New energy consumption proportion contribution evaluation model training method, evaluation method and device

Abstract

The application provides a new energy consumption proportion contribution evaluation model training method, an evaluation method and a device. The training method comprises the following steps: determining a historical new energy consumption proportion contribution score of historical day-ahead scheduling plan data according to a target scheduling plan meeting an annual new energy consumption proportion of a comprehensive energy base; generating a data set according to a corresponding relationship among the historical day-ahead scheduling plan data, historical day-ahead power prediction data and the historical new energy consumption proportion contribution score; and training a preset deep neural network by using the data set to obtain a new energy consumption proportion contribution evaluation model used for outputting a new energy consumption proportion contribution score. The application can effectively improve the training effectiveness and reliability of the new energy consumption proportion contribution evaluation model, improve the accuracy and effectiveness of the new energy consumption proportion contribution evaluation result, avoid energy waste caused by concentrated adjustment for reaching the standard, and effectively improve the rationality and reliability of energy configuration of the comprehensive energy base.

Description

Technical Field

[0001] This application relates to the field of energy dispatching technology, and in particular to training methods, evaluation methods and devices for assessing the contribution of new energy consumption ratios. Background Technology

[0002] Large-scale energy bases aggregate wind, solar, and thermal power and transmit it via direct current (DC). The operation of these bases requires advance planning for wind, solar, and thermal power dispatch to avoid insufficient reserve capacity or significant curtailment of wind and solar power due to improper configuration. One performance evaluation method for large-scale energy bases is the proportion of clean energy consumption, meaning that wind and solar power consumption must reach a certain percentage of total electricity generation during the year. Currently, this target is not considered in the existing dispatch planning methods, potentially leading to a concentrated reduction in thermal power output as the assessment deadline approaches, in an effort to meet the target. This approach results in wasted energy consumption.

[0003] Existing methods for assessing the contribution of renewable energy consumption ratios rely heavily on human experience, resulting in crude assessments that fail to achieve satisfactory results. For instance, when formulating day-ahead dispatch plans, using the same standards (such as whether renewable energy output reaches 50%) on different dates is clearly inaccurate due to the seasonality of wind and solar power. Summary of the Invention

[0004] In view of this, embodiments of this application provide a training method, evaluation method and apparatus for assessing the contribution of new energy consumption ratio, so as to eliminate or improve one or more defects existing in the prior art.

[0005] The first aspect of this application provides a training method for assessing the contribution of new energy consumption ratio, including:

[0006] Construct a scheduling plan that meets the annual target for the proportion of new energy consumption in the comprehensive energy base;

[0007] Based on the target scheduling plan, determine the historical renewable energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base;

[0008] A dataset is generated based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score.

[0009] A pre-set deep neural network is trained using the dataset to obtain a new energy consumption ratio contribution evaluation model, which outputs a new energy consumption ratio contribution score for the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

[0010] In some embodiments of this application, the step of determining the historical renewable energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base based on the target scheduling plan includes:

[0011] Obtain historical day-ahead power prediction data samples corresponding to multiple historical sampling time points of the integrated energy base. Each historical day-ahead power prediction data sample includes: historical day-ahead photovoltaic power prediction data and historical day-ahead wind power prediction data.

[0012] Obtain the historical day-ahead scheduling plan data sample corresponding to each of the historical day-ahead power prediction data samples for the next day. Each historical day-ahead scheduling plan sample includes: the historical day-ahead scheduling plan photovoltaic ratio, the historical day-ahead scheduling plan wind power ratio, and the historical day-ahead scheduling plan thermal power ratio.

[0013] Based on the proportion of new energy consumption on the current day under the target scheduling plan and the proportion of new energy consumption corresponding to each of the historical day-ahead scheduling plan samples, the contribution score of the historical new energy consumption ratio corresponding to each of the historical day-ahead scheduling plan samples is determined.

[0014] In some embodiments of this application, before training a preset deep neural network using the dataset, the following steps are further included:

[0015] Construct a loss function to represent the difference between the contribution score of new energy consumption ratio output by the deep neural network and the contribution score of new energy consumption ratio.

[0016] Correspondingly, training a preset deep neural network using the dataset includes:

[0017] With the goal of minimizing the loss function, a preset deep neural network is trained based on the dataset.

[0018] In some embodiments of this application, the historical day-ahead power prediction data and the historical day-ahead scheduling plan data are both time-series data;

[0019] Correspondingly, the deep neural network includes: LSTM model.

