Multi-time scale clean energy complementary characteristic analysis and utilization method and system

Abstract

The invention relates to the technical field of smart power grid and energy management, and discloses a multi-time scale clean energy complementary characteristic analysis and utilization method and system, and the method comprises the steps: collecting the historical output data and meteorological information of clean energy; analyzing historical output data and meteorological information by using a machine learning algorithm, and predicting output characteristics of the clean energy at different time scales; based on a prediction result, designing an optimal scheduling strategy, and improving the utilization efficiency of clean energy; and implementing an optimal scheduling strategy, dynamically adjusting the output of the renewable energy and the conventional power supply, and monitoring the system performance and the energy output change in real time in the implementation process. According to the method, by optimizing resource allocation in practice, efficient utilization of clean energy is achieved, and good economic benefits and environmental benefits are shown. By means of the innovative measures, the technical progress in the field of clean energy is promoted, and the sustainable development aim is achieved.

Description

Technical Field

[0001] The present invention relates to the field of smart grid and energy management technology, and in particular to a method and system for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales. Background Art

[0002] As the world continues to pay more attention to renewable energy, clean energy technology has developed rapidly. The application of clean energy such as wind energy, solar energy, and tidal energy has become the main source of energy in many countries and regions. In order to cope with the problem of imbalance between energy supply and demand, academia and industry have conducted in-depth research on clean energy output forecasting and scheduling optimization technology at multiple time scales. At present, a variety of data-driven methods are applied to the forecasting and management of clean energy. For example, traditional regression models and time series analysis methods provide a preliminary theoretical framework for short-term forecasting of clean energy. At the same time, the introduction of deep learning technology in recent years has greatly improved the forecasting accuracy and speed. Combined with the analysis of meteorological information and historical output data, machine learning algorithms show good prospects in improving forecasting accuracy, paving the way for the effective use of clean energy.

[0003] However, existing technologies still have shortcomings in dealing with the temporal variation characteristics of clean energy and climate diversity. On the one hand, existing prediction models usually only focus on the prediction of output characteristics at a single time scale, lack comprehensive consideration of different time scales, and fail to effectively capture the instantaneous changes and long-term trends of clean energy output. On the other hand, the optimization scheduling strategy often lacks flexibility in real-time adjustment and dynamic balance of renewable energy and traditional power output, and it is difficult to adapt to rapidly changing load demands and sudden climate events. In addition, current scheduling strategies usually fail to make full use of advanced data processing and intelligent algorithms, resulting in widespread energy loss and waste of resources. Therefore, although existing technologies have made certain progress, innovative solutions are still urgently needed in the analysis of the complementary characteristics and comprehensive utilization of clean energy. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales, including: collecting historical output data and meteorological information of clean energy; using a machine learning algorithm to analyze the historical output data and meteorological information, and predicting the output characteristics of clean energy at different time scales; based on the prediction results, designing an optimized scheduling strategy to improve the utilization efficiency of clean energy; implementing the optimized scheduling strategy to dynamically adjust the output of renewable energy and conventional power sources, and monitoring system performance and energy output changes in real time during the implementation process.

[0007] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, wherein: the meteorological information, the wind speed information at a specific location, including the average wind speed and the instantaneous wind speed, the collected wind speed data is subjected to time series analysis, outliers are eliminated, and the data is smoothed by a sliding average method to obtain a stable wind speed pattern;

[0008] Use ground radiation monitoring instruments to obtain the solar radiation energy reaching the surface per unit time, normalize the data at different time scales, and use radiation distribution models to analyze the impact of sunshine time and meteorological conditions on solar energy output;

[0009] Record air temperatures at specific locations, cross-validate air temperature data with other meteorological data, and use seasonal adjustment models to eliminate the effects of seasonal changes;

[0010] The height, frequency and periodic changes of tides are recorded, the tidal data are subjected to Fourier transform analysis, the periodic change characteristics are identified, and correlation analysis is performed with other meteorological variables to evaluate the impact of tidal changes on ocean energy output.

