Power grid control method, control device and electronic device

Abstract

This application provides a power grid control method, control device, and electronic device. The method includes: acquiring first data from a new energy power generation station within a first historical time period; processing the first data using a prediction model to obtain a power generation prediction result for a first predetermined day after the first historical time period; constructing a power grid dispatch model, at least inputting the power generation prediction result into the dispatch model to obtain a dispatch plan, and executing the dispatch plan to control the power grid. This method solves the problem of low accuracy in power grid control in the prior art.

Description

Technical Field

[0001] This application relates to the field of power grid dispatching, and more specifically, to a power grid control method, control device, computer-readable storage medium, and electronic device. Background Technology

[0002] With the depletion of fossil fuels and the deterioration of the ecological environment worldwide, the dual pressures are driving the rapid development of renewable energy. Establishing a high-quality, efficient, and low-carbon energy interconnection system for the new era has become an inevitable choice for countries around the world to achieve sustainable energy development. Against the backdrop of global energy transition and with strong support from various countries, renewable energy power generation technology has been deeply developed. Renewable energy power generation is mainly connected to the grid through centralized or distributed methods. This not only offers geographical flexibility, allowing for better distribution of power transmission demand across different regions, but also, as a pollution-free clean energy source, reduces environmental pollution from traditional power generation methods and saves on power generation costs. These advantages have led to a year-on-year increase in the proportion of distributed renewable energy power generation connected to the distribution network. However, as an important supplement to centralized power generation, the increasing number of distributed renewable energy power generation connections will bring energy production and trading closer to the demand side. The original traditional radial network is transforming into a complex network interconnected with multiple energy sources and multiple users. The previous source-grid-load energy flow is no longer unidirectional but bidirectional, bringing new challenges and tests to the power grid's power quality and voltage optimization control.

[0003] Existing technologies include methods for optimizing power grid control through model prediction. For example, a method for coordinated optimization control of active and reactive power in a distributed photovoltaic (PV) distribution network is disclosed. This method includes: based on model predictive control, dividing the distribution network system control process into long-term optimization control and short-term optimization control according to control objectives and control variables at different time scales, and establishing long-term and short-term optimization control models; transforming the solution problems of long-term and short-term optimization control into second-order cone programming problems; the long-term optimization control model uses PV power output and load demand forecast information to solve the active and reactive power output of each controllable device through multi-step rolling optimization, while the short-term optimization control model uses the solution results of the long-term optimization control model as a benchmark value to solve the incremental active and reactive power output of each controllable device. However, the above scheme does not perform coordinated optimization control based on the power generation of new energy types, leading to inaccurate optimization.

[0004] Therefore, there is an urgent need for a high-precision power grid control method. Summary of the Invention

[0005] The main objective of this application is to provide a power grid control method, control device, computer-readable storage medium, and electronic device to at least solve the problem of low accuracy in power grid control in the prior art.

[0006] To achieve the above objectives, according to one aspect of this application, a power grid control method is provided, comprising: acquiring first data from a new energy power station within a first historical time period, wherein the new energy power station includes a photovoltaic power station and a wind power station; the first data including at least a first power generation of the photovoltaic power station and a second power generation of the wind power station; processing the first data using a prediction model to obtain a power generation prediction result for a first predetermined day after the first historical time period, wherein the prediction model is trained using multiple sets of historical data, each set of historical data including second data within a second historical time period and third data for a second predetermined day; the second data including at least a third power generation of the photovoltaic power station and a fourth power generation of the wind power station for each day within the second historical time period; and the third data including at least a fifth power generation of the photovoltaic power station and a sixth power generation of the wind power station for the second predetermined day; and the power generation prediction result... The system includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A grid dispatch model is constructed, which includes an optimization objective and constraints. The optimization objective is set at least based on the grid operating cost, and the constraints are set at least based on power balance constraints. The grid is the equipment that connects the power generated by the new energy power station to the grid. The power generation forecast results are input into the dispatch model to obtain a dispatch plan. The dispatch plan is executed to control the grid. The dispatch plan specifies the amount of power that the seventh power generation and the eighth power generation need to be connected to the grid.

[0007] Optionally, before processing the first data using a prediction model to obtain the power generation prediction result for a predetermined day after the historical time period, the method further includes an acquisition step, acquiring multiple sets of the historical data; a preprocessing step, performing data preprocessing on the second data in the multiple sets of historical data to obtain multiple sets of fourth data; an input step, inputting the multiple sets of fourth data into a convolutional neural network model; and a training step, training the convolutional neural network model to obtain the prediction model.

[0008] Optionally, the preprocessing step includes cleaning the second data to obtain cleaned second data; imputing missing data in the cleaned second data to obtain imputed second data; and normalizing the imputed second data to obtain the fourth data.

[0009] Optionally, the training step further includes setting at least a set number of iterations to train the convolutional neural network, obtaining at least a plurality of ninth power generation data for the photovoltaic power station and tenth power generation data for the wind power station on the second predetermined day, as well as the loss function curve corresponding to the number of training iterations, wherein each set of fourth data includes one ninth power generation data and one tenth power generation data; a comparison step, comparing the ninth power generation data and the tenth power generation data obtained by training each set of fourth data with the third data corresponding to each set of fourth data to obtain a plurality of first differences, averaging the plurality of first differences to obtain a second difference; a judgment step, determining whether the trained convolutional neural network model is the prediction model based on whether the second difference is within a preset range and whether the loss function curve is in a convergent state, wherein the preset range is set according to the actual situation.