[0020] In some embodiments of this application, the step of determining the historical renewable energy consumption ratio contribution score corresponding to each of the historical day-ahead scheduling plan samples based on the renewable energy consumption ratio of the target scheduling plan on the current day and the renewable energy consumption ratio corresponding to each of the historical day-ahead scheduling plan samples includes:

[0021] Based on the preset formula for the contribution score of renewable energy consumption ratio, the historical renewable energy consumption ratio contribution score corresponding to each historical day-ahead scheduling plan sample is determined.

[0022] The quantitative formula for the contribution score of the new energy consumption ratio includes:

[0023]

[0024] In formula (1), S i Indicates the contribution score of the proportion of new energy consumption; C i This indicates the proportion of new energy consumption corresponding to each of the historical pre-dated scheduling plan samples; This indicates the proportion of new energy consumption on a given day under the target scheduling plan.

[0025] The second aspect of this application provides a method for assessing the contribution of new energy consumption ratio in integrated energy bases, including:

[0026] Obtain the pre-dispatch plan data and corresponding day-ahead power forecast data for the integrated energy base;

[0027] The daytime scheduling plan data and the corresponding daytime power prediction data are input into the renewable energy consumption ratio contribution assessment model so that the renewable energy consumption ratio contribution assessment model outputs the renewable energy consumption ratio contribution score corresponding to the daytime scheduling plan data.

[0028] The new energy consumption ratio contribution assessment model is pre-trained based on the new energy consumption ratio contribution assessment training method.

[0029] The third aspect of this application provides a training device for assessing the contribution of new energy consumption ratio, comprising:

[0030] The target plan construction module is used to construct a target scheduling plan that meets the annual renewable energy consumption ratio of the integrated energy base;

[0031] The scoring calculation module is used to determine the historical renewable energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base based on the target scheduling plan;

[0032] The dataset generation module is used to generate a dataset based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score.

[0033] The model training module is used to train a preset deep neural network using the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting a new energy consumption ratio contribution score of the new energy base based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

[0034] The fourth aspect of this application provides a device for assessing the contribution of new energy consumption ratio in an integrated energy base, comprising:

[0035] The data acquisition module is used to acquire the pre-scheduling plan data and the corresponding day-ahead power forecast data of the integrated energy base;

[0036] The model prediction module is used to input the day-ahead scheduling plan data and the corresponding day-ahead power prediction data into the renewable energy consumption ratio contribution assessment model, so that the renewable energy consumption ratio contribution assessment model outputs the renewable energy consumption ratio contribution score corresponding to the day-ahead scheduling plan data.

[0037] The new energy consumption ratio contribution assessment model is pre-trained based on the new energy consumption ratio contribution assessment training method.

[0038] The fifth aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the new energy consumption ratio contribution assessment training method, or implements the new energy consumption ratio contribution assessment method for the integrated energy base.

[0039] The sixth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned new energy consumption ratio contribution assessment training method, or implements the aforementioned new energy consumption ratio contribution assessment method for integrated energy bases.

[0040] The new energy consumption ratio contribution assessment model training method provided in this application constructs a target scheduling plan that meets the annual new energy consumption ratio of a comprehensive energy base; determines the historical new energy consumption ratio contribution score of the comprehensive energy base based on the target scheduling plan; generates a dataset based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical new energy consumption ratio contribution score; and trains a preset deep neural network using the dataset to obtain a new energy consumption ratio contribution assessment model that outputs the new energy consumption ratio contribution score of the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the comprehensive energy base. This method can effectively improve the training effectiveness and reliability of the new energy consumption ratio contribution assessment model, improve the accuracy and effectiveness of the new energy consumption ratio contribution assessment results, play a role in assisting scheduling decisions, avoid energy waste caused by centralized adjustments to meet targets, and effectively improve the rationality and reliability of energy allocation in comprehensive energy bases.

[0041] Additional advantages, objectives, and features of this application will be set forth in part in the description which follows, and will in part become apparent to those skilled in the art upon review of the following description, or may be learned by practice of the application. The objectives and other advantages of this application can be realized and obtained by means of the structures specifically pointed out in the specification and drawings.

[0042] Those skilled in the art will understand that the purposes and advantages that can be achieved with this application are not limited to those specifically described above, and that the above and other purposes that this application can achieve will be more clearly understood from the following detailed description. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating a method for training a contribution assessment model for the proportion of new energy consumption in one embodiment of this application.

