Power generation amount prediction device and method thereof

Abstract

A power generation amount prediction device according to one embodiment of the present document comprises a memory and at least one processor, wherein the at least one processor can: acquire first weather prediction information and second weather prediction information; compare first past weather prediction information with past weather information so as to identify a first accuracy of a first source; compares second past weather prediction information with past weather information so as to identify a second accuracy of a second source; and identify a predicted power generation amount of a generator at a specific time point on the basis of the first accuracy, the second accuracy, the first weather prediction information and the second weather prediction information.

Description

Power generation prediction device and method

[0001] Cross-citation with related applications

[0002] The present application claims the benefit of priority based on Korean Patent Application No. 10-2025-0039760 filed on March 27, 2025, and Korean Patent Application No. 10-2025-0087240 filed on June 30, 2025, and includes all contents disclosed in the documents of said patent applications as part of this specification.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a power generation prediction device and a method thereof.

[0005] Renewable energy technology is rapidly developing as an important alternative to address global warming and the depletion of energy resources. In particular, some renewable energy sources, such as solar and wind power, have a close relationship with weather conditions and generation volume, meaning their efficiency can be affected by weather changes. Consequently, improving the accuracy of power generation forecasts is emerging as a critical challenge in renewable energy systems that rely on meteorological variables. Enhancing forecasting accuracy is essential for maintaining grid stability and preventing supply surpluses or shortages. Furthermore, reducing forecasting errors can lead to lower energy costs and improved resource allocation efficiency. Accordingly, technological development aimed at improving the accuracy of power generation forecasts is currently underway.

[0006] According to the embodiments disclosed in this document, we intend to provide a power generation prediction device and a method for improving the prediction accuracy of predicted power generation.

[0007] According to the embodiments disclosed in this document, a power generation prediction device and a method for predicting the power generation of a generator based on weather forecast information from multiple sources are provided.

[0008] The technical problems of this document are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the descriptions below.

[0009] A power generation prediction device according to one embodiment of the present document may include a memory for storing at least one instruction and at least one processor for executing said at least one instruction.

[0010] According to one embodiment, the at least one processor can predict the weather at a specific point in time in a region including a generator and obtains first weather prediction information provided by a first source and second weather prediction information provided by a second source that predicts the weather at the specific point in time in the region, identify a first accuracy of the first source by comparing the first past weather prediction information of the region provided by the first source during a specified period prior to the specific point in time and the past weather information of the region during the specified period, identify a second accuracy of the second source by comparing the second past weather prediction information of the region provided by the second source during the specified period and the past weather information of the region during the specified period, and identify the predicted power generation amount of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather prediction information, and the second weather prediction information.

[0011] According to one embodiment, the at least one processor can identify a first weight based on the first accuracy, identify a second weight based on the second accuracy, and identify the predicted power generation amount at the specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information.

[0012] According to one embodiment, the at least one processor can identify the predicted power generation amount at the specific point in time based on the value obtained by calculating the first weight and the first weather forecast information, and the value obtained by calculating the second weight and the second weather forecast information.

[0013] According to one embodiment, the at least one processor can identify the first accuracy by comparing the first value of the first weather variable included in the first past weather forecast information with the second value of the first weather variable included in the past weather information, and identify the second accuracy by comparing the third value of the first weather variable included in the second past weather forecast information with the second value.

[0014] According to one embodiment, the at least one processor can identify the first accuracy based on the difference between the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, and the difference between the fourth value of the second weather variable included in the first past weather forecast information and the fifth value of the second weather variable included in the past weather information, and identify the second accuracy based on the difference between the third value of the first weather variable included in the second past weather forecast information and the second value, and the difference between the sixth value of the second weather variable included in the second past weather forecast information and the fifth value.

[0015] According to one embodiment, the at least one processor can identify the higher accuracy among the first accuracy and the second accuracy, and identify the predicted power generation amount at the specific point in time based on the first weather forecast information and one of the second weather forecast information corresponding to the higher accuracy.