[0011] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, the machine learning algorithm analysis includes processing historical data and meteorological information, extracting output characteristics and providing accurate predictions at multiple time scales;

[0012] An improved multivariate linear regression model is used, combined with regularization to prevent overfitting:

[0013]

[0014] Among them, Y i represents the clean energy output of the i-th sample, β0 is the intercept term, p is the total number of features, β j represents the regression coefficient of the jth feature, X ij represents the value of the jth feature in the i-th sample, λ is the regularization parameter, β k represents the absolute value of the kth regression coefficient;

[0015] During the training process, the initial regression coefficient β j will be set to random values ​​and optimized iteratively, using the trained model to extract estimates of clean energy output from the feature set:

[0016]

[0017] in, is the output feature; all input features X ij and the corresponding regression coefficient β j The model weights are linearly combined to output the prediction results for each sample.

[0018] For each sample, calculate the residual R of the force feature i , used for subsequent model analysis:

[0019]

[0020] Residual R i It is the difference between the actual output and the predicted output. By analyzing the residuals, we can determine the degree of fit of the model and evaluate the features that have a great impact on the prediction effect.

[0021] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, the prediction of output characteristics at different time scales includes evaluating model performance using cross-validation, adjusting regularization parameters to obtain the best effect, and evaluating model prediction accuracy using root mean square error and determination coefficient;

[0022] The model is used to expand the feature vector combined with the time factor, build an improved time series regression model, and perform multi-time scale prediction:

[0023]

[0024] Among them, Y t For the time T t The predicted value of clean energy output at the time of tj For the time T t is the input feature, and γ is the weight coefficient of the time factor.

[0025] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, the optimization scheduling strategy includes setting an objective function to maximize the proportion of clean energy use and introducing additional constraints to ensure the stability and reliability of the system;

[0026] The objective function F is set to optimize the scheduling strategy, expressed as:

[0027]

[0028] Among them, α, β, γ are weight coefficients, T is the number of time steps in the scheduling cycle, and E re (t) is the renewable energy power generation at time t, C total is the total generation cost in the dispatch period, S is the indicator of stability constraint;

[0029] During the optimization process, constraints are introduced to ensure the rationality and feasibility of the scheduling plan. The constraints include load matching constraints, power generation capacity constraints, and clean energy proportion constraints.

[0030] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, the dynamic adjustment includes: when the combined output of wind power and photovoltaic power generation reaches or exceeds 70% of the total power demand, the proportion of power supply from renewable energy is increased first, and the implementation measures are to increase the power generation output of solar energy and wind energy; reduce the load of traditional power sources, and ensure that power generation is stopped only when it is not less than 30% of the actual demand;

[0031] When the grid frequency fluctuates by more than ±0.5Hz, fast response regulation is implemented. The implementation measures include enabling the fast response layer interface to immediately adjust the wind turbine speed or photovoltaic power; starting the backup gas generator to quickly fill the insufficient power;

[0032] In response to seasonal changes, when the electricity demand index exceeds the preset threshold for five consecutive days, the implementation measures are to increase the charging speed of the energy storage system to store excess energy in a timely manner; reduce the output of renewable energy during high-demand periods to delay the depletion of energy storage facilities;

[0033] A cost-benefit ratio is set. When the unit cost of renewable energy power generation increases by more than 10%, a review is triggered. The implementation measures are to analyze the operating costs of renewable energy to determine whether it is necessary to adjust the power generation strategy or replace equipment; at the same time, evaluate the user's willingness to pay to seek economic optimization.

[0034] As a preferred solution of the method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales described in the present invention, the real-time monitoring of system performance and energy output changes includes integrating the collected data sources with the management system through a unified communication protocol, compressing the data in the data capture stage to reduce network bandwidth requirements, deploying edge computing capabilities on near-source devices, performing preliminary data analysis and processing, and reducing delays;

[0035] The processed data is uploaded to the central server for regular updates, which are divided into short-term, medium-term and long-term. The data update strategy in each cycle is different. In the short term, it focuses on rapid response, and in the medium term, it focuses on reasonable scheduling plans. Based on monitoring data and analysis results, the output distribution of renewable energy and conventional power sources is adjusted in real time. A rule-based response mechanism is used to optimize energy distribution, and dynamic information feedback is provided on user terminal devices, including real-time power consumption, current energy utilization, and future forecast information.