[0045] Figure 2 This is another flowchart illustrating the training method for the new energy consumption ratio contribution assessment model in one embodiment of this application.

[0046] Figure 3This is a flowchart illustrating the contribution assessment method for the proportion of new energy consumption in another embodiment of this application.

[0047] Figure 4 This is a schematic diagram of the structure of the training device for the new energy consumption ratio contribution assessment model in another embodiment of this application.

[0048] Figure 5 This is a schematic diagram of the structure of the new energy consumption ratio contribution assessment device in another embodiment of this application.

[0049] Figure 6 This is a flowchart illustrating the training of the new energy consumption ratio contribution assessment model and the new energy consumption ratio contribution assessment method provided in the application examples of this application.

[0050] Figure 7 This is a schematic diagram illustrating the structure of the LSTM model in an application example of this application. Detailed Implementation

[0051] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] It should also be noted that, in order to avoid obscuring this application with unnecessary details, only the structures and / or processing steps closely related to the solution according to this application are shown in the accompanying drawings, while other details that are not closely related to this application are omitted.

[0053] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0054] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0055] In the following description, embodiments of the present application will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0056] Considering that existing day-ahead scheduling plan generation methods often do not consider the annual renewable energy consumption ratio, and even if they do consider the annual renewable energy consumption ratio, they do not achieve sufficiently good results due to low method effectiveness, this application provides a method for training a renewable energy consumption ratio contribution evaluation model. This method evaluates the contribution of the day-ahead scheduling plan to the annual renewable energy consumption ratio during the day-ahead scheduling plan generation, thereby assisting in scheduling decisions and avoiding the waste caused by abandoning economic centralized adjustments in order to meet targets.

[0057] The following examples will provide a detailed description.

[0058] This application provides a method for training a new energy consumption ratio contribution assessment model, which can be implemented by a new energy consumption ratio contribution assessment model training device. See [link to relevant documentation]. Figure 1 The training method for the new energy consumption ratio contribution assessment model specifically includes the following:

[0059] Step 100: Construct a target scheduling plan that meets the annual renewable energy consumption ratio of the integrated energy base.

[0060] Specifically, based on historical daily wind and solar power monitoring data, a target scheduling plan is established to maximize wind and solar power generation.

[0061] Specifically, the annual renewable energy consumption ratio is calculated under any given scheduling plan. If the target ratio is reached or exceeded, the scheduling plan is confirmed as the target scheduling plan. If the consumption ratio is not reached, the daily thermal power output plan ΔR is reduced. T The target plan is determined as the target scheduling plan once it just meets the requirement of the proportion of new energy consumption, so that the scheduling plan can meet the annual proportion of new energy consumption.

[0062] Step 200: Determine the historical new energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base according to the target scheduling plan.

[0063] In step 200, the training device for the assessment model of the contribution of new energy consumption ratio first receives historical day-ahead power forecast data corresponding to historical day-ahead scheduling plan data collected from the database of the integrated energy base. It can be understood that the historical day-ahead power forecast data and the corresponding historical day-ahead scheduling plan data specifically refer to: historical day-ahead power forecast data samples collected at each historical sampling time point, and the historical day-ahead scheduling plan data samples for the following day corresponding to the historical sampling time point of each historical day-ahead power forecast data sample.

[0064] Step 300: Generate a dataset based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score.

[0065] It is understood that the dataset stores the correspondence between historical day-ahead scheduling plan data, historical day-ahead power prediction data, and the historical renewable energy consumption ratio contribution score. This correspondence means that the dataset not only stores the content of historical day-ahead power prediction data and the historical renewable energy consumption ratio contribution score, but also stores the correspondence between historical day-ahead power prediction data and the historical renewable energy consumption ratio contribution score.

[0066] Step 400: Train a preset deep neural network using the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting the new energy consumption ratio contribution score of the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

[0067] In one or more embodiments of this application, the contribution score for the proportion of new energy consumption can be simply referred to as the new energy consumption score.

[0068] In step 400, the dataset is used to train a preset deep neural network. Specifically, the dataset can be used as a training set to train the deep neural network; the dataset can also be divided into a training set, a validation set, and a test set, etc., so that after training the deep neural network with the training set, the deep neural network can be further optimized with the validation set and the test set, etc., to improve the reliability and effectiveness of the model training results. The specific settings can be set according to the actual application situation.