[0016] According to one embodiment, the at least one processor can identify the predicted power generation amount at a specific point in time by inputting one corresponding to the high accuracy into a first model that identifies the predicted power generation amount.

[0017] According to one embodiment, the at least one processor can identify the predicted power generation amount at a specific point in time by inputting the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information into a second model that identifies the predicted power generation amount.

[0018] A power generation prediction method according to one embodiment of the present document may include: a first weather prediction information provided by a first source and a second weather prediction information provided by a second source that predicts the weather at a specific point in time of a region including a generator; a first past weather prediction information of the region provided by the first source during a specified period prior to the specific point in time and a second past weather prediction information of the region during the specified period by comparing the first past weather prediction information of the region provided by the first source during the specified period and the past weather information of the region during the specified period; a second past weather prediction information provided by the second source during the region during the specified period and a second past weather prediction information of the region during the specified period by comparing the second past weather prediction information of the region during the specified period and the second past weather prediction information of the region during the specified period; and a second prediction of the power generation of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather prediction information, and the second weather prediction information.

[0019] According to one embodiment, the operation of identifying the predicted power generation amount of the generator at a specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information, and the operation of identifying a first weight based on the first accuracy, may include the operation of identifying a second weight based on the second accuracy, and the operation of identifying the predicted power generation amount at a specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information.

[0020] According to one embodiment, the operation of identifying the predicted power generation amount at a specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information may include the operation of identifying the predicted power generation amount at the specific point in time based on the value calculated by the first weight and the first weather forecast information, and the value calculated by the second weight and the second weather forecast information.

[0021] According to one embodiment, the operation of identifying the first accuracy of the first source by comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time with the past weather information of the region during the specified period includes the operation of identifying the first accuracy by comparing the first value of the first weather variable included in the first past weather forecast information with the second value of the first weather variable included in the past weather information, and the operation of identifying the second accuracy of the second source by comparing the second past weather forecast information provided by the second source during the specified period with the past weather information of the region during the specified period may include the operation of identifying the second accuracy by comparing the third value of the first weather variable included in the second past weather forecast information with the second value.

[0022] According to one embodiment, the operation of identifying the first accuracy of the first source by comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time with the past weather information of the region during the specified period includes the operation of identifying the first accuracy based on the difference between the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, and the difference between the fourth value of the second weather variable included in the first past weather forecast information and the fifth value of the second weather variable included in the past weather information, and the operation of identifying the second accuracy of the second source by comparing the second past weather forecast information provided by the second source during the specified period with the past weather information of the region during the specified period includes the operation of identifying the first accuracy based on the difference between the third value of the first weather variable included in the second past weather forecast information and the second value, and the difference between the sixth value of the second weather variable included in the second past weather forecast information and the fifth value. It may include an operation to identify a second accuracy.

[0023] According to one embodiment, the operation of identifying the predicted power generation amount of the generator at a specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information may include the operation of identifying the higher accuracy among the first accuracy and the second accuracy, and the operation of identifying the predicted power generation amount at the specific point in time based on one corresponding to the higher accuracy among the first weather forecast information and the second weather forecast information.

[0024] According to one embodiment, the operation of identifying the predicted power generation amount at a specific point in time based on one of the first weather forecast information and the second weather forecast information corresponding to the high accuracy may include the operation of identifying the predicted power generation amount at a specific point in time by inputting the one corresponding to the high accuracy into a first model for identifying the predicted power generation amount.

[0025] According to one embodiment, the operation of identifying the predicted power generation amount of the generator at a specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information may include the operation of identifying the predicted power generation amount at the specific point in time by inputting the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information into a second model that identifies the predicted power generation amount.

[0026] A computer-readable recording medium according to another embodiment of the present document can record a program for performing the power generation prediction method on a computer.

[0027] This technology can improve the accuracy of predicting power generation.

