New energy consumption capability assessment method and device, equipment, storage medium and product

Abstract

The invention relates to the technical field of new energy power generation, and discloses a new energy consumption capability assessment method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining the operation data of a new energy power generation system; constructing a new energy consumption capability evaluation model based on the operation data; training a new energy consumption capability evaluation model based on the operation data to obtain a target evaluation model; and evaluating the current consumption capability of the new energy power generation system by using the target evaluation model. According to the invention, the problem of low evaluation precision of the new energy consumption capability can be solved.

Description

Methods, devices, equipment, storage media and products for assessing the absorption capacity of new energy sources Technical Field

[0001] This invention relates to the field of new energy power generation technology, specifically to methods, devices, equipment, storage media, and products for assessing the absorption capacity of new energy sources. Background Technology

[0002] With the increasing severity of global climate change, strategies and goals for addressing climate change have been formulated, and energy transition with the reduction of greenhouse gas emissions at its core has become a global consensus. New energy sources, especially wind and solar power, have become an important component of this energy transition due to their cleanliness, renewability, and enormous potential. While wind and solar power offer significant environmental and economic benefits, their intermittency and volatility also pose significant challenges to the power system, such as the instability of power generation, grid instability, difficulty in predicting energy demand, and the complexity of dispatching.

[0003] Traditional methods for assessing renewable energy absorption capacity are mainly based on physical models and empirical formulas. They typically simplify the modeling of power systems and renewable energy generation, ignoring many complex nonlinear characteristics and stochastic factors, resulting in low assessment accuracy. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, equipment, storage medium and product for assessing the renewable energy absorption capacity, so as to solve the problem of low accuracy in assessing renewable energy absorption capacity.

[0005] In a first aspect, the present invention provides a method for assessing the absorption capacity of new energy sources. The method includes: acquiring operational data of a new energy power generation system; constructing a new energy absorption capacity assessment model based on the operational data; training the new energy absorption capacity assessment model based on the operational data to obtain a target assessment model; and using the target assessment model to assess the current absorption capacity of the new energy power generation system.

[0006] In this implementation, the application introduces machine learning algorithms that can more accurately capture the nonlinear characteristics of power systems and renewable energy generation, thereby significantly improving the accuracy of renewable energy absorption capacity assessment. Compared to traditional methods based on physical models and empirical formulas, artificial intelligence algorithms can better handle the complexity and uncertainty of data.

[0007] In one optional implementation, acquiring operational data of the new energy power generation system includes: acquiring historical operational data, which includes historical characteristic data and historical new energy output data. The historical characteristic data includes historical grid load data, historical power generation data, historical meteorological data, and historical equipment status data; performing correlation analysis on the historical characteristic data and historical new energy output data, and selecting first characteristic data from the historical characteristic data; and performing principal component analysis on the first characteristic data, and selecting second characteristic data from the first characteristic data.

[0008] In this implementation, historical data is used to select indicators that have a significant impact on power consumption assessment, which are then used for subsequent model training. The method in this application relies on a large amount of historical and real-time data, enabling dynamic adjustment and optimization of the model based on actual operating conditions. This data-driven nature makes the method highly adaptable, capable of adapting to the characteristics of different regions and power systems, and thus has broad applicability.

[0009] In one optional implementation, a new energy absorption capacity assessment model is constructed based on operational data, including: constructing multiple assessment models, such as a support vector machine module, a random forest model, and a deep neural network module; and determining the new energy absorption capacity assessment model from among the multiple assessment models based on operational data.

[0010] In this implementation, the optimal model is selected from multiple evaluation models using operational data, making the selected model more suitable for new energy consumption assessment and further improving the efficiency and accuracy of the assessment.

[0011] In one optional implementation, a new energy absorption capacity assessment model is trained based on operational data to obtain a target assessment model. This includes: using historical feature data as training features and historical new energy output data as training labels, and using cross-validation to train the new energy absorption capacity assessment model; adjusting the model parameters of the new energy absorption capacity assessment model using the mean squared error loss function to obtain the target assessment model.