[0069] In one or more embodiments of this application, the new energy consumption ratio contribution assessment model refers to a machine learning model used to generate the new energy consumption ratio contribution assessment. The architecture of this model is the same as its deep neural network architecture. That is, the new energy consumption ratio contribution assessment model refers to the currently trained deep neural network. Subsequently, according to actual application needs, the latest updated historical day-ahead scheduling plan data, historical day-ahead power prediction data, and the historical new energy consumption ratio contribution score can be collected periodically from the database of the integrated energy base. Then, the new energy consumption ratio contribution assessment model can be optimized and iterated using these updated historical day-ahead scheduling plan data, historical day-ahead power prediction data, and the historical new energy consumption ratio contribution score to obtain an updated new energy consumption ratio contribution assessment model, so as to further improve the reliability and effectiveness of the model training results and make it more suitable for the state changes of the integrated energy base.

[0070] As can be seen from the above description, the training method for the new energy consumption ratio contribution assessment model provided in this application embodiment can effectively improve the training effectiveness and reliability of the new energy consumption ratio contribution assessment model, improve the accuracy and effectiveness of the new energy consumption ratio contribution assessment results, play an auxiliary role in scheduling decision-making, avoid energy waste caused by centralized adjustments to meet standards, and effectively improve the rationality and reliability of energy allocation in comprehensive energy bases.

[0071] To further improve the effectiveness and reliability of the data foundation used for training the model, in a training method for a new energy consumption ratio contribution assessment model provided in this application embodiment, see [link to relevant documentation]. Figure 2 Step 200 of the training method for the contribution assessment model of the proportion of new energy consumption specifically includes the following:

[0072] Step 210: Obtain historical day-ahead power prediction data samples corresponding to multiple historical sampling time points of the integrated energy base. Each historical day-ahead power prediction data sample includes historical day-ahead photovoltaic power prediction data and historical day-ahead wind power prediction data.

[0073] Step 220: Obtain the historical day-ahead scheduling plan data sample corresponding to each of the historical day-ahead power prediction data samples for the next day. Each historical day-ahead scheduling plan sample includes: the historical day-ahead scheduling plan photovoltaic ratio, the historical day-ahead scheduling plan wind power ratio, and the historical day-ahead scheduling plan thermal power ratio.

[0074] Step 230: Based on the proportion of new energy consumption on the current day under the target scheduling plan and the proportion of new energy consumption corresponding to each of the historical day-ahead scheduling plan samples, determine the historical new energy consumption contribution score corresponding to each of the historical day-ahead scheduling plan samples.

[0075] Specifically, the daily day-ahead scheduling plan in historical data can be compared with the target scheduling plan to calculate the proportion of new energy consumption on that day under the target scheduling plan and the proportion of new energy consumption under the historical day-ahead scheduling plan. Then, the contribution score of the historical new energy consumption ratio for each of the historical day-ahead scheduling plan samples can be calculated separately.

[0076] To further improve the application effectiveness of the trained model, a training method for a new energy consumption ratio contribution assessment model is provided in this application embodiment. (See also...) Figure 2 The training method for the contribution assessment model of the new energy consumption ratio also includes the following steps before step 400:

[0077] Step 010: Construct a loss function to represent the difference between the contribution score of new energy consumption ratio output by the deep neural network and the contribution score of new energy consumption ratio.

[0078] In step 010, the difference between the contribution score of the new energy consumption ratio output by the deep neural network and the contribution score of the new energy consumption ratio can be determined by the average of the squared differences between the contribution score of the new energy consumption ratio and the contribution score of the new energy consumption ratio.

[0079] Correspondingly, see Figure 2 Step 400 of the training method for the contribution assessment model of new energy consumption ratio specifically includes the following:

[0080] Step 410: With the minimum value of the loss function as the objective, train a preset deep neural network based on the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting the new energy consumption ratio contribution score of the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

[0081] To further improve the reliability of model mapping learning, in the new energy consumption ratio contribution assessment model training method provided in this application embodiment, the historical day-ahead power prediction data and the historical day-ahead scheduling plan data are both time series data; correspondingly, the deep neural network includes: LSTM model.

[0082] It is understandable that the LSTM model refers to the Long Short-Term Memory (LSTM) model.

[0083] To further improve the effectiveness of quantifying the contribution of renewable energy consumption ratio, in the renewable energy consumption ratio contribution assessment model training method provided in this application embodiment, step 230 of the renewable energy consumption ratio contribution assessment model training method specifically includes the following:

[0084] Based on the preset formula for the contribution score of renewable energy consumption ratio, the historical renewable energy consumption ratio contribution score corresponding to each historical day-ahead scheduling plan sample is determined.