[0010] Optionally, the determination step includes determining the trained convolutional neural network model as the prediction model when the second difference is within the preset range and the loss function curve is in a convergent state; adjusting the parameters of the convolutional neural network model when the second difference is not within the preset range or the loss function curve is not in a convergent state, and sequentially repeating the input step, the training step, and the comparison step at least once until the second difference is within the preset range, and determining the trained convolutional neural network model as the prediction model, wherein the parameters include at least the number of iterations.

[0011] Optionally, constructing the optimization objective of the scheduling model includes constructing the operating cost of the power grid based on the power grid's loss cost, power purchase cost, and power sales revenue, wherein the operating cost C of the power grid... w The calculation formula is C W =C K +C T In the formula, C K C represents the loss cost of the power grid. T The power grid's electricity purchase cost and electricity sales revenue are defined; at least based on the power grid's capacity to absorb the power generated by the photovoltaic power station and the power grid's capacity to absorb the power generated by the wind power station, a renewable energy absorption cost for the power grid is constructed, wherein the renewable energy absorption cost C′ is...Dis The calculation formula is In the formula, P WT,dis (t) represents the grid's capacity to absorb the power generated by the photovoltaic power station, P PV,dis (t) represents the grid's capacity to absorb the power generated by the wind power station, and C(t) represents the electricity price at time t. The optimization objective of the scheduling model is constructed based on the minimum sum of the grid's operating cost and the cost of absorbing new energy.

[0012] Optionally, constructing the constraints of the scheduling model includes constructing a first constraint based on the maximum power generation of the photovoltaic power station and the seventh power generation, wherein the first constraint is P. PV (t)≤P PV,pre (t), where P PV (t) represents the maximum power generation of the photovoltaic power station, P PV,pre (t) represents the seventh power generation; based on the maximum power generation of the wind power station and the eighth power generation, a second constraint is constructed, wherein the second constraint is P. WT (t)≤P WT,pre (t), where P WT (t) represents the maximum power generation of the wind power station, P WT,pre (t) represents the eighth power generation; the power balance constraint is constructed based at least on the power purchased by the power grid and the energy storage capacity on the user side. The first constraint, the second constraint, and the power balance constraint constitute the constraint conditions of the scheduling model, wherein the power balance constraint is P. WT (t)+P PV (t)+P g (t)=P ESS (t)+P EV (t)+P load (t)+P loss (t), where P g (t) represents the power purchased by the power grid, P ESS (t) represents the energy storage power on the user side, P load (t) represents the power of the fixed load on the user side, P loss (t) represents the power lost on the user side, which is the power lost during the power transmission to the user side.

[0013] According to another aspect of this application, a power grid control device is provided, comprising:

[0014] The acquisition unit acquires the first data of the new energy power station within a first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0015] The processing unit processes the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station for the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same.

[0016] A construction unit is used to construct a power grid scheduling model. The scheduling model includes an optimization objective and constraints. The optimization objective is set based at least on the operating cost of the power grid, and the constraints are set based at least on power balance constraints. The power grid is the equipment used to connect the electricity generated by the new energy power plant to the grid.

[0017] The execution unit inputs at least the power generation forecast results into the scheduling model to obtain a scheduling plan, executes the scheduling plan to control the power grid, and the scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0018] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the above-described power grid control methods.

[0019] According to another aspect of this application, an electronic device is provided, the electronic device including one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a control method for performing any of the above-described power grids.

[0020] Applying the technical solution of this application, firstly, first data of a new energy power station within a first historical time period is obtained. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station. Secondly, a prediction model is used to process the first data to obtain a power generation prediction result for a first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for a second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station for the second predetermined day. The power generation forecast includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A grid dispatch model is constructed, which includes optimization objectives and constraints. The grid is the equipment for connecting the power generated by the new energy power station to the grid. At least the power generation forecast results are input into the dispatch model to obtain a dispatch plan. The dispatch plan is executed to control the grid. The dispatch plan is the amount of electricity that the seventh and eighth power generation needs to be connected to the grid. Compared with existing technologies, the present application's solution uses the historical power generation of photovoltaic power plants and wind power plants to train a convolutional neural network model to obtain a prediction model. This prediction model is then used to predict the power generation of photovoltaic power plants and wind power plants on a predetermined date, respectively. The prediction results are then used to make a scheduling plan for the power grid before the predetermined date, thereby achieving more precise control of the power grid and further solving the problem of low accuracy in power grid control in existing technologies. Attached Figure Description

[0021] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0022] Figure 1 A hardware structure block diagram of a mobile terminal for executing a power grid control method according to an embodiment of this application is shown;

[0023] Figure 2 A schematic flowchart of a power grid control method according to an embodiment of this application is shown;

[0024] Figure 3 A structural block diagram of a power grid control device according to an embodiment of this application is shown. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] As described in the background section, the existing technology suffers from low precision in power grid control. To address this issue, embodiments of this application provide a power grid control method, control device, computer-readable storage medium, and electronic device.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a power grid control method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] This embodiment provides a method for controlling a power grid that operates on a mobile terminal, computer terminal, or similar computing device. 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.

[0033] Figure 2 This is a flowchart of a power grid control method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0034] Step S201: Obtain the first data of the new energy power station within the first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0035] Specifically, the data for predicting new energy power plants mentioned above includes: historical power generation data of photovoltaic power generation in the power grid, historical power generation data of wind power generation, influencing factors of wind power generation, and influencing factors of photovoltaic power generation. Among them, the influencing factors of photovoltaic power generation include temperature data, humidity data, and radiation data; the influencing factors of wind turbine power generation include wind speed data and temperature data.