[0028] In addition, this technology can predict the amount of power generated by a generator based on weather forecast information from multiple sources.

[0029] In addition, various effects that can be identified directly or indirectly through this document may be provided.

[0030] FIG. 1 is a block diagram showing the configuration of a power generation prediction device in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0031] FIG. 2 illustrates examples of weather forecast information according to a plurality of sources in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0032] FIG. 3 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount according to one selected weather forecast information in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0033] FIG. 4 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount based on weights and weather forecast information in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0034] FIG. 5 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0035] FIG. 6 illustrates an example of a learning model for identifying a predicted power generation amount in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0036] FIG. 7 is a block diagram showing the hardware configuration of a computing system for performing a power generation prediction method according to one embodiment disclosed in this document.

[0037] Some embodiments disclosed in this document are described below with reference to the various embodiments of this document attached to the drawings. However, this is not intended to limit the technology to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives to embodiments of the technology.

[0038] It should be noted that when assigning reference numerals to the components of each drawing, the same components are assigned the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the various embodiments disclosed in this document, if it is determined that a detailed description of related known configurations or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted. The singular form of a noun corresponding to an item may include one or more items unless the relevant context clearly indicates otherwise.

[0039] In describing the components of the embodiments of this document, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components and do not limit the essence, order, or sequence of the components. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments disclosed in this document pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0040] Additionally, in this disclosure, expressions of "greater than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" may be replaced with "less than," and conditions described as "greater than and less than" may be replaced with "greater than and less than." Furthermore, "A" to "B" below refer to at least one of the elements from A (including A) to B (including B).

[0041] In this document, each of the phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof.

[0042] In this document, where any component (e.g., 1) is referred to as being “connected,” “coupled,” or “joined” to another component (e.g., 2), with or without the terms “functionally” or “communicationally,” or where it is referred to as “coupled” or “connected,” it means that the component may be connected to the other component directly (e.g., via a wire), wirelessly, or through a third component.

[0043] According to one embodiment, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0044] According to various embodiments, each component (e.g., module or program) of the described components may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the aforementioned components or operations may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as they were performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically; one or more of the operations may be executed in a different order; may be omitted; or one or more other operations may be added.

[0045] Hereinafter, embodiments of the present document will be described in detail with reference to FIGS. 1 to 6.

[0046] FIG. 1 is a block diagram showing the configuration of a power generation prediction device in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0047] Referring to FIG. 1, the power generation prediction device (101) may include a memory (103) that stores at least one instruction and at least one processor (105) that executes at least one instruction.

[0048] According to one embodiment, at least one processor (105) of a power generation prediction device (101) can acquire weather forecast information from various sources and, based on the weather forecast information, identify the predicted power generation amount of a generator at a specific point in time through a learning model. The learning model is described below with reference to FIG. 6.

[0049] However, the accuracy of the weather forecast information may vary depending on the source. At least one processor (105) can identify the predicted power generation amount of a generator based on the accuracy of the source providing the weather forecast information.

[0050] According to one embodiment, at least one processor (105) can obtain first weather forecast information provided from a first source that predicts the weather at a specific point in time in a region including a generator, and second weather forecast information provided from a second source that predicts the weather at a specific point in time in a region including a generator.

[0051] According to one embodiment, at least one processor (105) can identify the accuracy of a specific source by comparing past weather forecast information provided by a specific source (e.g., domestic meteorological agency, European meteorological agency, US weather agency, climate model) for a specified period (e.g., about one week) prior to a specific point in time with past weather information for a specified period. The past weather information may include weather information for a specified period in a region including a generator.

[0052] According to one embodiment, at least one processor (105) may refer to a root mean square error (RMSE) value, a relative bias value, and a Nash-Sutcliffe efficiency value to compare past weather forecast information with past weather information. A specified period may be determined based on a temporal scale according to a typical mobile low-pressure system.