[0085] The quantitative formula for the contribution score of the new energy consumption ratio includes:

[0086]

[0087] In formula (1), S i Indicates the contribution score of the proportion of new energy consumption; C i This indicates the proportion of new energy consumption corresponding to each of the historical pre-dated scheduling plan samples; This indicates the proportion of new energy consumption on a given day under the target scheduling plan.

[0088] Based on the above-described embodiment of the new energy consumption ratio contribution assessment model training method, this application also provides an embodiment of the new energy consumption ratio contribution assessment method for integrated energy bases, see [link to embodiment]. Figure 3 The evaluation method for the contribution of new energy consumption ratio in the comprehensive energy base specifically includes the following:

[0089] Step 500: Obtain the pre-scheduling plan data and corresponding day-ahead power forecast data of the integrated energy base.

[0090] Step 600: Input the day-ahead scheduling plan data and the corresponding day-ahead power prediction data into the renewable energy consumption ratio contribution evaluation model, so that the renewable energy consumption ratio contribution evaluation model outputs the renewable energy consumption ratio contribution score corresponding to the day-ahead scheduling plan data; wherein, the renewable energy consumption ratio contribution evaluation model is pre-trained based on the renewable energy consumption ratio contribution evaluation model training method.

[0091] The new energy consumption ratio contribution assessment model in the comprehensive energy base new energy consumption ratio contribution assessment method provided in this application can be implemented based on the processing flow of the new energy consumption ratio contribution assessment model training method in the above embodiments. Its function will not be repeated here, but can be referred to the detailed description of the above new energy consumption ratio contribution assessment model training method embodiments.

[0092] As can be seen from the above description, the new energy consumption ratio contribution assessment method provided in this application embodiment can effectively improve the training effectiveness and reliability of the new energy consumption ratio contribution assessment model, improve the accuracy and effectiveness of the new energy consumption ratio contribution assessment results, play an auxiliary role in scheduling decision-making, avoid energy waste caused by centralized adjustments to meet standards, and effectively improve the rationality and reliability of energy allocation in comprehensive energy bases.

[0093] From a software perspective, this application also provides a training device for all or part of the new energy consumption ratio contribution assessment model training method, see [link to relevant documentation]. Figure 4 The new energy consumption ratio contribution assessment model training device is connected to both the database of the integrated energy base and the new energy consumption ratio contribution assessment device. It retrieves historical data from the database and sends the trained model to the new energy consumption ratio contribution assessment device for online application. The new energy consumption ratio contribution assessment model training device specifically includes the following components:

[0094] Target planning module 10 is used to construct a target scheduling plan that meets the annual renewable energy consumption ratio of the integrated energy base.

[0095] The scoring calculation module 20 is used to determine the historical new energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base based on the target scheduling plan.

[0096] The dataset generation module 30 is used to generate a dataset based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score.

[0097] The model training module 40 is used to train a preset deep neural network using the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting the new energy consumption ratio contribution score of the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

[0098] The embodiments of the new energy consumption ratio contribution assessment model training device provided in this application can be used to execute the processing flow of the embodiments of the new energy consumption ratio contribution assessment model training method in the above embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the embodiments of the new energy consumption ratio contribution assessment model training method.

[0099] As can be seen from the above description, the training device for the new energy consumption ratio contribution assessment model provided in this application embodiment can effectively improve the training effectiveness and reliability of the new energy consumption ratio contribution assessment model, improve the accuracy and effectiveness of the new energy consumption ratio contribution assessment results, play an auxiliary role in scheduling decision-making, avoid energy waste caused by centralized adjustment to meet standards, and effectively improve the rationality and reliability of energy allocation in comprehensive energy bases.

[0100] From a software perspective, this application also provides a device for performing all or part of the renewable energy consumption ratio contribution assessment method described above, see [link to relevant documentation]. Figure 5 The renewable energy consumption ratio contribution assessment device is communicatively connected to both the renewable energy consumption ratio contribution assessment model training device and the user's client device. This allows it to receive the renewable energy consumption ratio contribution assessment model from the day-ahead scheduling plan model training device and send the predicted power output scheduling plan data to the client device for user viewing. Specifically, the renewable energy consumption ratio contribution assessment device includes the following components:

[0101] Data acquisition module 50 is used to acquire the pre-schedule planning data and the corresponding day-ahead power forecast data of the integrated energy base;

[0102] The model prediction module 60 is used to input the day-ahead scheduling plan data and the corresponding day-ahead power prediction data into the renewable energy consumption ratio contribution assessment model, so that the renewable energy consumption ratio contribution assessment model outputs the renewable energy consumption ratio contribution score corresponding to the day-ahead scheduling plan data; wherein, the renewable energy consumption ratio contribution assessment model is pre-trained based on the renewable energy consumption ratio contribution assessment model training method.