[0036] Step S202: Process the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0037] Specifically, the prediction model is a deep learning model (convolutional neural network model), which consists of a data input layer, a hidden layer with a non-linear activation function, and an output layer. The model's predictive ability is improved by training on historical datasets. The training process involves inputting the dataset into the convolutional neural network model, which outputs a prediction result (predicted photovoltaic power generation and predicted wind power generation). The prediction result is compared with the training set, and the convolutional neural network model automatically adjusts various parameters until the model converges, indicating that the model training is complete. Then, by inputting the data from the six days prior to the prediction date, the convolutional neural network model will predict the power generation data for the prediction date.

[0038] Specifically, the first and second historical time periods can be set to six days, specifically from Monday to Saturday. Then, the first and second reservation days can be set to Sunday, where the first and second intervals are from Saturday to Sunday, and the values ​​of the first and second intervals remain the same. Alternatively, the first and second historical time periods can be set to thirty days, specifically from the 1st to the 30th of each month. Then, the first and second reservation days can be set to the 31st, where the first and second intervals are from the 30th to the 31st, and the values ​​of the first and second intervals remain the same.

[0039] Step S203: Construct a grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the grid operating cost, and the constraints are set based at least on power balance constraints. The grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0040] Specifically, the construction of a power grid dispatching model requires consideration of the following key steps: First, the optimization objective needs to be determined. Typically, the optimization objective of power grid dispatching is to minimize the operating costs of the power grid, including fuel costs, transmission losses, and equipment operating costs. Depending on the actual situation, other optimization objectives can also be considered, such as maximizing the utilization of renewable energy generation and reducing carbon emissions. Second, after determining the optimization objective, constraints need to be considered. Power balance constraints are the most fundamental constraints, ensuring the balance between power supply and demand and avoiding overload or insufficient power supply. Finally, a mathematical model needs to be established: based on the determined optimization objective and constraints, a mathematical model for power grid dispatching is established. Linear programming, integer programming, and mixed-integer programming are commonly used mathematical tools to describe the operating state and optimization problem of the power grid to achieve the optimal dispatching scheme.

[0041] Step S204: At least the above power generation forecast results are input into the above scheduling model to obtain a scheduling plan, and the above scheduling plan is executed to control the above power grid. The above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0042] Specifically, firstly, the power generation forecast results are input into the dispatch model, which generates a dispatch plan based on the forecast data and grid demand. This dispatch plan includes the amount of electricity that the seventh and eighth generating units need to connect to the grid. Then, corresponding operations are performed according to this dispatch plan, such as adjusting generator output power and coordinating the operation of different power sources to ensure the normal operation of the grid and meet demand. Through this process, power generation forecast results can be effectively used to optimize grid operation and improve grid reliability and efficiency.

[0043] In the above embodiments, firstly, first data from new energy power plants within a first historical time period is acquired. The new energy power plants include photovoltaic power plants and wind power plants. The first data includes at least the first power generation of the photovoltaic power plants and the second power generation of the wind power plants. Secondly, a prediction model is used to process the first data to obtain a power generation prediction result for a first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for a second predetermined day. The second data includes at least the third power generation of the photovoltaic power plants and the fourth power generation of the wind power plants for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power plants and the sixth power generation of the wind power plants for the second predetermined day. The electricity generation forecast results include the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A grid dispatch model is constructed, which includes optimization objectives and constraints. The grid is the equipment for connecting the electricity generated by the new energy power station to the grid. At least the power generation forecast results are input into the dispatch model to obtain a dispatch plan. The dispatch plan is executed to control the grid. The dispatch plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid. Compared with existing technologies, the present application's solution uses the historical power generation of photovoltaic power plants and wind power plants to train a convolutional neural network model to obtain a prediction model. This prediction model is then used to predict the power generation of photovoltaic power plants and wind power plants on a predetermined date, respectively. The prediction results are then used to make a scheduling plan for the power grid before the predetermined date, thereby achieving more precise control of the power grid and further solving the problem of low accuracy in power grid control in existing technologies.

[0044] In one embodiment of this application, before processing the first data using a prediction model to obtain the power generation prediction result for a predetermined day after the historical time period, the method further includes: an acquisition step, acquiring multiple sets of the historical data; a preprocessing step, performing data preprocessing on the second data from the multiple sets of historical data to obtain multiple sets of fourth data; an input step, inputting the multiple sets of fourth data into a convolutional neural network model; and a training step, training the convolutional neural network model to obtain the prediction model. In this method, by training with multiple sets of historical data to obtain a prediction model, the power generation situation within a specific future time period can be predicted more accurately.

[0045] To further improve the quality and usability of the second data, in one embodiment of this application, the preprocessing steps include: cleaning the second data to obtain cleaned second data; filling in missing data in the cleaned second data to obtain filled second data; and normalizing the filled second data to obtain the fourth data.

[0046] Specifically, data cleaning involves filtering out outliers in the data, deleting the data of outliers, and then supplementing the data at that moment with the average of the values ​​of the outliers at the previous moment and the values ​​at the next moment. Data cleaning also includes processing duplicate data by deletion.

[0047] Specifically, data completion involves using the average of the values ​​from the previous time step and the values ​​from the next time step to fill in missing data.

[0048] Specifically, the formula for data normalization is:

[0049]

[0050] Where, x in Here are the normalized data, and x is the original data. min x is the minimum value in the data. max This represents the maximum value in the data.