[0053] For example, at least one processor (105) can identify the first accuracy of the first source by comparing the first value of the first weather variable (e.g., amount of sunshine, amount of precipitation, amount of sunshine, temperature) included in the first past weather forecast information provided by the first source with the second value of the first weather variable included in the past weather information.

[0054] For example, at least one processor (105) can identify the second accuracy of the second source by comparing the third value of the first weather variable and the second value of the second past weather forecast information provided by the second source.

[0055] According to one embodiment, at least one processor (105) can identify the higher accuracy among the first accuracy and the second accuracy, and identify the predicted power generation amount at a specific point in time based on the first weather forecast information and the one corresponding to the higher accuracy among the second weather forecast information. At least one processor (105) can identify the predicted power generation amount of a generator at a specific point in time by inputting the first weather forecast information and the second weather forecast information into a first model. The first model can be described by referring to the description of the learning model (603) of FIG. 6.

[0056] According to another embodiment, at least one processor (105) can identify a first weight based on a first accuracy and identify a second weight based on a second accuracy. At least one processor (105) can identify a predicted power generation amount at a specific point in time based on a value calculated from the first weight and the first weather forecast information, and a value calculated from the second weight and the second weather forecast information. At least one processor (105) can identify a predicted power generation amount of a generator at a specific point in time by inputting the value calculated from the first weight and the first weather forecast information, and the value calculated from the second weight and the second weather forecast information, into a second model. The second model can be described by referring to the description of the learning model (603) of FIG. 6.

[0057] According to one embodiment, when the first weather forecast information and the second weather forecast information include not only the first weather variable but also the second weather variable, at least one processor (105) can identify the first accuracy and the second accuracy in a different way.

[0058] For example, at least one processor (105) can identify the predicted power generation amount of a generator at a specific point in time based on a first accuracy, a second accuracy, first weather forecast information, and second weather forecast information.

[0059] For example, at least one processor (105) can identify the accuracy of a first source for a first weather variable and the accuracy of a first source for a second weather variable differently, and can identify the weight for the first weather variable and the weight for the second weather variable differently. At least one processor (105) can identify the weight for the first weather variable of the first source, the weight for the second weather variable of the first source, the weight for the first weather variable of the second source, and the weight for the second weather variable of the second source differently from each other. Additionally, at least one processor (105) can identify the predicted power generation amount of a generator based on the weight for each weather variable (e.g., first weather variable, second weather variable), the first weather forecast information, and the second weather forecast information.

[0060] As another example, at least one processor (105) can identify a first accuracy of a first source based on a first weather variable of a first source and a second weather variable of a first source, and identify a second accuracy of a second source based on a first weather variable of a second source and a second weather variable of a second source.

[0061] In other words, at least one processor (105) can identify the first accuracy of the first source based on the difference between the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, and the difference between the fourth value of the second weather variable included in the first past weather forecast information and the fifth value of the second weather variable included in the past weather information.

[0062] Additionally, at least one processor (105) can identify the second accuracy of the second source based on the difference between the third value and the second value of the first weather variable included in the second past weather forecast information, and the difference between the sixth value and the fifth value of the second weather variable included in the second past weather forecast information.

[0063] According to one embodiment, at least one processor (105) can identify a first weight based on a first accuracy of a first source, identify a second weight based on a second accuracy of a second source, and identify a predicted power generation amount at a specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information.

[0064] FIG. 2 illustrates examples of weather forecast information according to a plurality of sources in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0065] Weather forecast information may include external weather forecast information (201) and internal weather forecast information (211).

[0066] For example, external weather forecast information (201) may include first external weather forecast information (203) obtained based on a first external source, second external weather forecast information (205) obtained based on a second external source, and third external weather forecast information (207) obtained based on a third external source.

