Building energy-saving control method based on new energy

Abstract

The embodiment of the invention provides a building energy-saving control method based on new energy, and relates to the field of new energy. A building energy-saving control method based on new energy comprises the steps that multi-source meteorological data including meteorological radar, satellite remote sensing and ground observation are collected, and meanwhile real-time operation data of a wind turbine generator and a solar power generation device are obtained; s2, simulating wind field distribution and transmission of solar radiation in a building group or mountain terrain based on the multi-source meteorological data acquired in the step S1; associating the actual power output of the fan and the photovoltaic array with the meteorological parameters and the simulation result; continuously monitoring real-time data of the power generation system, and comparing the real-time data with the output of the prediction model; according to the method, the utilization rate of new energy is maximized, energy waste is reduced, and the overall performance and the energy-saving effect of building energy management are remarkably improved through intelligent control and optimization means.

Description

Technical Field

[0001] The present invention relates to the field of new energy, and in particular to a building energy-saving control method based on new energy. Background Art

[0002] With the intensification of the global energy crisis and the increasing prominence of environmental pollution, energy conservation and emission reduction have become a major issue of concern to all countries. As an important area of ​​energy consumption, energy consumption management and energy-saving control of buildings are particularly critical. Traditional building energy-saving control methods mainly rely on centralized control systems to manage lighting, air conditioning and other equipment through preset programs and strategies. However, these methods often lack dynamic response to real-time energy demand and supply conditions, resulting in low energy utilization efficiency and difficulty in fully realizing energy-saving potential.

[0003] In recent years, the rapid development of new energy technologies has provided new opportunities for building energy-saving control. Renewable energy such as solar energy and wind energy has gradually been applied to building energy systems due to its clean and sustainable characteristics. However, the intermittent and unstable nature of new energy has brought new challenges to building energy-saving control. At present, historical meteorological data and operating data of new energy power generation devices are used to establish power generation models to predict future energy supply. Existing methods mostly use linear fitting or basic nonlinear models, which have limited prediction accuracy and are difficult to cope with complex and changeable meteorological conditions. Summary of the invention

[0004] According to an embodiment of the present invention, a building energy-saving control method based on new energy is provided to solve the problems raised by the above background technology.

[0005] In a first aspect of the present invention, a building energy-saving control method based on new energy is provided, comprising:

[0006] S1. Collect multi-source meteorological data including meteorological radar, satellite remote sensing and ground observation, and obtain real-time operation data of wind turbines and solar power generation devices.

[0007] S2. Based on the multi-source meteorological data collected in step S1, simulate the wind field distribution and the transmission of solar radiation in the building complex or mountainous terrain;

[0008] S3. Correlate the actual power output of wind turbines and photovoltaic arrays with meteorological parameters and simulation results to establish a multi-task prediction model; train and update the model by continuously collecting new operating and meteorological data to improve the comprehensive prediction accuracy of wind and solar energy output;

[0009] S4. After obtaining the real-time prediction results, dynamically adjust the speed control, blade pitch angle setting and unit yaw angle of the wind turbine to adapt to the possible instantaneous wind direction change or drastic fluctuation of wind speed; for the photovoltaic system, plan the angle of the photovoltaic panel or perform tracking control according to the real-time radiation prediction and shading conditions; if the terrain or buildings cause excessive shading to wind or solar energy, the power loss can be reduced and the stability of power generation can be ensured by adjusting the layout of the wind turbines and formulating a rotation solar panel shade avoidance strategy;

[0010] S5. Continuously monitor the real-time data of the power generation system and compare it with the output of the prediction model; if it is found that the power output of a wind turbine or photovoltaic module deviates significantly from the predicted value, the fault diagnosis or performance evaluation process is automatically started to correct the problem in time by troubleshooting equipment failure, component wear or accidental shading. If the equipment is confirmed to be normal, the model parameters are adaptively corrected.

[0011] Preferably, it further includes data mining of historical fault information of wind turbines and photovoltaic components. When the deviation between the predicted result and the actual output power exceeds a preset threshold, the fault diagnosis module is automatically linked to perform status detection on key components, and the model parameters are corrected or equipment maintenance is triggered based on the detection results.