[0051] In another embodiment, the training steps further include: setting at least a set number of iterations to train the convolutional neural network, obtaining at least a plurality of ninth power generation figures for the photovoltaic power station and tenth power generation figures for the wind power station on the second predetermined day, and loss function curves corresponding to the number of training iterations, wherein each set of the fourth data includes one ninth power generation figure and one tenth power generation figure; a comparison step, comparing the ninth power generation figure and the tenth power generation figure obtained from training each set of the fourth data with the third data corresponding to each set of the fourth data, obtaining a plurality of first differences, averaging the plurality of first differences to obtain a second difference; and a judgment step, determining whether the trained convolutional neural network model is the prediction model based on whether the second difference is within a preset range and whether the loss function curve is in a convergent state, wherein the preset range is set according to the actual situation. In this method, by training and evaluating the model, the model is further ensured to have higher prediction accuracy and stability.

[0052] To more effectively improve model performance, in one embodiment of this application, the above-mentioned judgment step includes: when the second difference is within the preset range and the loss function curve is in a convergent state, determining that the trained convolutional neural network model is the prediction model; when the second difference is not within the preset range or the loss function curve is not in a convergent state, adjusting the parameters of the convolutional neural network model, and sequentially repeating the input step, the training step, and the comparison step at least once, until the second difference is within the preset range, determining that the trained convolutional neural network model is the prediction model, wherein the parameters include at least the number of iterations.

[0053] Specifically, for a convolutional neural network model to converge, at least three metrics must be met: mean squared error (MSE), mean absolute percentage error (MAS), and prediction accuracy. MSE is a commonly used metric to assess the difference between the model's predicted and actual values. A smaller MSE value indicates a smaller difference between the predicted and actual values, and a higher degree of model convergence. MAS assesses the percentage difference between the model's predicted and actual values. A smaller MAS value indicates a smaller percentage difference between the predicted and actual values, and a higher degree of model convergence. Prediction accuracy is a comprehensive metric, typically including precision, recall, and F1 score. Higher prediction accuracy indicates higher accuracy in classification or regression tasks, and a better degree of model convergence.

[0054] In another embodiment, the optimization objective of constructing the above-described scheduling model includes: constructing the operating cost of the power grid based on the power grid's loss cost, electricity purchase cost, and electricity sales revenue, wherein the operating cost C of the power grid... w The calculation formula is C W =C K +C T In the formula, C K For the aforementioned losses and costs of the aforementioned power grid, C T The above-mentioned electricity purchase cost and electricity sales revenue of the aforementioned power grid; at least based on the power grid's capacity to absorb the power generated by the aforementioned photovoltaic power station and the power grid's capacity to absorb the power generated by the aforementioned wind power station, construct the renewable energy absorption cost of the aforementioned power grid, wherein the aforementioned renewable energy absorption cost C′ Dis The calculation formula is In the formula, P WT,dis (t) represents the grid's capacity to absorb the power generated by the photovoltaic power station, P PV,dis C(t) represents the grid's capacity to absorb the power generated by the wind power station, and C(t) represents the electricity price at time t. Based on the minimum sum of the grid's operating costs and the renewable energy absorption costs, the optimization objective of the scheduling model is constructed. This method further improves the grid's operating efficiency and reliability by setting the optimization objective.

[0055] Specifically, the optimization objective is, firstly, to minimize the total grid operating cost and prioritize the absorption of renewable energy. The total grid operating cost consists of grid operating costs, loss costs, electricity purchase costs, and electricity sales revenue. The cost of absorbing renewable energy is determined by the absorption capacity of photovoltaic power generation, the absorption capacity of wind power generation, and electricity prices.

[0056] To further improve the efficiency of the power grid system, in one embodiment of this application, the constraints for constructing the above-mentioned scheduling model include: constructing a first constraint based on the maximum power generation of the photovoltaic power station and the seventh power generation, wherein the first constraint is P. PV (t)≤P PV,pre (t), where P PV (t) represents the maximum power generation of the aforementioned photovoltaic power station, P PV,pre (t) represents the seventh power generation; based on the maximum power generation of the wind power station and the eighth power generation, a second constraint is constructed, wherein the second constraint is P. WT (t)≤P WT,pre (t), where P WT (t) represents the maximum power generation of the aforementioned wind power station, P WT,pre(t) represents the eighth power generation; based at least on the power purchased by the power grid and the energy storage capacity on the user side, the power balance constraint is constructed. The first constraint, the second constraint, and the power balance constraint constitute the constraints of the scheduling model. The power balance constraint is P. WT (t)+P PV (t)+P g (t)=P ESS (t)+P EV (t)+P load (t)+P loss (t), where P g (t) represents the power purchased by the aforementioned power grid, P ESS (t) represents the energy storage power on the user side, P load (t) represents the power of the fixed load on the user side mentioned above, P loss (t) represents the power lost on the user side, which is the power lost during the transmission of electricity to the user side.

[0057] Specifically, the constraints include photovoltaic (PV) output constraints, wind power output constraints, and power balance constraints. PV output constraints ensure that PV output does not exceed the predicted data, wind power output constraints ensure that wind power output does not exceed the predicted data, and power balance constraints ensure the balance between grid-purchased power, user-side energy storage power, stationary load power, and power loss.

[0058] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the power grid control method of this application will be described in detail below with reference to specific embodiments.

[0059] This embodiment relates to a specific power grid control method, including the following steps:

[0060] Step 1: Obtain multiple sets of historical data from new energy power plants, including photovoltaic power plants and wind power plants;

[0061] Step 2: Preprocess multiple sets of historical data to obtain the dataset used for model training;

[0062] Step 3: Establish a convolutional neural network model for predicting new energy power generation;

[0063] Step 4: Input the training set obtained in Step 2 into the convolutional neural network model in Step 3, and train the convolutional neural network model to obtain the prediction model;

[0064] Step 5: Use the prediction model to predict the first data of the new energy power station in the first historical time period to obtain the power generation of the new energy power station on the first predetermined day.