[0012] In this implementation, cross-validation generates more stable and reproducible results, averaging the model's performance across different datasets and reducing the likelihood of overfitting the training data. Allowing all training data to participate in the training process ensures sufficient data for evaluating model performance. Furthermore, this application utilizes the mean squared error loss function for parameter updates, which is sensitive to bias and improves the accuracy of the trained model.

[0013] In one optional implementation, acquiring the operating data of the new energy power generation system further includes: determining key features in the operating data based on the second feature data, and acquiring the current operating data corresponding to the key features, wherein the current operating data is one or more of the current grid load data, current power generation data, current meteorological data, and current equipment status data; evaluating the current absorption capacity of the new energy power generation system using the target evaluation model includes: inputting the current operating data into the target evaluation model to calculate the current evaluated output data of the new energy power generation system.

[0014] In this implementation, the trained model is used for evaluation and prediction. The artificial intelligence algorithm model of this application can handle the characteristics of various complex systems, including various types of new energy power generation (such as wind power and photovoltaic) and various power grid structures (such as microgrids and smart grids). This broad adaptability makes this method highly valuable for application in various power systems.

[0015] Secondly, the present invention provides a new energy absorption capacity assessment device, which includes: an acquisition module for acquiring operating data of a new energy power generation system; a construction module for constructing multiple assessment models and determining a new energy absorption capacity assessment model from among the multiple assessment models based on the operating data; a training module for training the new energy absorption capacity assessment model based on the operating data to obtain a target assessment model; and an assessment module for assessing the current absorption capacity of the new energy power generation system using the target assessment model.

[0016] In one optional implementation, the acquisition module includes: a first acquisition unit, used to acquire historical operating data, the historical operating data including historical feature data and historical renewable energy output data, the historical feature data including historical grid load data, historical power generation data, historical meteorological data and historical equipment status data; a first screening unit, used to perform correlation analysis on the historical feature data and historical renewable energy output data, and screen first feature data from the historical feature data; and a second screening unit, used to perform principal component analysis on the first feature data, and screen second feature data from the first feature data.

[0017] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the new energy consumption capacity assessment method of the first aspect or any corresponding embodiment described above.

[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the new energy consumption capacity assessment method of the first aspect or any corresponding embodiment described above.

[0019] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the new energy consumption capacity assessment method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 is a flowchart of a new energy consumption capacity assessment method according to an embodiment of the present invention; Figure 2 is a flowchart of another new energy consumption capacity assessment method according to an embodiment of the present invention; Figure 3 is a structural block diagram of a new energy consumption capacity assessment device according to an embodiment of the present invention; Figure 4 is a hardware structure diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] New energy sources, especially wind and solar power, have become an important part of the energy transition due to their clean, renewable, and high-potential characteristics. While wind and solar power offer significant environmental and economic benefits, their intermittency and volatility also pose significant challenges to the power system. These challenges include: power generation instability (wind and solar power generation is greatly affected by weather conditions, exhibiting significant randomness and volatility); grid instability (a high proportion of new energy connections can lead to instability in grid frequency and voltage, threatening the safe operation of the grid); difficulty in load forecasting (the uncertainty of new energy generation increases the difficulty of grid load forecasting, and traditional forecasting methods struggle to cope with this complexity); and dispatch complexity (to maintain stable power system operation, dispatch centers need to frequently adjust the output of traditional power sources to balance the fluctuations in new energy generation, increasing dispatch complexity and operating costs).

[0024] Traditional methods for assessing renewable energy absorption capacity are mainly based on physical models and empirical formulas. These methods typically have the following limitations: 1. Model simplification: Traditional methods usually simplify the modeling of power systems and renewable energy generation, ignoring many complex nonlinear characteristics and random factors, resulting in low assessment accuracy.

[0025] 2. Insufficient data utilization: Traditional methods often rely on limited historical data and expert experience, failing to make full use of a large amount of real-time and historical data, which limits the adaptability and accuracy of the model.

[0026] 3. High computational complexity: The physical models and empirical formulas have high computational complexity, making it difficult to meet the needs of real-time evaluation and rapid decision-making.

[0027] 4. Lack of dynamic adjustment capability: Traditional methods are usually static and difficult to adjust dynamically based on real-time data, and cannot reflect changes in the power system in a timely manner.