[0012] Preferably, the S5 step further includes: systematically analyzing the deviation between the actual output power and the predicted power, identifying and recording abnormal modes in the operation of the wind turbine; based on the identified abnormal modes, dynamically adjusting the parameter settings of the wind power generation model, and optimizing the prediction algorithm to improve the accuracy of future power predictions and the overall operational stability of the system.

[0013] Preferably, the S5 step further includes: establishing a multi-level evaluation system to comprehensively evaluate the implementation effect of the energy allocation plan, including multiple dimensions such as energy utilization efficiency, energy-saving effect, system stability and user satisfaction; weighting and comprehensively scoring each evaluation indicator to form an overall evaluation result of the energy allocation plan; based on the overall evaluation result, identifying the deficiencies in the energy allocation plan, and formulating targeted optimization measures, such as adjusting the energy allocation priority, optimizing the energy conversion path or improving the energy storage strategy, so as to continuously improve the overall performance and energy-saving effect of the control method.

[0014] Preferably, step S2 further includes subdividing the collected energy consumption data and new energy generation data according to time periods and spatial regions to identify energy usage patterns and new energy supply fluctuations in different times and regions;

[0015] Trend and correlation analysis is performed on the segmented data to determine the dynamic relationship between energy consumption and new energy generation, thereby optimizing the construction of energy consumption and supply models.

[0016] Preferably, the S3 step further includes: conducting a time series comparative analysis of historical meteorological data and energy demand data to identify the impact of meteorological changes on energy demand; constructing a multivariate prediction model to comprehensively consider the comprehensive impact of meteorological factors such as temperature, humidity, and light intensity on future energy supply and demand, so as to improve the accuracy and reliability of the prediction.

[0017] Preferably, the S4 step further comprises:

[0018] According to the priority of energy dispatch strategy, different types of new energy resources are allocated in sequence to ensure that the energy needs of key loads are met first;

[0019] Dynamically adjust the energy allocation ratio of each functional area to achieve energy balance and optimal configuration among regions based on real-time environmental parameters and energy supply conditions;

[0020] The energy scheduling plan is adjusted and optimized in multiple rounds to gradually approach the optimal energy-saving effect of the overall system.

[0021] Preferably, the collected energy consumption data and new energy generation data are subjected to time series segmentation processing to divide the data into multiple time periods with similar energy usage patterns and generation characteristics;

[0022] In each time period, the key factors that significantly affect energy consumption and new energy generation are identified and extracted, and the variables that have a significant impact on the energy consumption and supply model are screened out; based on the extracted key factors, the energy consumption and supply data are normalized to eliminate the interference of different dimensions and data ranges on subsequent modeling, ensuring the stability and accuracy of the model; time periods with similar energy consumption and supply characteristics are classified to provide a structured data basis for the construction of a dynamic energy consumption and supply model; in each type of time period, targeted energy consumption and supply relationship models are established to reflect the dynamic correlation between energy consumption and new energy generation in different time periods.

[0023] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0024] The energy-saving control method for buildings based on new energy provided by the present invention can accurately simulate the distribution of wind energy and solar energy in different terrains and time periods through the efficient collection and meticulous processing of multi-source meteorological data, combined with fluid mechanics and light radiation coupling simulation, so as to construct a highly accurate multi-task prediction model. This model comprehensively considers various meteorological factors such as temperature, humidity, and light intensity, and accurately predicts future energy supply and demand, significantly improving the accuracy of power prediction and the operational stability of the system. At the same time, the method comprehensively evaluates and optimizes the energy allocation scheme by establishing a multi-level evaluation system and using fuzzy logic or hierarchical analysis, thereby achieving multi-objective comprehensive optimization of energy utilization efficiency, energy-saving effect, system stability and user satisfaction. In addition, the continuous fault diagnosis and adaptive optimization mechanism enable the system to identify and adjust abnormal modes in real time, dynamically optimize the parameters of the power generation model, and ensure that the system remains efficient and reliable under complex and changeable environmental conditions. In summary, it has broad application prospects and significant technical advantages.