[0036] As a preferred solution of the multi-time scale clean energy complementary characteristic analysis and utilization system described in the present invention, it includes: a data collection module, a feature extraction and modeling module, an optimization scheduling strategy module, a real-time monitoring and feedback module, and a decision support and optimization module;

[0037] The data collection module is responsible for collecting historical data and real-time meteorological information related to clean energy output;

[0038] The feature extraction and modeling module processes the collected historical data and meteorological information, uses an improved multivariate linear regression model to extract features and predict output characteristics at multiple time scales;

[0039] The optimization scheduling strategy module designs and implements the optimization scheduling strategy according to the output of the feature extraction and modeling module to improve the utilization efficiency of clean energy;

[0040] The real-time monitoring and feedback module is responsible for real-time monitoring of the overall system performance and energy output changes, including the collection and analysis of key indicators of grid frequency, power demand and energy output;

[0041] The decision support and optimization module combines various data analysis results to support managers' decision-making; by setting cost-benefit ratios, it evaluates the operating costs of renewable energy and users' willingness to pay, provides economic optimization suggestions, helps optimize power generation strategies and equipment selection, and ensures the economic sustainability of the system.

[0042] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales are implemented.

[0043] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales are implemented.

[0044] Beneficial effects of the present invention: This method integrates meteorological information and historical output data, uses advanced machine learning algorithms, conducts multi-dimensional analysis and modeling, and comprehensively improves the understanding of clean energy output characteristics. By constructing an improved multivariate linear regression model and combining it with regularization technology, the overfitting phenomenon of the model is effectively curbed, and more accurate multi-time scale predictions are provided. In addition, the designed optimization scheduling strategy takes into account real-time monitoring data when dynamically adjusting the output of renewable energy and traditional power sources, so that the system can still maintain high stability and reliability when facing uncertainty and external interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0046] Figure 1 A schematic flow chart of a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to an embodiment of the present invention.

[0047] Figure 2 A schematic diagram of the working modules of a multi-time-scale clean energy complementary characteristics analysis and utilization system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0052] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales, including:

[0055] S1: Collect historical output data and meteorological information of clean energy.

[0056] Furthermore, the meteorological information, wind speed information at a specific location, including average wind speed and instantaneous wind speed, performs time series analysis on the collected wind speed data, eliminates outliers, and smoothes the data by a sliding average method to obtain a stable wind speed pattern;

[0057] Use ground radiation monitoring instruments to obtain the solar radiation energy reaching the surface per unit time, normalize the data at different time scales, and use radiation distribution models to analyze the impact of sunshine time and meteorological conditions on solar energy output;

[0058] Record air temperatures at specific locations, cross-validate air temperature data with other meteorological data, and use seasonal adjustment models to eliminate the effects of seasonal changes;

[0059] The height, frequency and periodic changes of tides are recorded, the tidal data are subjected to Fourier transform analysis, the periodic change characteristics are identified, and correlation analysis is performed with other meteorological variables to evaluate the impact of tidal changes on ocean energy output.

[0060] S2: Use machine learning algorithms to analyze historical output data and meteorological information to predict the output characteristics of clean energy at different time scales.

[0061] Furthermore, historical data and meteorological information are processed to extract output characteristics and provide accurate forecasts at multiple time scales;

[0062] An improved multivariate linear regression model is used, combined with regularization to prevent overfitting:

[0063]

[0064] Among them, Y i represents the clean energy output of the i-th sample, β0 is the intercept term, p is the total number of features, β j represents the regression coefficient of the jth feature, X ij represents the value of the jth feature in the i-th sample, λ is the regularization parameter, β k represents the absolute value of the kth regression coefficient;

[0065] During the training process, the initial regression coefficient β j will be set to random values ​​and optimized iteratively, using the trained model to extract estimates of clean energy output from the feature set:

[0066]

[0067] in, is the output feature; all input features X ij and the corresponding regression coefficient β j The model weights are linearly combined to output the prediction results for each sample.