[0028] With the increasing proportion of renewable energy generation in the power system, accurate assessment of renewable energy absorption capacity will become a crucial guarantee for the safe and stable operation of the power grid. Therefore, this application proposes a method for assessing renewable energy absorption capacity, applying artificial intelligence technology to achieve load forecasting and absorption capacity assessment. This method improves the accuracy and efficiency of the assessment, overcoming the limitations of traditional methods. By fully utilizing historical and real-time data to construct a data-driven assessment model, the actual situation of the power system and renewable energy generation can be more accurately reflected. Furthermore, by introducing artificial intelligence algorithms, the assessment model can be dynamically adjusted, supporting real-time decision-making and optimized scheduling, further improving the utilization rate of renewable energy and the stability of the power system.

[0029] According to an embodiment of the present invention, a method for assessing the absorption capacity of new energy sources is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a method for assessing the renewable energy absorption capacity. Figure 1 is a flowchart of a renewable energy absorption capacity assessment method according to an embodiment of the present invention. It should be noted that if substantially the same results are obtained, this embodiment is not limited to the flow order shown in Figure 1. As shown in Figure 1, the process includes the following steps: Step S101, obtaining the operating data of the renewable energy power generation system.

[0031] Specifically, operational data is collected from the power system and new energy power generation system. This operational data includes, but is not limited to, grid load data, power generation data, meteorological data, equipment status data, and output data.

[0032] Furthermore, the operational data undergoes preprocessing. This preprocessing includes data cleaning, missing value imputation, and normalization.

[0033] The operating data of the new energy power generation system includes historical operating data and current operating data. Historical operating data is used to train the new energy absorption capacity assessment model, and current operating data is used to conduct absorption assessment.

[0034] Step S102: Construct a new energy consumption capacity assessment model based on operational data.

[0035] By utilizing historical operational data, and taking into account specific application scenarios, data characteristics, and expected goals, a new energy consumption capacity assessment model suitable for the current assessment task is constructed.

[0036] The assessment model for renewable energy absorption capacity includes support vector machine modules, random forest models, and deep neural network modules.

[0037] Step S103: Train the new energy consumption capacity assessment model based on the operating data to obtain the target assessment model.

[0038] Using historical operational data as a training set, a loss function is constructed to train the new energy absorption capacity assessment model, thus obtaining the target assessment model.

[0039] Specifically, the model structure example for the assessment model of new energy absorption capacity is as follows: .

[0040] in, The assessment structure for the new energy absorption capacity assessment model. For the input historical running data, These are the model parameters.

[0041] Iteratively update model parameters using the loss function The loss function can be one or more of the following: mean squared error loss function, mean absolute error loss function, Huber loss function, smoothing L1 loss function, etc.

[0042] Step S104: Use the target evaluation model to evaluate the current absorption capacity of the new energy power generation system.

[0043] Input the current operating data into the target evaluation model to calculate the current evaluated output data of the new energy power generation system.

[0044] The renewable energy absorption capacity assessment method provided in this embodiment introduces a machine learning algorithm, which can more accurately capture the nonlinear characteristics of the power system and renewable energy generation, thereby significantly improving the assessment accuracy of renewable energy absorption capacity. Compared with traditional methods based on physical models and empirical formulas, artificial intelligence algorithms can better handle the complexity and uncertainty of data.

[0045] This embodiment provides a method for assessing the renewable energy absorption capacity. Figure 2 is a flowchart of another renewable energy absorption capacity assessment method according to an embodiment of the present invention. It should be noted that if there are substantially the same results, this embodiment is not limited to the process order shown in Figure 2. As shown in Figure 2, the process includes the following steps: Step S201, obtaining the operating data of the renewable energy power generation system.

[0046] Specifically, in one implementation, step S201 includes: step S2011, obtaining historical operation data.

[0047] Historical operational data includes historical characteristic data and historical renewable energy output data. Historical characteristic data includes historical grid load data, historical power generation data, historical meteorological data, and historical equipment status data.

[0048] Specifically, historical characteristic data and corresponding historical renewable energy output data are collected from the power system and renewable energy generation system. In subsequent model training, the historical characteristic data is used as feature data, and the historical renewable energy output data is used as label data.

[0049] In one implementation, grid load data, wind power generation data, photovoltaic power generation data, wind speed data, and solar radiation intensity data are acquired from various regions of the power system and new energy power generation system.