[0025] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention is described clearly and completely below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0028] The energy-saving control method for buildings based on new energy described in the present invention involves multiple links such as multi-source meteorological data collection, wind and solar power generation model construction, energy output prediction, dynamic energy scheduling control, and system adaptive optimization. The entire system mainly includes the following parts:

[0029] Multi-source meteorological data acquisition module: responsible for collecting multi-source meteorological data including meteorological radar, satellite remote sensing and ground observation. New energy power generation device monitoring module: real-time acquisition of wind turbine and solar power generation device operation data. Data preprocessing module: unified format, noise elimination and missing data supplement for the collected multi-source data. Fluid mechanics and light radiation coupling simulation module: simulates the wind field distribution and the transmission of solar radiation in a specific terrain. Multi-task prediction model construction module: based on actual operation data and simulation results, establishes a prediction model for wind and solar energy output. Dynamic energy scheduling control module: according to the prediction results, real-time adjustment of the operating parameters of wind turbines and photovoltaic systems. Fault diagnosis and adaptive optimization module: continuously monitors the system operation status, performs fault diagnosis and optimizes the prediction model.

[0030] The present invention provides a building energy-saving control method based on new energy, comprising:

[0031] S1. Collect multi-source meteorological data including meteorological radar, satellite remote sensing and ground observation, covering wind direction, wind speed, temperature, air pressure, humidity and solar radiation distribution; at the same time, obtain real-time operation data of wind turbines and solar power generation devices, including rotor speed, blade angle, photovoltaic panel inclination, power generation, etc. Unify the format and remove noise of data from different sources, and interpolate and supplement missing data. Furthermore, through meteorological radar, satellite remote sensing and ground observation stations, collect multi-dimensional meteorological data including wind direction, wind speed, temperature, air pressure, humidity and solar radiation distribution. Obtain real-time operation data from wind turbines and solar power generation devices, such as rotor speed, blade angle, photovoltaic panel inclination and current power generation.

[0032] Convert data from different sources into a unified data format for subsequent processing and analysis. Use filtering algorithms (such as Kalman filtering, moving average filtering, etc.) to remove noise from the data and improve data quality. Use interpolation algorithms (such as linear interpolation, polynomial interpolation, etc.) to supplement missing data to ensure data integrity. Synchronize data from different sources according to timestamps to ensure data consistency in the time dimension.

[0033] S2. Based on the multi-source meteorological data collected in step S1, the fluid mechanics and light radiation coupling simulation method is used to simulate the wind field distribution and the transmission of solar radiation in the building complex or mountainous terrain; in this process, terrain factors, eddy effects and complex shading (such as partial shading of solar energy by adjacent wind turbine towers and surrounding buildings) and other influencing factors are introduced to obtain the theoretical distribution of wind energy and solar energy in different spatial locations and time periods.

[0034] Furthermore, the fluid mechanics model is used to simulate the distribution and changes of wind fields in building complexes or mountainous terrain, taking into account the impact of topography on wind flow, such as eddy effects, wind speed attenuation, etc. The radiation transmission model is used to simulate the distribution of solar radiation in different spatial locations and time periods, taking into account factors such as terrain shielding and building shading.

[0035] Topographic factors: including the impact of surface roughness, ups and downs, etc. on wind field and solar radiation.

[0036] Eddy effect: the impact of eddies formed around complex terrain or buildings on wind speed and direction.

[0037] Shielding factors: The interference of adjacent wind turbine towers on wind flow and the partial shading of solar power generation devices by surrounding buildings lead to changes in solar radiation intensity.

[0038] S3. The actual power output of wind turbines and photovoltaic arrays is associated with meteorological parameters and simulation results to establish a multi-task prediction model; this model can not only predict the power output of each wind turbine in real time under different blade angles, wind directions and wind speeds, but also estimate the power generation efficiency of photovoltaic modules under different inclination angles, light intensities and shading conditions. By continuously collecting new operating and meteorological data to train and update the model, the comprehensive prediction accuracy of wind and solar energy output can be improved.