[0067] External sources may include climate models from meteorological agencies of various countries, such as the local data assimilation and prediction system (LDAS) operated by the Korea Meteorological Administration, the high-resolution medium-range weather forecasts-high resolution (ECFMWF-HRES) operated by the European Centre for Medium-Range Weather Forecasts (ECMWF), and the global forecast system (GFS) operated by the National Weather Service (NWS) of the United States. However, the embodiments of this document are not limited thereto.

[0068] Internal sources may include global / regional climate models or artificial intelligence (AI) forecasting models. However, the embodiments of this document are not limited thereto.

[0069] FIG. 3 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount according to one selected weather forecast information in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0070] In the following, it is assumed that at least one processor (105) of the power generation prediction device (101) of FIG. 1 performs the process of FIG. 3. Also, in the description of FIG. 3, the operation described as being performed by the power generation prediction device (101) can be understood as being controlled by at least one processor (105) of the power generation prediction device (101).

[0071] In the first operation (301), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify one of the first weather prediction information and the second weather prediction information that corresponds to a higher accuracy.

[0072] The first weather forecast information predicts the weather at a specific point in time in a region including a generator and may be provided by a first source. The second weather forecast information predicts the weather at a specific point in time in a region including a generator and may be provided by a second source.

[0073] In the second operation (303), at least one processor (105) of the power generation prediction device (101) according to one embodiment can input one corresponding to high accuracy into the model.

[0074] The model can be described by referring to the description of the learning model (603) in FIG. 6.

[0075] In the third operation (305), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify the predicted power generation amount of the generator.

[0076] In other words, at least one processor (105) of the power generation prediction device (101) can identify the predicted power generation output from the model.

[0077] FIG. 4 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount based on weights and weather forecast information in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0078] In the following, it is assumed that at least one processor (105) of the power generation prediction device (101) of FIG. 1 performs the process of FIG. 4. Also, in the description of FIG. 4, the operation described as being performed by the power generation prediction device (101) can be understood as being controlled by at least one processor (105) of the power generation prediction device (101).

[0079] In the first operation (401), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify a weight for each weather prediction information based on the accuracy of the source of the weather prediction information.

[0080] In the second operation (403), at least one processor (105) of the power generation prediction device (101) according to one embodiment can input weights and weather prediction information into the model.

[0081] In the third operation (405), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify the predicted power generation amount of the generator.

[0082] FIG. 5 illustrates an example of the flow of operation of a power generation prediction device that identifies a predicted power generation amount in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0083] In the following, it is assumed that at least one processor (105) of the power generation prediction device (101) of FIG. 1 performs the process of FIG. 5. Also, in the description of FIG. 5, the operation described as being performed by the power generation prediction device (101) can be understood as being controlled by at least one processor (105) of the power generation prediction device (101).

[0084] In the first operation (501), at least one processor (105) of the power generation prediction device (101) according to one embodiment can obtain first weather prediction information and second weather prediction information.

[0085] The first weather forecast information predicts the weather at a specific point in time in a region including a generator and may be provided by a first source. The second weather forecast information predicts the weather at a specific point in time in a region including a generator and may be provided by a second source.

[0086] In the second operation (503), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify the first accuracy of the first source by comparing the first past weather prediction information with the past weather information.

[0087] The first past weather forecast information may be provided by the first source for a specified period prior to a specific point in time. The past weather information may represent weather information for the region containing the generator during a specified period prior to a specific point in time.

[0088] In the third operation (505), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify the second accuracy of the second source by comparing the second past weather prediction information with the past weather information.

[0089] Second historical weather forecast information may be provided from a second source for a specified period prior to a specific point in time. The historical weather information may represent weather information for the region containing the generator during a specified period prior to a specific point in time.

[0090] In the fourth operation (507), at least one processor (105) of the power generation prediction device (101) according to one embodiment can identify the predicted power generation amount based on the first accuracy, the second accuracy, the first weather prediction information, and the second weather prediction information.

[0091] The predicted power generation can represent the predicted power generation of the generator at a specific point in time.