[0050] For example, the total grid load obtained from the power system and the new energy power generation system is 5000MW, and the loads of each region are as follows: Region A load 1500MW; Region B load 2000MW; Region C load 1500MW. Wind speed data is 6m / s; solar radiation intensity is 800... Historical wind power generation is 1200MW, and historical photovoltaic power generation is 800MW.

[0051] Furthermore, data cleaning is performed on the operational data. Specifically, missing values ​​are imputed in the operational data.

[0052] In one implementation, a data recognition algorithm is used to identify missing data in the running data, and the missing values ​​are filled using the mean, median, or mode of the running data.

[0053] In another implementation, for time-series running data, a data recognition algorithm is used to identify missing data in the running data, and the missing values ​​are filled by running data adjacent to the missing positions.

[0054] In another implementation, for continuously changing operational data, a data recognition algorithm is used to identify missing data in the operational data, and linear or other interpolation methods are used to fill in the missing values.

[0055] In another implementation, a regression or classification model is built to predict and fill in missing values ​​in the running data.

[0056] Furthermore, the running data is normalized to a specified range. For example, the running data is normalized to the interval [0, 1].

[0057] In one implementation, the min-max normalization method is used to normalize the running data. Specifically, the formula for the min-max normalization method is: .

[0058] in, This is the original running data. For normalized runtime data, The maximum value of the running data. This is the minimum value of the running data.

[0059] In one implementation, the zero-mean unit variance normalization method is used to normalize the operating data. Specifically, the formula for the zero-mean unit variance normalization method is: .

[0060] in, This is the original running data. For normalized runtime data, The mean of the running data, This represents the standard deviation of the running data.

[0061] Step S2012: Perform correlation analysis on historical feature data and historical new energy output data, and select the first feature data from the historical feature data.

[0062] By using correlation analysis, one or more historical feature data that are highly correlated with historical new energy output data are selected to obtain the first feature data.

[0063] In one implementation, the correlation coefficient between historical characteristic data and historical renewable energy output data is calculated using the Pearson correlation coefficient. The Pearson correlation coefficient is a statistic used to measure the strength and direction of the linear relationship between two continuous variables.

[0064] Specifically, the formula for calculating the Pearson correlation coefficient is as follows: .

[0065] in, The Pearson correlation coefficient between historical characteristic data and historical renewable energy output data. Let be the covariance between historical feature data and historical renewable energy output data, be the standard deviation of historical feature data, and be the standard deviation of historical renewable energy output data.

[0066] The first feature data is either the historical feature data with the largest Pearson correlation coefficient (preset quantity) or the historical feature data with a Pearson correlation coefficient greater than the preset correlation coefficient.

[0067] Step S2013: Perform principal component analysis on the first feature data and select the second feature data from the first feature data.

[0068] Specifically, key features are extracted based on principal component analysis, where the feature extraction formula is: .

[0069] Where Z is the feature matrix, X is the original data matrix of the first feature data, and W is the feature weight matrix corresponding to the first feature data.

[0070] One or more second feature data are selected from the first feature data based on the feature matrix.

[0071] In another implementation, step S201 above further includes: step S2014, determining key features in the running data based on the second feature data, and obtaining the current running data corresponding to the key features.

[0072] Specifically, real-time operational data is collected from the power system and new energy power generation system. The current operational data includes one or more of the following: current grid load data, current power generation data, current meteorological data, and current equipment status data.

[0073] Step S202: Construct a new energy consumption capacity assessment model based on operational data.

[0074] Specifically, step S202 above includes: step S2021, constructing multiple evaluation models.

[0075] The evaluation models include support vector machine modules, random forest models, and deep neural network modules.

[0076] Step S2022: Determine the assessment model for new energy absorption capacity from multiple assessment models based on operational data.

[0077] The various assessment models were evaluated using model performance evaluation indicators, and the optimal model was selected as the assessment model for new energy absorption capacity.

[0078] Specifically, the model performance evaluation metrics include accuracy, precision, recall, F1 score, and mean squared error. In step S203, the new energy absorption capacity assessment model is trained based on operational data to obtain the target assessment model.

