultraviolet radiation intensity data, and calculate the wind field distortion coefficients based on the wind speed data, the wind direction data, the turbulence intensity data, and the frozen soil deformation coefficients; a second calculation unit configured to calculate the air thinning correction coefficients based on the atmospheric pressure data and the snow reflectivity data, and calculate the hot spot attenuation coefficients based on the air thinning correction coefficients; a third calculation unit configured to calculate the foundation settlement coefficients based on the geothermal gradient data and the atmospheric pressure data, and calculate the fan aerodynamic correction coefficients based on the foundation settlement coefficients and the atmospheric pressure data.

4. The highland clean energy power generation amount prediction system based on high altitude characteristics according to claim 1, characterized by, The prediction model construction module comprises: a photovoltaic prediction unit configured to construct a photovoltaic power generation prediction sub-model containing the frozen soil deformation coefficients, the ultraviolet attenuation coefficients, the air thinning correction coefficients, and the hot spot attenuation coefficients; a wind power prediction unit configured to construct a wind power generation prediction sub-model containing the wind field distortion coefficients, the ultraviolet attenuation coefficients, the foundation settlement coefficients, and the fan aerodynamic correction coefficients; an integration unit configured to integrate the photovoltaic power generation prediction sub-model and the wind power generation prediction sub-model into the coupled prediction model. 5.The highland clean energy power generation amount prediction system based on high altitude characteristics according to claim 1, wherein The method further comprises the following steps: An edge computing node configured to be deployed along a plateau highway, to preprocess the multi-source data and calculate the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air thinning correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the fan aerodynamic correction coefficient; A communication network configured to transmit the data processed by the edge computing node to a cloud server; And a cloud server configured to run the prediction model construction module and the prediction execution module, to generate the plateau clean energy power generation prediction value based on high-altitude characteristics, and to feed back the prediction value to the edge computing node. 6.The highland clean energy power generation amount prediction system based on high altitude characteristics according to claim 5, wherein The edge computing node comprises: A microprocessor configured to execute data preprocessing algorithms and coefficient calculation algorithms; A memory configured to store multi-source data, the preprocessing algorithms, and the coefficient calculation algorithms; An analog-to-digital converter configured to convert the data of the distributed optical fiber sensor, the ultraviolet spectrometer, the three-dimensional ultrasonic anemometer, the air pressure sensor, the spectrometer, and the ground temperature sensor array into a unified vector; A communication interface configured to interact with the cloud server through the communication network; wherein the microprocessor is connected with the analog-to-digital converter through an SPI bus, and the microprocessor transmits data to the cloud server through the communication interface.

7. The plateau clean energy power generation amount prediction method based on high altitude characteristics, applied to the plateau clean energy power generation amount prediction system based on high altitude characteristics according to any one of claims 1 to 6, characterized in that, It comprises: Collecting multi-source data; wherein the multi-source data includes permafrost freeze-thaw cycle data, freeze-thaw depth data, ultraviolet radiation intensity data, canyon terrain wind field data, atmospheric pressure data, snow albedo data, and ground temperature gradient data; Normalizing the multi-source data and calculating the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air thinning correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the fan aerodynamic correction coefficient; Building a coupled prediction model containing the permafrost deformation coefficient, the ultraviolet attenuation coefficient, the wind field distortion coefficient, the air thinning correction coefficient, the hot spot attenuation coefficient, the foundation settlement coefficient, and the fan aerodynamic correction coefficient; Outputting a plateau clean energy power generation prediction value based on high-altitude characteristics based on the coupled prediction model.

Images