[0092] FIG. 6 illustrates an example of a learning model for identifying a predicted power generation amount in a power generation prediction device and a power generation prediction method according to one embodiment of the present document.

[0093] Referring to FIG. 6, the learning model (603) may include a learning model that identifies the predicted power generation amount of a generator.

[0094] According to one embodiment, at least one processor (105) of a power generation prediction device (101) inputs a first accuracy, a second accuracy, first weather forecast information, second weather forecast information, or any combination thereof as input data (601), and outputs the predicted power generation amount of a generator from a learning model (603) as output data (605).

[0095] According to one embodiment, if at least one processor (105) of a power generation prediction device (101) includes an artificial intelligence dedicated processor (e.g., a neural processing unit (NPU)) for training an artificial neural network (ANN) model, the artificial intelligence dedicated processor can train an artificial neural network by utilizing weight data stored in memory as training data for a machine learning model.

[0096] According to one embodiment, examples of learning algorithms may include supervised learning, unsupervised learning, self-supervised learning, semi-supervised learning, or reinforcement learning.

[0097] According to one embodiment, the artificial neural network included in the learning model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values ​​and can perform neural network operations through operations between the operation result of the previous layer and the plurality of weights. The plurality of weights possessed by the plurality of neural network layers may be optimized by the learning results of the artificial intelligence model. For example, the plurality of weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized.

[0098] According to one embodiment, the artificial neural network may include a deep neural network, such as a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks, but is not limited to the examples described above.

[0099] According to one embodiment, at least one processor (105) of a power generation prediction device (101) can output a predicted power generation amount, which is output data (605) correlated with at least one of input data (601), such as a first accuracy, a second accuracy, first weather forecast information, second weather forecast information, or a combination thereof, based on a selected artificial intelligence model.

[0100] According to one embodiment, the predicted power generation amount may be higher when the amount of sunlight identified based on weather forecast information is high, the amount of precipitation is low, the duration of sunlight is long, or the temperature is close to an appropriate temperature range.

[0101] However, it may not be limited to having a linear positive correlation between the amount of sunlight, precipitation, sunshine duration, or temperature and the predicted power generation.

[0102] In addition, other meteorological variables, as well as sunlight, precipitation, sunshine duration, and temperature, can be included in the weather forecast information.

[0103] FIG. 7 is a block diagram showing the hardware configuration of a computing system for performing a power generation prediction method according to one embodiment disclosed in this document.

[0104] Referring to FIG. 7, a computing system (700) according to one embodiment disclosed in this document may include an MCU (710), memory (720), an input / output I / F (730), and a communication I / F (740).

[0105] The MCU (710) may be at least one processor that executes various programs stored in memory (720) (e.g., power generation prediction program, weather prediction information acquisition program, data analysis program, data decomposition algorithm, and normalization program, etc.), processes various information including characteristic data of battery cells and potential variables through these programs, and performs the functions of the power generation prediction device (101) shown in FIGS. 1 to 6.

[0106] The memory (720) can store various programs such as a power generation prediction program, a weather forecast information acquisition program, a data analysis program, a data decomposition algorithm, and a normalization program.

[0107] These memories (720) may be provided in multiple quantities as needed. The memories (720) may be volatile memories or non-volatile memories. As volatile memories, the memory (720) may use RAM, DRAM, SRAM, etc. As non-volatile memories, the memory (720) may use ROM, PROM, EAROM, EPROM, EEPROM, flash memory, etc. The examples of the listed memories (720) are merely examples and are not limited to these examples.

[0108] The input / output I / F (730) can provide an interface that enables data transmission and reception between an input device (not shown), such as a keyboard, mouse, or touch panel, and an output device (not shown), such as a display, and the MCU (710).

[0109] The communication I / F (740) is configured to transmit and receive various data with a server and may be various devices capable of supporting wired or wireless communication. For example, the power generation prediction device (101) can transmit and receive various information, including the shape model of a battery cell, from a separately provided external server via the communication I / F (740).