[0039] Furthermore, the actual power output of wind turbines and photovoltaic arrays is correlated with the collected meteorological parameters and simulation results.

[0040] A multi-task learning method is used to establish a comprehensive model that can simultaneously predict the power output of wind turbines and the power generation efficiency of photovoltaic modules.

[0041] Select deep learning algorithms suitable for processing multi-source and multi-task data, such as multi-task neural networks, ensemble learning methods, etc. Use historical operating data and meteorological data to build a training data set, including input features (wind direction, wind speed, temperature, air pressure, humidity, solar radiation, etc.) and output targets (wind turbine power, photovoltaic power generation efficiency). Use an independent test data set to verify the generalization ability of the model and ensure the adaptability of the model in different environments.

[0042] S4. After obtaining the real-time prediction results, the wind turbine speed control, blade pitch angle setting and unit yaw angle are dynamically adjusted to adapt to possible instantaneous wind direction changes or drastic fluctuations in wind speed. For the photovoltaic system, the photovoltaic panel angle is planned or tracking control is performed according to the real-time radiation prediction and shading conditions. If the terrain or buildings cause excessive shading to wind or solar energy, the power loss can be reduced and the power generation stability can be ensured by adjusting the wind turbine layout and formulating a rotating solar panel shade avoidance strategy. All strategy adjustments are completed based on the deviation between the predicted value and the actual output power, and can be comprehensively evaluated and corrected in combination with multi-objective optimization requirements such as scheduling cost and equipment life.

[0043] Using the constructed multi-task prediction model, the power output prediction values ​​of each wind turbine under different blade angles, wind directions and wind speeds, as well as the power generation efficiency prediction values ​​of photovoltaic modules under different inclination angles, light intensities and shading conditions are obtained in real time. According to the instantaneous wind speed changes, the rotor speed of the wind turbine is dynamically adjusted to optimize the power generation efficiency. According to the predicted wind speed and wind direction, the pitch angle of the blade is adjusted to reduce wind energy waste and prevent overload. According to the wind direction changes, the yaw angle of the wind turbine is adjusted in real time so that the wind turbine is always facing the wind source direction to maximize wind energy capture. According to the real-time solar radiation prediction and shading conditions, the inclination angle of the photovoltaic panel is adjusted to obtain the maximum solar radiation. Implement dynamic tracking control of photovoltaic panels to ensure that the photovoltaic panels are always at the optimal radiation angle to improve power generation efficiency. If the terrain or buildings cause excessive shading to wind energy, the layout position of the wind turbine can be dynamically adjusted to optimize wind energy capture. Formulate a rotating solar panel shade avoidance strategy to reduce the shading effect of neighboring buildings or other obstacles on solar energy by regularly adjusting the layout of photovoltaic panels. Compare the predicted power value with the actual output power to evaluate the effectiveness of the energy scheduling strategy. Combined with multi-objective optimization requirements such as scheduling cost and equipment life, the energy scheduling strategy is comprehensively evaluated and adjusted. Based on the evaluation results, the energy allocation priority is optimized, the energy conversion path is adjusted, or the energy storage strategy is improved to achieve the best energy-saving effect.

[0044] S5. Continuously monitor the real-time data of the power generation system and compare it with the output of the prediction model; if it is found that the power output of a wind turbine or photovoltaic module deviates significantly from the predicted value, the fault diagnosis or performance evaluation process is automatically started to correct the problem in time by troubleshooting equipment failure, component wear or accidental shading. If the equipment is confirmed to be normal, the model parameters are adaptively corrected to make subsequent predictions more accurate. Through this iterative learning and optimization mechanism, the comprehensive utilization efficiency of wind and solar energy and the stability of the system are continuously improved.

[0045] Continuously monitor the real-time operating data of the power generation system and compare it with the output of the prediction model. Detect the deviation between the power output and the predicted value by setting the threshold. If the power output of a wind turbine or photovoltaic module deviates significantly from the predicted value, automatically start the fault diagnosis or performance evaluation process. Through sensor data analysis, equipment status detection and other means, check possible causes such as equipment failure, component wear or accidental shading. Correct the detected problems in time and restore the normal operation of the equipment. If the equipment is confirmed to be normal, but there is still a deviation in the prediction model, the model parameters are adaptively corrected. Adjust the model parameters through the optimization algorithm to improve the accuracy of subsequent predictions.