[0079] Specifically, step S203 includes: step S2031, using historical feature data as training features and historical new energy output data as training labels, and using cross-validation to train the new energy consumption capacity assessment model.

[0080] The new energy absorption capacity assessment model is trained and predicted using k-fold cross-training based on historical characteristic data and historical new energy output data.

[0081] For example, a test set and k historical data subsets are constructed using historical feature data and historical renewable energy output data. These k historical data subsets are referred to as k folds, i.e., Folds1 to Foldsk, where each fold represents a historical data subset. Five independent rounds of training and prediction validation are then performed. In each round of training and prediction validation, k-1 folds outside the current round are selected and merged as the training set, and the remaining fold is used as the validation set.

[0082] In the first round of training and prediction validation, Folds2 to Foldsk are used as the training set, and Folds1 is used as the validation set. The new energy consumption capacity assessment model is first trained using the data in the training set, and then the new energy consumption capacity assessment model after one round of training is validated using the validation set, and prediction data is output. The second round of training and prediction validation is then carried out, using Folds1, Folds3 to Foldsk as the training set, and Fold2 as the validation set. The new energy consumption capacity assessment model after one round of training is first trained using the data in the training set, and then the new energy consumption capacity assessment model after two rounds of training is validated using the validation set, and prediction data is output. After completing k rounds of training, the trained new energy consumption capacity assessment model and k prediction data are obtained. The k output data are concatenated according to the time sequence to obtain the model prediction data corresponding to the new energy consumption capacity assessment model.

[0083] Step S2032: Adjust the model parameters of the new energy absorption capacity assessment model using the mean square error loss function to obtain the target assessment model.

[0084] During training, the mean squared error loss function is used for iterative optimization. The mean squared error loss function is: .

[0085] in, Data on historical contributions to new energy sources For the predicted data, n is the number of samples of historical feature data.

[0086] For example, the performance evaluation indexes of the constructed evaluation models are used to evaluate the various evaluation models, and the support vector machine is selected as the evaluation model for the new energy absorption capacity.

[0087] The specific steps for training the new energy consumption capacity assessment model are as follows: Initialize the initial model parameters of the support vector machine, using historical feature data as training features and historical new energy output data as training labels, input these into the support vector machine, and solve for the model parameters by optimizing the objective function, where the objective function is: .

[0088] The constraints are as follows: .

[0089] .

[0090] Where w is the weight vector and b is the bias value. As slack variables, For penalty parameters, This is the kernel function.

[0091] Using the above constraints, carryover optimization is performed until the objective function converges, training is complete, the updated model parameters are saved, and the objective evaluation model is obtained.

[0092] Step S204: Use the target evaluation model to evaluate the current absorption capacity of the new energy power generation system.

[0093] Input the current operating data into the target evaluation model to calculate the current evaluated output data of the new energy power generation system.

[0094] For example, the total grid load obtained from the power system and the new energy power generation system is 5000MW, and the loads of each region are as follows: Region A load 1500MW; Region B load 2000MW; Region C load 1500MW. Wind speed data is 6m / s; solar radiation intensity is 800 W / m². 2 Historical wind power generation is 1200MW, and historical photovoltaic power generation is 800MW. Inputting this into the target evaluation model, the current estimated output of the new energy power generation system is 1800MW.

[0095] Furthermore, based on the assessment results, the power grid dispatch center formulates optimized dispatch strategies. For example, when the current assessed output data is low, it increases the output of pumped storage power stations or adjusts the operation mode of traditional power sources to improve the proportion of new energy consumption.

[0096] The assessment results of the new energy absorption capacity assessment method in this application are highly consistent with the actual operation results, with a mean square error of less than 5%.

[0097] The renewable energy absorption capacity assessment method provided in this embodiment has the following advantages: This application can improve the assessment accuracy. Specifically, this application utilizes artificial intelligence algorithms, such as support vector machines, random forests, and deep neural networks, which are complex models that can more accurately capture the nonlinear characteristics of the power system and renewable energy generation, thereby significantly improving the assessment accuracy of renewable energy absorption capacity. Compared with traditional methods based on physical models and empirical formulas, artificial intelligence algorithms can better handle the complexity and uncertainty of data.