[0110] In this way, a computer program according to one embodiment disclosed in this document may be implemented as a function module that performs, for example, each of the functions illustrated in FIG. 1 by being written to memory (720) and processed by an MCU (710).

[0111] As described above, even though all components constituting the embodiments disclosed in this document have been described as being combined or operating in combination, the embodiments disclosed in this document are not necessarily limited to such embodiments. That is, within the scope of the purposes of the embodiments disclosed in this document, all components may be selectively combined in one or more ways to operate.

[0112] Furthermore, terms such as "include," "compose," or "have" as described above, unless specifically stated otherwise, mean that the relevant component may be inherent; thus, they should be interpreted as allowing for the inclusion of additional components rather than excluding them. All terms, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments disclosed in this document pertain, unless otherwise defined. Commonly used terms, such as those defined in advance, should be interpreted in accordance with their contextual meanings in the relevant technology and, unless explicitly defined in this document, should not be interpreted in an ideal or overly formal sense.

[0113] The foregoing disclosure outlines the features of several embodiments to enable those skilled in the art to better understand the aspects of the present disclosure. Those skilled in the art will understand that the present disclosure can be readily used as a basis for designing or modifying other structures to perform the same purpose or achieve the same advantages as the embodiments introduced herein. Furthermore, those skilled in the art will recognize that such equivalent configurations do not depart from the scope of the present disclosure and that various changes, substitutions, and modifications may be made in the present specification without departing from the scope of the present disclosure.

Claims

1. Memory; and It includes at least one processor, The above-mentioned at least one processor is, Predicting the weather at a specific point in time in a region including a generator, obtaining first weather prediction information provided from a first source, and predicting the weather at the specific point in time in said region, obtaining second weather prediction information provided from a second source, and By comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time above with the past weather information of the region during the specified period above, the first accuracy of the first source is identified, and By comparing the second past weather forecast information provided by the second source during the specified period of the above region with the past weather information of the above region during the specified period, the second accuracy of the second source is identified, and A configuration configured to identify the predicted power generation amount of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information. Power generation prediction device.

2. In Claim 1, The above-mentioned at least one processor is, Identifying a first weight based on the above first accuracy, and Identifying a second weight based on the above second accuracy, and A configuration configured to identify the predicted power generation amount at the specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information. Power generation prediction device.

3. In Claim 2, The above-mentioned at least one processor is, A method configured to identify the predicted power generation amount at a specific point in time based on the value calculated from the first weight and the first weather forecast information, and the value calculated from the second weight and the second weather forecast information. Power generation prediction device.

4. In Claim 1, The above-mentioned at least one processor is, By comparing the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, the first accuracy is identified, and A configuration configured to identify the second accuracy by comparing the third value of the first weather variable included in the second past weather forecast information with the second value. Power generation prediction device.

5. In Claim 1, The above-mentioned at least one processor is, Based on the difference between the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, and the difference between the fourth value of the second weather variable included in the first past weather forecast information and the fifth value of the second weather variable included in the past weather information, the first accuracy is identified. A configuration for identifying the second accuracy based on the difference between the third value of the first weather variable included in the second past weather forecast information and the second value, and the difference between the sixth value of the second weather variable included in the second past weather forecast information and the fifth value. Power generation prediction device.

6. In Claim 1, The above-mentioned at least one processor is, Identifying the higher accuracy among the first accuracy and the second accuracy, A configuration configured to identify the predicted power generation amount at a specific point in time based on one of the first weather forecast information and the second weather forecast information corresponding to the high accuracy. Power generation prediction device.

7. In Claim 6, The above-mentioned at least one processor is, By inputting one corresponding to the above high accuracy into a first model for identifying the above predicted power generation amount, the predict power generation amount at the above specific point in time is configured to identify the above predicted power generation amount. Power generation prediction device.