[0046] Data mining is performed on historical fault information of wind turbines and photovoltaic modules to analyze the correlation between fault modes and operating parameters.

[0047] Abnormal detection: When the deviation between the predicted result and the actual output power exceeds the preset threshold, the fault diagnosis module is automatically linked to perform status detection on key components.

[0048] Maintenance trigger: Based on the detection results, the model parameters are modified or equipment maintenance is triggered to ensure the stable operation of the power generation system.

[0049] It further includes data mining of historical fault information of wind turbines and photovoltaic modules. When the deviation between the predicted result and the actual output power exceeds a preset threshold, the fault diagnosis module is automatically linked to perform status detection on key components, and the model parameters are corrected or equipment maintenance is triggered based on the detection results.

[0050] By collecting multi-source meteorological data and new energy power generation device data, and processing them in a unified format and removing noise, the accuracy and integrity of the data are ensured. Through fluid mechanics and light radiation coupling simulation, combined with actual operation data, accurate wind and solar power generation models are established to improve the accuracy of energy output prediction. According to real-time prediction results, the operating parameters of wind turbines and photovoltaic systems are dynamically adjusted to optimize energy distribution, maximize the utilization of new energy, and reduce energy waste. Through fault diagnosis and adaptive learning mechanisms, the prediction model and control strategy are continuously optimized to improve the stability and energy-saving effect of the system and adapt to complex and changing operating environments.

[0051] In this embodiment, the S5 step further includes: systematically analyzing the deviation between the actual output power and the predicted power, using advanced data processing technology and machine learning algorithms to deeply explore the abnormal modes in the operation of wind turbines, and recording in detail the frequency of occurrence, duration and specific impact of these abnormal modes on power generation efficiency. Based on the identified abnormal modes, the method optimizes the weight and structure of the prediction algorithm by real-time monitoring and dynamically adjusting the key parameter settings of the wind power generation model, such as wind speed response sensitivity, blade angle adjustment range and yaw control strategy, thereby significantly improving the accuracy of future power predictions. At the same time, the system continuously monitors and evaluates the performance of the adjusted model by introducing an adaptive feedback mechanism to ensure that the entire power generation system can maintain a high degree of operational stability and reliability under complex and changeable wind conditions.

[0052] In this embodiment, the S5 step further includes: establishing a multi-level evaluation system to conduct a comprehensive and detailed comprehensive evaluation of the implementation effect of the energy allocation plan. The evaluation system covers multiple key dimensions, including but not limited to the degree of improvement in energy utilization efficiency, the manifestation of energy-saving effects, the stability of system operation, and the satisfaction of end users. By applying fuzzy logic or hierarchical analysis, the method scientifically assigns weights and comprehensively scores each evaluation index, and finally forms an overall evaluation result of the energy allocation plan. Based on this overall evaluation result, the method can accurately identify the deficiencies in the energy allocation plan and formulate corresponding targeted optimization measures. These optimization measures may involve dynamically adjusting the priority of energy allocation, optimizing the path design of energy conversion, or improving the strategic configuration of energy storage, aiming to continuously improve the overall performance and energy-saving effect of the control method, and ensure that the system always maintains the best energy management state under different operating environments.

[0053] In this embodiment, the collected energy consumption data and new energy generation data are subdivided and processed according to different time periods and spatial regions to deeply identify the energy use patterns and fluctuations in new energy supply in different times and regions. Through this subdivision, the method can accurately capture the spatiotemporal dynamic characteristics of energy demand and supply, such as the growth of energy demand during peak hours and the shortage of new energy supply in specific areas. Subsequently, advanced statistical analysis methods, including time series analysis, regression analysis, and correlation analysis, are applied to conduct in-depth trend analysis and correlation analysis on the subdivided data to comprehensively determine the dynamic relationship between energy consumption and new energy generation. This analysis not only reveals the spatiotemporal correlation between energy demand and supply, but also provides a solid data foundation and theoretical support for the construction of an energy consumption and supply optimization model, ensuring that the model can accurately reflect the actual energy use and supply conditions, thereby achieving more efficient and intelligent energy management.