[0065] Step Six: Construct a power grid scheduling model;

[0066] Step 7: Input the power generation of the new energy power plant on the first predetermined day obtained in Step 5 into the grid dispatch model to obtain the grid dispatch plan, thereby realizing the control of the grid.

[0067] 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, and 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.

[0068] This application also provides a power grid control device. It should be noted that the power grid control device of this application can be used to execute the power grid control method provided in this application. This device 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 implements 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.

[0069] The following describes the power grid control device provided in the embodiments of this application.

[0070] Figure 3 This is a schematic diagram of a power grid control device according to an embodiment of this application. Figure 3 As shown, the device includes:

[0071] The acquisition unit 10 acquires the first data of the new energy power station within a first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0072] Specifically, the data for predicting new energy power plants mentioned above includes: historical power generation data of photovoltaic power generation in the power grid, historical power generation data of wind power generation, influencing factors of wind power generation, and influencing factors of photovoltaic power generation. Among them, the influencing factors of photovoltaic power generation include temperature data, humidity data, and radiation data; the influencing factors of wind turbine power generation include wind speed data and temperature data.

[0073] Processing unit 20 processes the first data using a prediction model to obtain a power generation prediction result for a first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0074] Specifically, the prediction model is a deep learning model (convolutional neural network model), which consists of a data input layer, a hidden layer with a non-linear activation function, and an output layer. The model's predictive ability is improved by training on historical datasets. The training process involves inputting the dataset into the convolutional neural network model, which outputs a prediction result (predicted photovoltaic power generation and predicted wind power generation). The prediction result is compared with the training set, and the convolutional neural network model automatically adjusts various parameters until the model converges, indicating that the model training is complete. Then, by inputting the data from the six days prior to the prediction date, the convolutional neural network model will predict the power generation data for the prediction date.

[0075] Specifically, the first and second historical time periods can be set to six days, specifically from Monday to Saturday. Then, the first and second reservation days can be set to Sunday, where the first and second intervals are from Saturday to Sunday, and the values ​​of the first and second intervals remain the same. Alternatively, the first and second historical time periods can be set to thirty days, specifically from the 1st to the 30th of each month. Then, the first and second reservation days can be set to the 31st, where the first and second intervals are from the 30th to the 31st, and the values ​​of the first and second intervals remain the same.

[0076] Construction unit 30 constructs a power grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the operating cost of the power grid, and the constraints are set based at least on power balance constraints. The power grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0077] Specifically, the construction of a power grid dispatching model requires consideration of the following key steps: First, the optimization objective needs to be determined. Typically, the optimization objective of power grid dispatching is to minimize the operating costs of the power grid, including fuel costs, transmission losses, and equipment operating costs. Depending on the actual situation, other optimization objectives can also be considered, such as maximizing the utilization of renewable energy generation and reducing carbon emissions. Second, after determining the optimization objective, constraints need to be considered. Power balance constraints are the most fundamental constraints, ensuring the balance between power supply and demand and avoiding overload or insufficient power supply. Finally, a mathematical model needs to be established: based on the determined optimization objective and constraints, a mathematical model for power grid dispatching is established. Linear programming, integer programming, and mixed-integer programming are commonly used mathematical tools to describe the operating state and optimization problem of the power grid to achieve the optimal dispatching scheme.

[0078] The execution unit 40 inputs the above power generation forecast results into the above scheduling model to obtain a scheduling plan, executes the above scheduling plan to control the above power grid, and the above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid respectively.

[0079] Specifically, firstly, the power generation forecast results are input into the dispatch model, which generates a dispatch plan based on the forecast data and grid demand. This dispatch plan includes the amount of electricity that the seventh and eighth generating units need to connect to the grid. Then, corresponding operations are performed according to this dispatch plan, such as adjusting generator output power and coordinating the operation of different power sources to ensure the normal operation of the grid and meet demand. Through this process, power generation forecast results can be effectively used to optimize grid operation and improve grid reliability and efficiency.

[0080] In the above embodiments, firstly, first data from new energy power plants within a first historical time period is acquired. The new energy power plants include photovoltaic power plants and wind power plants. The first data includes at least the first power generation of the photovoltaic power plants and the second power generation of the wind power plants. Secondly, a prediction model is used to process the first data to obtain a power generation prediction result for a first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for a second predetermined day. The second data includes at least the third power generation of the photovoltaic power plants and the fourth power generation of the wind power plants for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power plants and the sixth power generation of the wind power plants for the second predetermined day. The electricity generation forecast results include the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A grid dispatch model is constructed, which includes optimization objectives and constraints. The grid is the equipment for connecting the electricity generated by the new energy power station to the grid. At least the power generation forecast results are input into the dispatch model to obtain a dispatch plan. The dispatch plan is executed to control the grid. The dispatch plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid. Compared with existing technologies, the present application's solution uses the historical power generation of photovoltaic power plants and wind power plants to train a convolutional neural network model to obtain a prediction model. This prediction model is then used to predict the power generation of photovoltaic power plants and wind power plants on a predetermined date, respectively. The prediction results are then used to make a scheduling plan for the power grid before the predetermined date, thereby achieving more precise control of the power grid and further solving the problem of low accuracy in power grid control in existing technologies.

[0081] In one embodiment of this application, the acquisition unit further includes an acquisition module, a preprocessing module, an input module, and a training module. The acquisition module performs an acquisition step to acquire multiple sets of the aforementioned historical data. The preprocessing module performs a preprocessing step to preprocess the second data from the multiple sets of historical data to obtain multiple sets of fourth data. The input module performs an input step to input the multiple sets of fourth data into a convolutional neural network model. The training module performs a training step to train the convolutional neural network model to obtain the aforementioned prediction model. In this scheme, by training with multiple sets of historical data to obtain a prediction model, the power generation situation within a specific future time period can be predicted more accurately.