8. In Claim 1, The above-mentioned at least one processor is, A method configured to identify the predicted power generation amount at a specific point in time by inputting the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information into a second model that identifies the predicted power generation amount. Power generation prediction device.

9. An operation to obtain first weather forecast information provided from a first source for predicting the weather at a specific point in time in a region including a generator, and second weather forecast information provided from a second source for predicting the weather at the specific point in time in said region; An operation to identify the first accuracy of the first source by comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time above with the past weather information of the region during the specified period above; An operation to identify the second accuracy of the second source by comparing the second past weather forecast information provided by the second source during the specified period of the region with the past weather information of the region during the specified period; and The operation of identifying the predicted power generation amount of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information, Power generation prediction method.

10. In Claim 9, Based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information, the operation of identifying the predicted power generation amount of the generator at the specific point in time, and the operation of identifying the first weight based on the first accuracy, An operation to identify a second weight based on the second accuracy above; and The operation of identifying the predicted power generation amount at the specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information, Power generation prediction method.

11. In Claim 10, The operation of identifying the predicted power generation amount at the specific point in time based on the first weight, the first weather forecast information, the second weight, and the second weather forecast information is, A method comprising identifying the predicted power generation amount at a specific point in time based on the value calculated from the first weight and the first weather forecast information, and the value calculated from the second weight and the second weather forecast information. Power generation prediction method.

12. In Claim 9, The operation of identifying the first accuracy of the first source by comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time above with the past weather information of the region during the specified period above, The method includes an operation of identifying the first accuracy by comparing the first value of the first weather variable included in the first past weather forecast information with the second value of the first weather variable included in the past weather information. The operation of identifying the second accuracy of the second source by comparing the second past weather forecast information provided by the second source during the specified period of the said region with the past weather information of the said region during the specified period, The operation of identifying the second accuracy by comparing the third value of the first weather variable included in the second past weather forecast information with the second value, Power generation prediction method.

13. In Claim 9, The operation of identifying the first accuracy of the first source by comparing the first past weather forecast information of the region provided by the first source during a specified period prior to the specific point in time above with the past weather information of the region during the specified period above, The method includes an operation of identifying the first accuracy based on the difference between the first value of the first weather variable included in the first past weather forecast information and the second value of the first weather variable included in the past weather information, and the difference between the fourth value of the second weather variable included in the first past weather forecast information and the fifth value of the second weather variable included in the past weather information. The operation of identifying the second accuracy of the second source by comparing the second past weather forecast information provided by the second source during the specified period of the said region with the past weather information of the said region during the specified period is, The operation of identifying the second accuracy based on the difference between the third value of the first weather variable included in the second past weather forecast information and the second value, and the difference between the sixth value of the second weather variable included in the second past weather forecast information and the fifth value. Power generation prediction method.

14. In Claim 9, The operation of identifying the predicted power generation amount of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information is, An operation to identify the higher accuracy among the first accuracy and the second accuracy; and The operation of identifying the predicted power generation amount at a specific point in time based on one of the first weather forecast information and the second weather forecast information corresponding to the high accuracy, Power generation prediction method.

15. In Claim 14, The operation of identifying the predicted power generation amount at a specific point in time based on one of the first weather forecast information and the second weather forecast information corresponding to the high accuracy is, The operation of identifying the predicted power generation amount at the specific point in time by inputting one corresponding to the above high accuracy into the first model that identifies the predicted power generation amount, Power generation prediction method.

16. In Claim 9, The operation of identifying the predicted power generation amount of the generator at the specific point in time based on the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information is, The operation of identifying the predicted power generation amount at a specific point in time by inputting the first accuracy, the second accuracy, the first weather forecast information, and the second weather forecast information into a second model that identifies the predicted power generation amount, wherein Power generation prediction method.

17. A computer-readable recording medium having a program recorded thereon for performing the method of any one of claims 9 to 16 on a computer.

Images