[0103] The embodiments of the renewable energy consumption ratio contribution assessment device provided in this application can be used to execute the processing flow of the renewable energy consumption ratio contribution assessment method in the above embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above renewable energy consumption ratio contribution assessment method embodiments.

[0104] As can be seen from the above description, the new energy consumption ratio contribution assessment device provided in this application embodiment can effectively improve the training effectiveness and reliability of the new energy consumption ratio contribution assessment model, improve the accuracy and effectiveness of the new energy consumption ratio contribution assessment results, play an auxiliary role in scheduling decision-making, avoid energy waste caused by centralized adjustment to meet standards, and effectively improve the rationality and reliability of energy allocation in comprehensive energy bases.

[0105] It is understood that the training portion of the renewable energy consumption ratio contribution assessment model training device, and the assessment portion of the renewable energy consumption ratio contribution assessment device, can be completed in the client device. The specific selection can be based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations in this regard. If all operations are completed in the client device, the client device may further include a processor for the specific processing of the renewable energy consumption ratio contribution assessment model training and the renewable energy consumption ratio contribution assessment.

[0106] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0107] The server and the client device can communicate using any suitable network protocol, including those not yet developed as of the date of this application. Such network protocols may include, for example, TCP / IP, UDP / IP, HTTP, HTTPS, etc. Furthermore, such network protocols may also include RPC (Remote Procedure Call Protocol) and REST (Representational State Transfer Protocol) protocols used on top of the aforementioned protocols.

[0108] To further illustrate this solution, this application also provides a specific application example of a renewable energy consumption ratio contribution assessment model training and a renewable energy consumption ratio contribution assessment method. This method can assess the contribution of day-ahead scheduling plans to the annual renewable energy consumption ratio. First, it uses a scoring method to score the contribution of daily scheduling arrangements in historical data to the corresponding annual renewable energy consumption ratio. Then, it uses day-ahead wind and solar power forecast data and day-ahead scheduling plans from historical data as input, and the corresponding scores as the target output to train a deep neural network model. After training, the network model can use the day-ahead power forecast data and day-ahead scheduling plans as input to output a score on the contribution of the scheduling plan to the annual renewable energy consumption ratio, thereby assisting dispatchers in making further decisions.

[0109] See Figure 6 The new energy consumption ratio contribution assessment model training and new energy consumption ratio contribution assessment method provided in this application example specifically include the following:

[0110] S1. Based on historical daily wind and solar power monitoring data, establish a dispatch plan to maximize wind and solar power generation.

[0111] S2. Calculate the annual renewable energy consumption ratio under this scheduling plan. If the target ratio is reached or exceeded, proceed to step S3. If the consumption ratio is not reached, reduce the daily thermal power output plan ΔR. T This will just meet the requirement of renewable energy consumption ratio. The target scheduling plan at this point is...

[0112]

[0113] In the formula These represent the output percentages of wind power, photovoltaic power, and thermal power at time j on day i, respectively. This dispatch plan can meet the annual renewable energy consumption ratio and is called the target dispatch plan.

[0114] S3. Compare the daily day-ahead scheduling plans in the historical data with the target scheduling plan, and calculate the proportion of new energy consumption for that day under the target scheduling plan. The proportion of renewable energy consumption under the current dispatch plan and historical data (C) i The rating of the dispatch plan for that day is:

[0115]

[0116] S4. Establish a training dataset consisting of day-ahead wind power forecast data, day-ahead photovoltaic power forecast data, day-ahead dispatch plans, and corresponding renewable energy consumption ratio scores. The composition of a single sample is shown in the following formula:

[0117]

[0118] In the formula, the left side represents the model input, which includes wind power prediction data P. Wi Photovoltaic power forecast data P Pi The proportion of wind power in the current dispatch plan is R. Wi The photovoltaic ratio of the current dispatch plan is R. Pi The proportion of thermal power in the current dispatch plan is R. Ti The right side shows the model's target output, which is the score S for the proportion of new energy consumption in the current day's scheduling plan. i .