[0082] To further improve the quality and usability of the second data, in one embodiment of this application, the preprocessing module includes a data cleaning submodule, a data completion submodule, and a data normalization submodule. The data cleaning submodule is used to clean the second data to obtain the cleaned second data. The data completion submodule is used to complete the missing data in the cleaned second data to obtain the completed second data. The data normalization submodule is used to normalize the completed second data to obtain the fourth data.

[0083] Specifically, data cleaning involves filtering out outliers in the data, deleting the data of outliers, and then supplementing the data at that moment with the average of the values ​​of the outliers at the previous moment and the values ​​at the next moment. Data cleaning also includes processing duplicate data by deletion.

[0084] Specifically, data completion involves using the average of the values ​​from the previous time step and the values ​​from the next time step to fill in missing data.

[0085] Specifically, the formula for data normalization is:

[0086]

[0087] Where, x in Here are the normalized data, and x is the original data. min x is the minimum value in the data. max This represents the maximum value in the data.

[0088] In another embodiment, the training module further includes a training submodule, a comparison submodule, and a judgment submodule. The training submodule is used to train the convolutional neural network by setting at least a certain number of iterations, obtaining at least multiple ninth power generation values ​​of the photovoltaic power station and tenth power generation values ​​of the wind power station on the second predetermined day, as well as the corresponding loss function curves when the training count reaches the specified number of iterations. Each set of the fourth data includes one ninth power generation value and one tenth power generation value. The training submodule performs a comparison step, comparing the ninth and tenth power generation values ​​obtained from training each set of the fourth data with the corresponding third data for each set of the fourth data, obtaining multiple first differences, and averaging these multiple first differences to obtain a second difference value. The judgment submodule performs a judgment step, determining whether the trained convolutional neural network model is the prediction model based on whether the second difference value is within a preset range and whether the loss function curve is in a convergent state. The preset range is set according to actual conditions. In this scheme, the training and evaluation steps further ensure that the model has high prediction accuracy and stability.

[0089] To more effectively improve model performance, in one embodiment of this application, the judgment submodule includes a determination submodule and a repetition execution submodule. The judgment submodule is used to determine that the trained convolutional neural network model is the prediction model when the second difference is within the preset range and the loss function curve is in a convergent state. The repetition execution submodule is used to adjust the parameters of the convolutional neural network model when the second difference is not within the preset range or the loss function curve is not in a convergent state, and to sequentially repeat the input step, the training step, and the comparison step at least once until the second difference is within the preset range, thereby determining that the trained convolutional neural network model is the prediction model. The parameters include at least the number of iterations.

[0090] Specifically, for a convolutional neural network model to converge, at least three metrics must be met: mean squared error (MSE), mean absolute percentage error (MAS), and prediction accuracy. MSE is a commonly used metric to assess the difference between the model's predicted and actual values. A smaller MSE value indicates a smaller difference between the predicted and actual values, and a higher degree of model convergence. MAS assesses the percentage difference between the model's predicted and actual values. A smaller MAS value indicates a smaller percentage difference between the predicted and actual values, and a higher degree of model convergence. Prediction accuracy is a comprehensive metric, typically including precision, recall, and F1 score. Higher prediction accuracy indicates higher accuracy in classification or regression tasks, and a better degree of model convergence.

[0091] In another embodiment, the construction unit includes a first construction module, a second construction module, and a third construction module, wherein the first construction module is used to construct the operating cost of the power grid based on the power grid's loss cost and the power grid's electricity purchase cost and electricity sales revenue, wherein the operating cost C of the power grid... w The calculation formula is C W =C K +C T In the formula, C K For the aforementioned losses and costs of the aforementioned power grid, C T The above-mentioned power purchase cost and power sales revenue of the aforementioned power grid; the second construction module is used to construct the renewable energy absorption cost of the aforementioned power grid based at least on the power grid's capacity to absorb the power generated by the aforementioned photovoltaic power station and the power grid's capacity to absorb the power generated by the aforementioned wind power station, wherein the aforementioned renewable energy absorption cost C′ Dis The calculation formula is In the formula, P WT,dis (t) represents the grid's capacity to absorb the power generated by the photovoltaic power station, P PV,dis (t) represents the grid's capacity to absorb the power generated by the wind power station, and C(t) represents the electricity price at time t. The third construction module is used to construct the optimization objective of the scheduling model based on the minimum sum of the grid's operating costs and the renewable energy absorption costs. In this scheme, the grid's operating efficiency and reliability are further improved by setting the optimization objective.

[0092] Specifically, the optimization objective is, firstly, to minimize the total grid operating cost and prioritize the absorption of renewable energy. The total grid operating cost consists of grid operating costs, loss costs, electricity purchase costs, and electricity sales revenue. The cost of absorbing renewable energy is determined by the absorption capacity of photovoltaic power generation, the absorption capacity of wind power generation, and electricity prices.