[0098] This application enhances assessment efficiency. Specifically, through automated data processing and model training, it enables rapid assessment of renewable energy absorption capacity. Traditional methods often require extensive manual calculations and adjustments, while this application, through a data-driven approach, reduces human intervention and improves assessment efficiency. Furthermore, the model can quickly provide assessment results after real-time data input, supporting rapid decision-making by the power grid dispatch center.

[0099] This application presents a highly flexible, data-driven approach. Specifically, the method relies on a large amount of historical and real-time data, enabling dynamic adjustment and optimization of the model based on actual operating conditions. This data-driven characteristic makes the method highly adaptable, capable of accommodating the characteristics of different regions and power systems, and thus possessing broad applicability.

[0100] This application demonstrates the adaptability to complex systems. Specifically, the artificial intelligence-based algorithm can handle the characteristics of various complex systems, including multiple types of new energy power generation (such as wind power and photovoltaics) and various power grid structures (such as microgrids and smart grids). This broad adaptability makes the method highly valuable for application in various power systems.

[0101] This application can improve the utilization rate of renewable energy. Specifically, through accurate assessment of renewable energy absorption capacity, the power grid dispatch center can formulate more reasonable dispatch plans and operating strategies, optimize the allocation of power resources, and thus improve the utilization rate of renewable energy. Especially in power systems with a high proportion of renewable energy integration, the method of this invention can significantly improve the stability and reliability of the system.

[0102] This application can reduce operating costs. Specifically, accurate assessment and optimized dispatch can reduce unnecessary reserve capacity in the power system and decrease the start-up and shutdown frequency of traditional generator units, thereby reducing operating costs. By improving the absorption capacity of new energy sources, it can also reduce dependence on fossil fuels, lower fuel costs, and reduce carbon emissions.

[0103] This application enables real-time dynamic adjustment. Specifically, the method of this application can dynamically adjust and optimize based on real-time data, enabling rapid response to changes in the power system and improving dispatch flexibility and response speed. This plays an important role in handling emergencies and uncertainties, and helps maintain the safe and stable operation of the power system.

[0104] This application demonstrates strong scalability. Because the method is based on a general artificial intelligence algorithm, it possesses high scalability and portability. With the continuous acquisition of new data and improvements to the algorithm, the evaluation model can be continuously optimized and upgraded to adapt to the future development needs of the power system.

[0105] This embodiment also provides a new energy consumption capacity assessment device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0106] This embodiment provides a new energy absorption capacity assessment device. Figure 3 is a structural block diagram of the new energy absorption capacity assessment device according to an embodiment of the present invention. As shown in Figure 3, it includes: an acquisition module 301, used to acquire the operating data of the new energy power generation system.

[0107] Module 302 is used to build multiple assessment models and determine the assessment model for new energy absorption capacity among multiple assessment models based on operational data.

[0108] Training module 303 is used to train the new energy consumption capacity assessment model based on operational data to obtain the target assessment model.

[0109] Evaluation module 304 is used to evaluate the current absorption capacity of the new energy power generation system using the target evaluation model.

[0110] In some optional implementations, the acquisition module 301 includes: a first acquisition unit, used to acquire historical operating data, which includes historical characteristic data and historical new energy output data. The historical characteristic data includes historical grid load data, historical power generation data, historical meteorological data, and historical equipment status data.

[0111] The first screening unit is used to perform correlation analysis on historical feature data and historical new energy output data, and to screen the first feature data from the historical feature data.

[0112] The second screening unit is used to perform principal component analysis on the first feature data and screen the second feature data from the first feature data.

[0113] In some optional implementations, the acquisition module 301 further includes: a first determining unit, configured to determine key features in the operating data based on the second feature data, and acquire the current operating data corresponding to the key features, wherein the current operating data is one or more of the current power grid load data, current power generation data, current meteorological data, and current equipment status data.

[0114] In some alternative implementations, the building module 302 includes: a building unit for building various evaluation models, including a support vector machine module, a random forest model, and a deep neural network module.

[0115] The second determining unit is used to determine the assessment model for new energy absorption capacity among multiple assessment models based on operational data.

[0116] In some optional implementations, the training module 303 includes: a first training unit, used to train the new energy consumption capacity assessment model using historical feature data as training features and historical new energy output data as training labels, and using cross-validation.