[0054] In this embodiment, the S5 step further includes: systematically analyzing the deviation between the actual output power and the predicted power, using advanced data processing technology and machine learning algorithms to deeply explore the abnormal modes in the operation of wind turbines, and recording in detail the frequency of occurrence, duration and specific impact of these abnormal modes on power generation efficiency. Based on the identified abnormal modes, the method optimizes the weight and structure of the prediction algorithm by real-time monitoring and dynamically adjusting the key parameter settings of the wind power generation model, such as wind speed response sensitivity, blade angle adjustment range and yaw control strategy, thereby significantly improving the accuracy of future power predictions. At the same time, the system continuously monitors and evaluates the performance of the adjusted model by introducing an adaptive feedback mechanism to ensure that the entire power generation system can maintain a high degree of operational stability and reliability under complex and changeable wind conditions.

[0055] In this embodiment, the S5 step further includes: establishing a multi-level evaluation system to conduct a comprehensive and detailed comprehensive evaluation of the implementation effect of the energy allocation plan. The evaluation system covers multiple key dimensions, including but not limited to the degree of improvement in energy utilization efficiency, the manifestation of energy-saving effects, the stability of system operation, and the satisfaction of end users. By applying fuzzy logic or hierarchical analysis, the method scientifically assigns weights and comprehensively scores each evaluation index, and finally forms an overall evaluation result of the energy allocation plan. Based on this overall evaluation result, the method can accurately identify the deficiencies in the energy allocation plan and formulate corresponding targeted optimization measures. These optimization measures may involve dynamically adjusting the priority of energy allocation, optimizing the path design of energy conversion, or improving the strategic configuration of energy storage, aiming to continuously improve the overall performance and energy-saving effect of the control method, and ensure that the system always maintains the best energy management state under different operating environments.

[0056] In this embodiment, the collected energy consumption data and new energy generation data are subdivided and processed according to different time periods and spatial regions to deeply identify the energy use patterns and fluctuations in new energy supply in different times and regions. Through this subdivision, the method can accurately capture the spatiotemporal dynamic characteristics of energy demand and supply, such as the growth of energy demand during peak hours and the shortage of new energy supply in specific areas. Subsequently, advanced statistical analysis methods, including time series analysis, regression analysis, and correlation analysis, are applied to conduct in-depth trend analysis and correlation analysis on the subdivided data to comprehensively determine the dynamic relationship between energy consumption and new energy generation. This analysis not only reveals the spatiotemporal correlation between energy demand and supply, but also provides a solid data foundation and theoretical support for the construction of an energy consumption and supply optimization model, ensuring that the model can accurately reflect the actual energy use and supply conditions, thereby achieving more efficient and intelligent energy management.

[0057] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A building energy-saving control method based on new energy, characterized in that: include: S1. Collect multi-source meteorological data including meteorological radar, satellite remote sensing and ground observation, and obtain real-time operation data of wind turbines and solar power generation devices. S2. Based on the multi-source meteorological data collected in step S1, simulate the wind field distribution and the transmission of solar radiation in the building complex or mountainous terrain; S3. Correlate the actual power output of wind turbines and photovoltaic arrays with meteorological parameters and simulation results to establish a multi-task prediction model; train and update the model by continuously collecting new operating and meteorological data to improve the comprehensive prediction accuracy of wind and solar energy output; S4. After obtaining the real-time prediction results, dynamically adjust the speed control, blade pitch angle setting and unit yaw angle of the wind turbine to adapt to the possible instantaneous wind direction change or drastic fluctuation of wind speed; for the photovoltaic system, plan the angle of the photovoltaic panel or perform tracking control according to the real-time radiation prediction and shading conditions; if the terrain or buildings cause excessive shading to wind or solar energy, the power loss can be reduced and the stability of power generation can be ensured by adjusting the layout of the wind turbines and formulating a rotation solar panel shade avoidance strategy; S5. Continuously monitor the real-time data of the power generation system and compare it with the output of the prediction model; If the power output of a wind turbine or photovoltaic module is found to be significantly different from the predicted value, the fault diagnosis or performance evaluation process is automatically started to correct the problem in a timely manner by troubleshooting equipment failure, component wear or accidental shading. If the equipment is confirmed to be normal, the model parameters are adaptively corrected.