[0093] To further improve the efficiency of the power grid system, in one embodiment of this application, the construction unit includes a fourth construction module, a fifth construction module, and a sixth construction module. The fourth construction module is used to construct a first constraint condition based on the maximum power generation of the photovoltaic power station and the seventh power generation, wherein the first constraint condition is P. PV (t)≤P PV,pre (t), where P PV (t) represents the maximum power generation of the aforementioned photovoltaic power station, P PV,pre (t) represents the seventh power generation; the fifth construction module is used to construct a second constraint condition based on the maximum power generation of the wind power station and the eighth power generation, wherein the second constraint condition is P. WT (t)≤P WT,pre (t), where PWT (t) represents the maximum power generation of the aforementioned wind power station, P WT,pre (t) represents the eighth power generation; the sixth construction module is used to construct the power balance constraint based at least on the power purchased by the power grid and the energy storage capacity on the user side. The first constraint, the second constraint, and the power balance constraint constitute the constraints of the scheduling model, wherein the power balance constraint is P. WT (t)+P PV (t)+P g (t)=P ESS (t)+P EV (t)+P load (t)+P loss (t), where P g (t) represents the power purchased by the aforementioned power grid, P ESS (t) represents the energy storage power on the user side, P load (t) represents the power of the fixed load on the user side mentioned above, P loss (t) represents the power lost on the user side, which is the power lost during the transmission of electricity to the user side.

[0094] Specifically, the constraints include photovoltaic (PV) output constraints, wind power output constraints, and power balance constraints. PV output constraints ensure that PV output does not exceed the predicted data, wind power output constraints ensure that wind power output does not exceed the predicted data, and power balance constraints ensure the balance between grid-purchased power, user-side energy storage power, stationary load power, and power loss.

[0095] The aforementioned power grid control device includes a processor and a memory. The acquisition unit, processing unit, construction unit, and execution unit are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0096] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting the kernel parameters addresses the problem of low precision in existing power grid control technologies.

[0097] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0098] This invention provides a computer-readable storage medium including a stored program, wherein, when the program runs, it controls the device containing the computer-readable storage medium to execute the power grid control method, the method including:

[0099] Step S201: Obtain the first data of the new energy power station within the first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0100] Step S202: Process the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0101] Step S203: Construct a grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the grid operating cost, and the constraints are set based at least on power balance constraints. The grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0102] Step S204: At least the above power generation forecast results are input into the above scheduling model to obtain a scheduling plan, and the above scheduling plan is executed to control the above power grid. The above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0103] This invention provides a processor for running a program, wherein the program executes a power grid control method, the method comprising:

[0104] Step S201: Obtain the first data of the new energy power station within the first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0105] Step S202: Process the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0106] Step S203: Construct a grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the grid operating cost, and the constraints are set based at least on power balance constraints. The grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0107] Step S204: At least the above power generation forecast results are input into the above scheduling model to obtain a scheduling plan, and the above scheduling plan is executed to control the above power grid. The above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0108] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0109] Step S201: Obtain the first data of the new energy power station within the first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0110] Step S202: Process the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0111] Step S203: Construct a grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the grid operating cost, and the constraints are set based at least on power balance constraints. The grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0112] Step S204: At least the above power generation forecast results are input into the above scheduling model to obtain a scheduling plan, and the above scheduling plan is executed to control the above power grid. The above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0113] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0114] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0115] Step S201: Obtain the first data of the new energy power station within the first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station.

[0116] Step S202: Process the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station on the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval is the same as the second interval.

[0117] Step S203: Construct a grid dispatch model. The dispatch model includes an optimization objective and constraints. The optimization objective is set based at least on the grid operating cost, and the constraints are set based at least on power balance constraints. The grid is the equipment that connects the electricity generated by the new energy power plants to the grid.

[0118] Step S204: At least the above power generation forecast results are input into the above scheduling model to obtain a scheduling plan, and the above scheduling plan is executed to control the above power grid. The above scheduling plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid.

[0119] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0120] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0122] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0123] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0124] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0125] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0126] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0127] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0128] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0129] In the above embodiments, firstly, first data from new energy power plants within a first historical time period is acquired. The new energy power plants include photovoltaic power plants and wind power plants. The first data includes at least the first power generation of the photovoltaic power plants and the second power generation of the wind power plants. Secondly, a prediction model is used to process the first data to obtain a power generation prediction result for a first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for a second predetermined day. The second data includes at least the third power generation of the photovoltaic power plants and the fourth power generation of the wind power plants for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power plants and the sixth power generation of the wind power plants for the second predetermined day. The electricity generation forecast results include the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A grid dispatch model is constructed, which includes optimization objectives and constraints. The grid is the equipment for connecting the electricity generated by the new energy power station to the grid. At least the power generation forecast results are input into the dispatch model to obtain a dispatch plan. The dispatch plan is executed to control the grid. The dispatch plan is the amount of electricity that the seventh power generation and the eighth power generation need to be connected to the grid. Compared with existing technologies, the present application's solution uses the historical power generation of photovoltaic power plants and wind power plants to train a convolutional neural network model to obtain a prediction model. This prediction model is then used to predict the power generation of photovoltaic power plants and wind power plants on a predetermined date, respectively. The prediction results are then used to make a scheduling plan for the power grid before the predetermined date, thereby achieving more precise control of the power grid and further solving the problem of low accuracy in power grid control in existing technologies.

[0130] 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 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 power grid control method, characterized in that, include: Acquire first data of a new energy power station within a first historical time period, wherein the new energy power station includes photovoltaic power stations and wind power stations, and the first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station; The first data is processed using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within the second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station for the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A power grid dispatch model is constructed, the dispatch model including optimization objectives and constraints, the optimization objectives being set at least based on the operating costs of the power grid, the constraints being set at least based on power balance constraints, and the power grid being the equipment for connecting the electricity generated by the new energy power plants to the grid; The power generation forecast results are input into the dispatch model to obtain a dispatch plan, which is then executed to control the power grid. The dispatch plan specifies the amount of electricity that the seventh and eighth power generation units need to connect to the grid. Before processing the first data using a prediction model to obtain the power generation prediction result for a predetermined day after the historical time period, the method further includes: an acquisition step, acquiring multiple sets of the historical data; a preprocessing step, performing data preprocessing on the second data in the multiple sets of historical data to obtain multiple sets of fourth data; an input step, inputting the multiple sets of fourth data into a convolutional neural network model; and a training step, training the convolutional neural network model to obtain the prediction model.