[0068] For each sample, calculate the residual R of the force feature i , used for subsequent model analysis:

[0069]

[0070] Residual R i It is the difference between the actual output and the predicted output. By analyzing the residuals, we can determine the degree of fit of the model and evaluate the features that have a great impact on the prediction effect.

[0071] It should be noted that cross-validation was used to evaluate the model performance, the regularization parameters were adjusted to obtain the best results, and the root mean square error and determination coefficient were used to evaluate the model prediction accuracy;

[0072] The model is used to expand the feature vector combined with the time factor, build an improved time series regression model, and perform multi-time scale prediction:

[0073]

[0074] Among them, Y t For the time T t The predicted value of clean energy output at the time of tj For the time T t is the input feature, and γ is the weight coefficient of the time factor.

[0075] S3: Based on the prediction results, design an optimized scheduling strategy to improve the efficiency of clean energy utilization.

[0076] Furthermore, the objective function is set to maximize the proportion of clean energy use, and additional constraints are introduced to ensure the stability and reliability of the system;

[0077] The objective function F is set to optimize the scheduling strategy, expressed as:

[0078]

[0079] Among them, α, β, γ are weight coefficients, T is the number of time steps in the scheduling cycle, and E re (t) is the renewable energy power generation at time t, C total is the total generation cost in the dispatch period, S is the indicator of stability constraint;

[0080] During the optimization process, constraints are introduced to ensure the rationality and feasibility of the scheduling plan. The constraints include load matching constraints, power generation capacity constraints, and clean energy proportion constraints.

[0081] It should be noted that the load matching constraints are:

[0082]

[0083] This constraint ensures that the total power generation can meet the demand load L(t) at each time t;

[0084] Power generation capacity constraints:

[0085]

[0086] Ensure that the power generation of renewable energy and traditional energy does not exceed their respective maximum power generation capacity.

[0087] Clean energy ratio constraints:

[0088]

[0089] This constraint requires that at each moment, the proportion of clean energy must not be less than the minimum requirement P min .

[0090] S4: Implement optimized dispatching strategies, dynamically adjust the output of renewable energy and conventional power sources, and monitor system performance and energy output changes in real time during the implementation process.

[0091] Furthermore, when the combined output of wind and photovoltaic power generation reaches or exceeds 70% of the total electricity demand, the proportion of renewable energy power supply will be increased first, and the implementation measures are to increase the output of solar and wind power generation; reduce the load of traditional power sources, and ensure that power generation is not stopped until it is no less than 30% of the actual demand;

[0092] When the grid frequency fluctuates by more than ±0.5Hz, fast response regulation is implemented. The implementation measures include enabling the fast response layer interface to immediately adjust the wind turbine speed or photovoltaic power; starting the backup gas generator to quickly fill the insufficient power;

[0093] In response to seasonal changes, when the electricity demand index exceeds the preset threshold for five consecutive days, the implementation measures are to increase the charging speed of the energy storage system to store excess energy in a timely manner; reduce the output of renewable energy during high-demand periods to delay the depletion of energy storage facilities;

[0094] A cost-benefit ratio is set. When the unit cost of renewable energy power generation increases by more than 10%, a review is triggered. The implementation measures are to analyze the operating costs of renewable energy to determine whether it is necessary to adjust the power generation strategy or replace equipment; at the same time, evaluate the user's willingness to pay to seek economic optimization.

[0095] Furthermore, the collected data sources are integrated with the management system through a unified communication protocol. During the data capture phase, data compression is performed to reduce network bandwidth requirements. Edge computing capabilities are deployed on near-source devices to perform preliminary data analysis and processing to reduce latency.

[0096] The processed data is uploaded to the central server for regular updates, which are divided into short-term, medium-term and long-term. The data update strategy in each cycle is different. In the short term, it focuses on rapid response, and in the medium term, it focuses on reasonable scheduling plans. Based on monitoring data and analysis results, the output distribution of renewable energy and conventional power sources is adjusted in real time. A rule-based response mechanism is used to optimize energy distribution, and dynamic information feedback is provided on user terminal devices, including real-time power consumption, current energy utilization, and future forecast information.