[0117] The second training unit is used to adjust the model parameters of the new energy absorption capacity assessment model using the mean square error loss function, so as to obtain the target assessment model.

[0118] In some optional implementations, the evaluation module 304 includes a calculation unit for inputting current operating data into the target evaluation model and calculating the current evaluation output data of the new energy power generation system.

[0119] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0120] In this embodiment, the new energy consumption capacity assessment device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0121] This invention also provides a computer device having the new energy consumption capacity assessment device shown in Figure 3 above.

[0122] Please refer to Figure 4, which is a schematic diagram of a computer device according to an optional embodiment of the present invention. As shown in Figure 4, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 uses one processor 10 as an example.

[0123] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0124] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0125] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0126] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0127] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means; Figure 4 shows an example of a connection via a bus.

[0128] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0129] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0130] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0131] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for assessing the capacity for renewable energy absorption, characterized in that, The method includes: acquiring operational data of a new energy power generation system; constructing a new energy absorption capacity assessment model based on the operational data; training the new energy absorption capacity assessment model based on the operational data to obtain a target assessment model; and using the target assessment model to assess the current absorption capacity of the new energy power generation system.

2. The method for assessing the capacity for renewable energy absorption according to claim 1, characterized in that, The acquisition of operational data of the new energy power generation system includes: acquiring historical operational data, which includes historical characteristic data and historical new energy output data, including historical grid load data, historical power generation data, historical meteorological data, and historical equipment status data; performing correlation analysis on the historical characteristic data and historical new energy output data, and selecting first characteristic data from the historical characteristic data; and performing principal component analysis on the first characteristic data, and selecting second characteristic data from the first characteristic data.

3. The method for assessing the capacity for renewable energy absorption according to claim 2, characterized in that, The step of constructing a new energy absorption capacity assessment model based on the operational data includes: constructing multiple assessment models, including a support vector machine module, a random forest model, and a deep neural network module; and determining the new energy absorption capacity assessment model from among the multiple assessment models based on the operational data.

4. The method for assessing the capacity for renewable energy absorption according to claim 3, characterized in that, The step of training the new energy absorption capacity assessment model based on the operational data to obtain the target assessment model includes: using the historical feature data as training features and the historical new energy output data as training labels, and using cross-validation to train the new energy absorption capacity assessment model; and using the mean squared error loss function to adjust the model parameters of the new energy absorption capacity assessment model to obtain the target assessment model.

5. The method for assessing the capacity for renewable energy absorption according to claim 2, characterized in that, The acquisition of the operating data of the new energy power generation system further includes: determining the key features in the operating data based on the second feature data, and acquiring the current operating data corresponding to the key features, wherein the current operating data is one or more of the current grid load data, current power generation data, current meteorological data, and current equipment status data; the assessment of the current absorption capacity of the new energy power generation system using the target assessment model includes: inputting the current operating data into the target assessment model to calculate the current assessed output data of the new energy power generation system.

6. A device for assessing the absorption capacity of new energy sources, characterized in that, The device includes: an acquisition module for acquiring operational data of a new energy power generation system; a construction module for constructing multiple evaluation models and determining a new energy absorption capacity evaluation model from among the multiple evaluation models based on the operational data; a training module for training the new energy absorption capacity evaluation model based on the operational data to obtain a target evaluation model; and an evaluation module for evaluating the current absorption capacity of the new energy power generation system using the target evaluation model.

7. The new energy consumption capacity assessment device according to claim 6, characterized in that, The acquisition module includes: a first acquisition unit for acquiring historical operating data, which includes historical feature data and historical renewable energy output data, including historical grid load data, historical power generation data, historical meteorological data, and historical equipment status data; a first filtering unit for performing correlation analysis on the historical feature data and historical renewable energy output data, and filtering first feature data from the historical feature data; and a second filtering unit for performing principal component analysis on the first feature data, and filtering second feature data from the first feature data.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the new energy consumption capacity assessment method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to cause the computer to execute the new energy consumption capacity assessment method according to any one of claims 1 to 5.

10. A computer program product, characterized in that, It includes computer instructions, which are used to cause a computer to execute the new energy consumption capacity assessment method according to any one of claims 1 to 5.

Images