2. The power grid control method according to claim 1, characterized in that, The preprocessing steps include: The second data is cleaned to obtain the cleaned second data; The missing data in the cleaned second data is filled in to obtain the filled second data; The supplemented second data is normalized to obtain the fourth data.

3. The power grid control method according to claim 1, characterized in that, The training steps also include: The convolutional neural network is trained with at least a set number of iterations to obtain at least a plurality of ninth power generation of the photovoltaic power station, tenth power generation of the wind power station, and loss function curves corresponding to the number of training iterations on the second predetermined days. Each set of the fourth data includes one ninth power generation and one tenth power generation. In the comparison step, the ninth and tenth power generation obtained by training each group of the fourth data are compared with the third data corresponding to each group of the fourth data to obtain multiple first differences. The multiple first differences are averaged to obtain a second difference. The judgment step involves determining whether the trained convolutional neural network model is the prediction model based on whether the second difference is within a preset range and whether the loss function curve is in a convergent state. The preset range is set according to the actual situation.

4. The power grid control method according to claim 3, characterized in that, The determination step includes: If the second difference is within the preset range and the loss function curve is in a convergent state, the trained convolutional neural network model is determined to be the prediction model. If the second difference is not within the preset range or the loss function curve is not in a convergent state, adjust the parameters of the convolutional neural network model, and repeat the input step, the training step and the comparison step at least once in sequence until the second difference is within the preset range, and determine the trained convolutional neural network model as the prediction model, wherein the parameters include at least the number of iterations.

5. The power grid control method according to claim 1, characterized in that, The optimization objective for constructing the scheduling model includes: The operating cost of the power grid is constructed based on the power grid's loss costs, electricity purchase costs, and electricity sales revenue. The operating cost of the power grid... The calculation formula is In the formula, The loss cost of the power grid. The electricity purchase cost and electricity sales revenue of the power grid; Based at least on the grid's capacity to absorb the power generated by the photovoltaic power station and the grid's capacity to absorb the power generated by the wind power station, a renewable energy absorption cost for the grid is constructed, wherein the formula for calculating the renewable energy absorption cost is... for In the formula, The power grid's capacity to absorb the electricity generated by the photovoltaic power station. The power grid's capacity to absorb the electricity generated by the wind power station. Let t be the electricity price at time t; The optimization objective of the scheduling model is constructed based on the lowest sum of the operating cost of the power grid and the cost of absorbing new energy sources.

6. The power grid control method according to claim 1, characterized in that, The constraints for constructing the scheduling model include: Based on the maximum power generation of the photovoltaic power station and the seventh power generation, a first constraint condition is constructed, wherein the first constraint condition is: In the formula, This represents the maximum power generation of the photovoltaic power station. This refers to the seventh power generation; Based on the maximum power generation of the wind power station and the eighth power generation, a second constraint condition is constructed, wherein the second constraint condition is: ,in, The maximum power generation of the wind power station. This refers to the eighth power generation; The power balance constraint is constructed based at least on the power purchased by the power grid and the energy storage capacity on the user side. The first constraint, the second constraint, and the power balance constraint constitute the constraint conditions of the scheduling model, wherein the power balance constraint is... ,in, The power purchase capacity of the power grid. The energy storage power on the user side, The power of the fixed load on the user side. The power loss on the user side refers to the power lost during the power transmission process to the user side.

7. A power grid control device, characterized in that, include: The acquisition unit acquires the first data of the new energy power station within a first historical time period. The new energy power station includes photovoltaic power stations and wind power stations. The first data includes at least the first power generation of the photovoltaic power station and the second power generation of the wind power station. The processing unit processes the first data using a prediction model to obtain the power generation prediction result for the first predetermined day after the first historical time period. The prediction model is trained using multiple sets of historical data. Each set of historical data includes second data within a second historical time period and third data for the second predetermined day. The second data includes at least the third power generation of the photovoltaic power station and the fourth power generation of the wind power station for each day within the second historical time period. The third data includes at least the fifth power generation of the photovoltaic power station and the sixth power generation of the wind power station for the second predetermined day. The power generation prediction result includes the seventh power generation of the photovoltaic power station and the eighth power generation of the wind power station. The first historical time period and the second historical time period are different historical time periods with the same duration. The time interval between the last day of the first historical time period and the first predetermined day is the first interval, and the time interval between the last day of the second historical time period and the second predetermined day is the second interval. The first interval and the second interval are the same. A construction unit is used to construct a power grid scheduling model. The scheduling model includes an optimization objective and constraints. The optimization objective is set based at least on the operating cost of the power grid, and the constraints are set based at least on power balance constraints. The power grid is the equipment used to connect the electricity generated by the new energy power plant to the grid. The execution unit inputs at least the power generation forecast results into the scheduling model to obtain a scheduling plan, and executes the scheduling plan to control the power grid. The scheduling plan specifies the amount of electricity that the seventh and eighth power generation units need to connect to the grid. The acquisition unit further includes an acquisition module, a preprocessing module, an input module, and a training module. The acquisition module performs an acquisition step to acquire multiple sets of historical data. The preprocessing module performs a preprocessing step to preprocess the second data from the multiple sets of historical data to obtain multiple sets of fourth data. The input module performs an input step to input the multiple sets of fourth data into a convolutional neural network model. The training module performs a training step to train the convolutional neural network model to obtain the prediction model.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the power grid control method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a control method for performing a power grid according to any one of claims 1 to 6.

Images