[0097] Embodiment 2, the second embodiment of the present invention, is different from the first two embodiments in that:

[0098] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0100] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] Example 3, reference Figure 2 , which is an embodiment of the present invention, provides a multi-time scale clean energy complementary characteristic analysis and utilization system, characterized by: comprising a data collection module 1, a feature extraction and modeling module 2, an optimization scheduling strategy module 3, a real-time monitoring and feedback module 4, and a decision support and optimization module 5;

[0103] Data collection module 1, responsible for collecting historical data and real-time meteorological information related to clean energy output;

[0104] Feature extraction and modeling module 2 processes the collected historical data and meteorological information, uses an improved multivariate linear regression model to extract features and predict output characteristics at multiple time scales;

[0105] Optimization scheduling strategy module 3, based on the output of feature extraction and modeling module, designs and implements optimization scheduling strategy to improve the utilization efficiency of clean energy;

[0106] Real-time monitoring and feedback module 4 is responsible for real-time monitoring of the overall system performance and energy output changes, including the collection and analysis of key indicators of grid frequency, power demand and energy output;

[0107] Decision support and optimization module 5 combines various data analysis results to support managers' decision-making; by setting cost-benefit ratios, it evaluates the operating costs of renewable energy and users' willingness to pay, provides economic optimization suggestions, helps optimize power generation strategies and equipment selection, and ensures the economic sustainability of the system.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales, characterized by: include, Collect historical clean energy output data and meteorological information; Use machine learning algorithms to analyze historical output data and meteorological information to predict the output characteristics of clean energy at different time scales; Based on the prediction results, design optimized scheduling strategies to improve the efficiency of clean energy utilization; Implement optimized scheduling strategies, dynamically adjust the output of renewable energy and conventional power sources, and monitor system performance and energy output changes in real time during the implementation process.

2. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 1, characterized in that: The meteorological information, wind speed information at a specific location, including average wind speed and instantaneous wind speed, performs time series analysis on the collected wind speed data, eliminates outliers, and smoothes the data by a sliding average method to obtain a stable wind speed pattern; Use ground radiation monitoring instruments to obtain the solar radiation energy reaching the surface per unit time, normalize the data at different time scales, and use radiation distribution models to analyze the impact of sunshine time and meteorological conditions on solar energy output; Record air temperatures at specific locations, cross-validate air temperature data with other meteorological data, and use seasonal adjustment models to eliminate the effects of seasonal changes; The height, frequency and periodic changes of tides are recorded, the tidal data are subjected to Fourier transform analysis, the periodic change characteristics are identified, and correlation analysis is performed with other meteorological variables to evaluate the impact of tidal changes on ocean energy output.

3. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 2, characterized in that: The machine learning algorithm analysis includes processing historical data and meteorological information, extracting output characteristics and providing accurate predictions at multiple time scales; An improved multivariate linear regression model is used, combined with regularization to prevent overfitting: Among them, Y i represents the clean energy output of the i-th sample, β0 is the intercept term, p is the total number of features, β j represents the regression coefficient of the jth feature, X ij represents the value of the jth feature in the i-th sample, λ is the regularization parameter, β k represents the absolute value of the kth regression coefficient; During the training process, the initial regression coefficient β j will be set to random values ​​and optimized iteratively, using the trained model to extract estimates of clean energy output from the feature set: in, is the output feature; all input features X ij and the corresponding regression coefficient β j The model weights are linearly combined to output the prediction results for each sample. For each sample, calculate the residual R of the force feature i , used for subsequent model analysis: Residual R i It is the difference between the actual output and the predicted output. By analyzing the residuals, we can determine the degree of fit of the model and evaluate the features that have a great impact on the prediction effect.

4. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 3, characterized in that: The prediction of output characteristics at different time scales includes using cross-validation to evaluate model performance, adjusting regularization parameters to obtain the best results, and using root mean square error and determination coefficient to evaluate model prediction accuracy; The model is used to expand the feature vector combined with the time factor, build an improved time series regression model, and perform multi-time scale prediction: Among them, Y t For the time T t The predicted value of clean energy output at the time of tj For the time T t is the input feature, and γ is the weight coefficient of the time factor.

5. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 4, characterized in that: The optimization scheduling strategy includes setting an objective function to maximize the proportion of clean energy use and introducing additional constraints to ensure the stability and reliability of the system; The objective function F is set to optimize the scheduling strategy, expressed as: Among them, α, β, γ are weight coefficients, T is the number of time steps in the scheduling cycle, and E re (t) is the renewable energy power generation at time t, C total is the total generation cost in the dispatch period, S is the indicator of stability constraint; During the optimization process, constraints are introduced to ensure the rationality and feasibility of the scheduling plan. The constraints include load matching constraints, power generation capacity constraints, and clean energy proportion constraints.

6. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 5, characterized in that: The dynamic adjustment includes giving priority to increasing the proportion of renewable energy power supply when the combined output of wind and photovoltaic power generation reaches or exceeds 70% of the total power demand. The implementation measures include increasing the output of solar and wind power generation; reducing the load of traditional power sources, and stopping power generation only when it is no less than 30% of the actual demand; When the grid frequency fluctuates by more than ±0.5Hz, fast response regulation is implemented. The implementation measures include enabling the fast response layer interface to immediately adjust the wind turbine speed or photovoltaic power; starting the backup gas generator to quickly fill the insufficient power; In response to seasonal changes, when the electricity demand index exceeds the preset threshold for five consecutive days, the implementation measures are to increase the charging speed of the energy storage system to store excess energy in a timely manner; reduce the output of renewable energy during high-demand periods to delay the depletion of energy storage facilities; A cost-benefit ratio is set. When the unit cost of renewable energy power generation increases by more than 10%, a review is triggered. The implementation measures are to analyze the operating costs of renewable energy to determine whether it is necessary to adjust the power generation strategy or replace equipment; at the same time, evaluate the user's willingness to pay to seek economic optimization.

7. The method for analyzing and utilizing the complementary characteristics of clean energy at multiple time scales according to claim 6, characterized in that: The real-time monitoring of system performance and energy output changes includes integrating the collected data sources with the management system through a unified communication protocol, compressing the data during the data capture phase to reduce network bandwidth requirements, deploying edge computing capabilities on near-source devices, performing preliminary data analysis and processing, and reducing latency; Upload the processed data to the central server for regular updates, which are divided into short-term, medium-term and long-term. The data update strategy in each period is different. In the short term, it focuses on rapid response, while in the medium term, it focuses on reasonable scheduling plans; Based on monitoring data and analysis results, the output distribution of renewable energy and conventional power sources is adjusted in real time. A rule-based response mechanism is used to optimize energy distribution, providing dynamic information feedback on user terminal devices, including real-time power consumption, current energy utilization, and future forecast information.

8. A system using the multi-time scale clean energy complementary characteristics analysis and utilization method as claimed in any one of claims 1 to 7, characterized in that: It includes data collection module, feature extraction and modeling module, optimization scheduling strategy module, real-time monitoring and feedback module, and decision support and optimization module; The data collection module is responsible for collecting historical data and real-time meteorological information related to clean energy output; The feature extraction and modeling module processes the collected historical data and meteorological information, uses an improved multivariate linear regression model to extract features and predict output characteristics at multiple time scales; The optimization scheduling strategy module designs and implements the optimization scheduling strategy according to the output of the feature extraction and modeling module to improve the utilization efficiency of clean energy; The real-time monitoring and feedback module is responsible for real-time monitoring of the overall system performance and energy output changes, including the collection and analysis of key indicators of grid frequency, power demand and energy output; The decision support and optimization module supports managers’ decision making by combining various data analysis results; By setting the cost-benefit ratio, evaluating the operating cost of renewable energy and the user's willingness to pay, providing economic optimization suggestions, helping to optimize power generation strategies and equipment selection, and ensuring the economic sustainability of the system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images