2. The building energy-saving control method based on new energy according to claim 1 is characterized in that: It further includes data mining of historical fault information of wind turbines and photovoltaic modules. When the deviation between the predicted result and the actual output power exceeds a preset threshold, the fault diagnosis module is automatically linked to perform status detection on key components, and the model parameters are corrected or equipment maintenance is triggered based on the detection results.

3. The building energy-saving control method based on new energy according to claim 1 is characterized in that: The S5 step further includes: systematically analyzing the deviation between the actual output power and the predicted power, identifying and recording abnormal modes in the operation of the wind turbine; based on the identified abnormal modes, dynamically adjusting the parameter settings of the wind power generation model, and optimizing the prediction algorithm to improve the accuracy of future power predictions and the overall operational stability of the system.

4. The building energy-saving control method based on new energy according to claim 1 is characterized in that: The S5 step further includes: establishing a multi-level evaluation system to comprehensively evaluate the implementation effect of the energy allocation plan, including multiple dimensions such as energy utilization efficiency, energy-saving effect, system stability and user satisfaction; weighting and comprehensively scoring each evaluation indicator to form an overall evaluation result of the energy allocation plan; based on the overall evaluation result, identifying the deficiencies in the energy allocation plan and formulating targeted optimization measures, such as adjusting the energy allocation priority, optimizing the energy conversion path or improving the energy storage strategy, so as to continuously improve the overall performance and energy-saving effect of the control method.

5. The building energy-saving control method based on new energy according to claim 1 is characterized in that: The step S2 further includes segmenting the collected energy consumption data and new energy generation data according to time periods and spatial regions to identify energy usage patterns and new energy supply fluctuations in different times and regions; Trend and correlation analysis is performed on the segmented data to determine the dynamic relationship between energy consumption and new energy generation, thereby optimizing the construction of energy consumption and supply models.

6. The building energy-saving control method based on new energy according to claim 1 is characterized in that: The S3 step further includes: conducting a time series comparative analysis of historical meteorological data and energy demand data to identify the impact of meteorological changes on energy demand; constructing a multivariate prediction model to comprehensively consider the comprehensive impact of meteorological factors such as temperature, humidity, and light intensity on future energy supply and demand, thereby improving the accuracy and reliability of the prediction.

7. The building energy-saving control method based on new energy according to claim 1 is characterized in that: The S4 step further comprises: According to the priority of energy dispatch strategy, different types of new energy resources are allocated in sequence to ensure that the energy needs of key loads are met first; Dynamically adjust the energy allocation ratio of each functional area to achieve energy balance and optimal configuration among regions based on real-time environmental parameters and energy supply conditions; The energy scheduling plan is adjusted and optimized in multiple rounds to gradually approach the optimal energy-saving effect of the overall system.

8. The building energy-saving control method based on new energy according to claim 1 is characterized in that: Perform time series segmentation processing on the collected energy consumption data and new energy generation data, dividing the data into multiple time periods with similar energy usage patterns and generation characteristics; In each time period, the key factors that significantly affect energy consumption and new energy generation are identified and extracted, and the variables that have a significant impact on the energy consumption and supply model are screened out; based on the extracted key factors, the energy consumption and supply data are normalized to eliminate the interference of different dimensions and data ranges on subsequent modeling, ensuring the stability and accuracy of the model; time periods with similar energy consumption and supply characteristics are classified to provide a structured data basis for the construction of a dynamic energy consumption and supply model; in each type of time period, targeted energy consumption and supply relationship models are established to reflect the dynamic correlation between energy consumption and new energy generation in different time periods.