[0119] S5. Establish the model, taking P into account Wi P Pi R Wi R Pi R Ti All data are time series. This example uses a deep neural network model based on the LSTM module; see [link to specific structure] for details. Figure 7 The LSTM model includes a network consisting of multiple sequentially connected LSTM layers, and a multilayer perceptron (MLP) connected to the network.

[0120] S6. Establish the loss function:

[0121]

[0122] S7. Use the dataset established in S4 and the loss function in S6 to train the model in S5 to obtain the trained model.

[0123] S8. Input the day-ahead wind power forecast data, day-ahead photovoltaic power forecast data, and day-ahead dispatch plan into the model trained in S7 to obtain the renewable energy consumption ratio score of the day-ahead dispatch plan. The higher the score, the higher the contribution of the day-ahead dispatch plan to the annual renewable energy consumption ratio.

[0124] In summary, the renewable energy consumption ratio contribution assessment model training and method provided in this application offer a quantitative scoring method for the annual renewable energy consumption ratio contribution of historical day-ahead scheduling plans. The network structure takes power prediction data and day-ahead scheduling plans as inputs and outputs renewable energy consumption contribution scores. It proposes a complete process for establishing a dataset by quantitatively scoring the renewable energy consumption ratio contribution of historical day-ahead scheduling plans, and then training a deep learning network using this dataset to estimate the renewable energy consumption ratio contribution of existing day-ahead scheduling plans. This allows for scoring the contribution of day-ahead scheduling plans to the annual renewable energy consumption ratio after they are generated, thus assisting in subsequent scheduling optimization or decision-making.

[0125] This application also provides an electronic device, which may include a processor, a memory, a receiver, and a transmitter. The processor is used to execute the new energy consumption ratio contribution assessment model training method or the new energy consumption ratio contribution assessment method mentioned in the above embodiments. The processor and the memory can be connected via a bus or other means, taking a bus connection as an example. The receiver can be connected to the processor and the memory via wired or wireless means.

[0126] The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0127] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the new energy consumption ratio contribution assessment model training method or the new energy consumption ratio contribution assessment method in the embodiments of this application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the new energy consumption ratio contribution assessment model training method or the new energy consumption ratio contribution assessment method in the above method embodiments.

[0128] The memory 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 by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0129] The one or more modules are stored in the memory, and when executed by the processor, the training method for the new energy consumption ratio contribution assessment model or the new energy consumption ratio contribution assessment method in the embodiment are executed.

[0130] In some embodiments of this application, the user equipment may include a processor, a memory, and a transceiver unit. The transceiver unit may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected via a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.

[0131] As one implementation method, the functions of the receiver and transmitter in this application can be implemented by transceiver circuits or dedicated transceiver chips, and the processor can be implemented by dedicated processing chips, processing circuits or general-purpose chips.

[0132] As another implementation approach, the server provided in this application embodiment can be implemented using a general-purpose computer. That is, the program code implementing the processor, receiver, and transmitter functions is stored in memory, and the general-purpose processor implements the processor, receiver, and transmitter functions by executing the code in memory.

[0133] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the steps of the aforementioned new energy consumption ratio contribution assessment model training method or new energy consumption ratio contribution assessment method. The computer-readable storage medium can be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium known in the art.

[0134] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave.

[0135] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0136] In this application, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0137] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to the embodiments of this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A training method for evaluating the contribution of new energy consumption ratio, characterized in that, include: Construct a scheduling plan that meets the annual target for the proportion of new energy consumption in the comprehensive energy base; Based on the target scheduling plan, determine the historical renewable energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base; A dataset is generated based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score. A preset deep neural network is trained using the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting a new energy consumption ratio contribution score of the day-ahead scheduling plan data based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base. The historical renewable energy consumption ratio contribution score, determined based on the historical day-ahead scheduling plan data of the integrated energy base according to the target scheduling plan, includes: The historical day-ahead power prediction data samples corresponding to multiple historical sampling time points of the integrated energy base are obtained. Each historical day-ahead power prediction data sample includes: historical day-ahead photovoltaic power prediction data and historical day-ahead wind power prediction data. Obtain the historical day-ahead scheduling plan data sample corresponding to each of the historical day-ahead power prediction data samples for the next day. Each historical day-ahead scheduling plan sample includes: the historical day-ahead scheduling plan photovoltaic ratio, the historical day-ahead scheduling plan wind power ratio, and the historical day-ahead scheduling plan thermal power ratio. Based on the proportion of new energy consumption on the day under the target scheduling plan and the proportion of new energy consumption corresponding to each of the historical day-ahead scheduling plan samples, the historical new energy consumption ratio contribution score corresponding to each of the historical day-ahead scheduling plan samples is determined respectively. Before training the preset deep neural network using the dataset, the method further includes: Construct a loss function to represent the difference between the contribution score of new energy consumption ratio output by the deep neural network and the contribution score of new energy consumption ratio. Correspondingly, training a preset deep neural network using the dataset includes: With the goal of minimizing the loss function, a pre-defined deep neural network is trained based on the dataset. The step involves determining the historical renewable energy consumption contribution score for each historical day-ahead scheduling plan sample based on the renewable energy consumption ratio of the current day under the target scheduling plan and the renewable energy consumption ratio corresponding to each historical day-ahead scheduling plan sample, including: Based on the preset formula for the contribution score of renewable energy consumption ratio, the historical renewable energy consumption ratio contribution score corresponding to each historical day-ahead scheduling plan sample is determined. The quantitative formula for the contribution score of the new energy consumption ratio includes: （1） In formula (1), The score represents the contribution of the proportion of new energy consumption. This indicates the proportion of new energy consumption corresponding to each of the historical pre-dated scheduling plan samples; This indicates the proportion of new energy consumption on a given day under the target scheduling plan.

2. The method for evaluating the contribution of new energy consumption ratio according to claim 1, characterized in that, The historical daytime power prediction data and historical daytime scheduling plan data are both time series data. Correspondingly, the deep neural network includes: LSTM model.

3. A method for assessing the contribution of new energy consumption ratio in a comprehensive energy base, characterized in that, include: Obtain the pre-dispatch plan data and corresponding day-ahead power forecast data for the integrated energy base; The daytime scheduling plan data and the corresponding daytime power prediction data are input into the renewable energy consumption ratio contribution assessment model so that the renewable energy consumption ratio contribution assessment model outputs the renewable energy consumption ratio contribution score corresponding to the daytime scheduling plan data. The new energy consumption ratio contribution assessment model is pre-trained based on the new energy consumption ratio contribution assessment training method described in any one of claims 1 to 2.

4. A training device for assessing the contribution of new energy consumption ratio, based on the training method for assessing the contribution of new energy consumption ratio as described in any one of claims 1 to 2; The features include: The target plan construction module is used to construct a target scheduling plan that meets the annual renewable energy consumption ratio of the integrated energy base; The scoring calculation module is used to determine the historical renewable energy consumption ratio contribution score of the historical day-ahead scheduling plan data of the integrated energy base based on the target scheduling plan; The dataset generation module is used to generate a dataset based on the correspondence between the historical day-ahead scheduling plan data, the historical day-ahead power prediction data corresponding to the historical day-ahead scheduling plan data, and the historical renewable energy consumption ratio contribution score. The model training module is used to train a preset deep neural network using the dataset to obtain a new energy consumption ratio contribution evaluation model for outputting a new energy consumption ratio contribution score of the new energy base based on the day-ahead scheduling plan data and the corresponding day-ahead power prediction data of the integrated energy base.

5. A device for evaluating the contribution of renewable energy consumption ratio in a comprehensive energy base, based on the method for evaluating the contribution of renewable energy consumption ratio in a comprehensive energy base as described in any one of claims 3; characterized in that, include: The data acquisition module is used to acquire the pre-scheduling plan data and the corresponding day-ahead power forecast data of the integrated energy base; The model prediction module is used to input the day-ahead scheduling plan data and the corresponding day-ahead power prediction data into the renewable energy consumption ratio contribution assessment model, so that the renewable energy consumption ratio contribution assessment model outputs the renewable energy consumption ratio contribution score corresponding to the day-ahead scheduling plan data. The new energy consumption ratio contribution assessment model is pre-trained based on the new energy consumption ratio contribution assessment training method described in any one of claims 1 to 2.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the new energy consumption ratio contribution assessment training method as described in any one of claims 1 to 2, or implements the new energy consumption ratio contribution assessment method for integrated energy bases as described in claim 3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the new energy consumption ratio contribution assessment training method as described in any one of claims 1 to 2, or implements the new energy consumption ratio contribution assessment method of the integrated energy base as described in claim 3.

Images