Energy analysis device and energy analysis method

Abstract

According to some embodiments, an energy analysis device comprises: a processor; and a memory configured to store instructions that, when executed by the processor, cause the processor to: generate weather interpolation data for a region of interest by performing data interpolation on the basis of observation values of weather observation data for the region of interest to which a renewable energy power plant belongs; generate a power generation amount estimation function on the basis of the weather interpolation data and past power generation amount data of the renewable energy power plant; and estimate an expected power generation amount of the renewable energy power plant on the basis of weather forecast data for the region of interest and the power generation amount estimation function.

Description

Energy analysis device and energy analysis method

[0001] Cross-citation with related applications

[0002] This application claims the benefit of priority based on Korean Patent Application No. 10-2024-0125948 filed on September 13, 2024, and includes all contents disclosed in the document of said patent application as part of this specification.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to an energy analysis device and an energy analysis method.

[0005] Most methodologies for predicting renewable energy generation are based on power curves constructed from the relationship between meteorological environmental variables, such as solar radiation, temperature, and wind speed, and the amount of power generated. Power curves defined through simulations or computer modeling can be based on meteorological variables in limited environments and can be considered a convenient and useful tool for predicting power generation. However, actual meteorological variables are not limited solely to the environments defined in laboratories or modeling, and they can interact with each other and change non-linearly. Therefore, actual power curves can differ significantly from the ideal forms calculated by experiments or modeling.

[0006] For example, depending on the topographical characteristics where renewable energy power plants are located, exceptional weather phenomena and changes such as fog, sea fog, and turbulence may occur that are not captured in existing experiments and modeling, which can lead to a decrease in the reliability of power generation forecasts. In addition to environmental characteristics, weather forecasts currently provided by domestic and international meteorological agencies based on single scenarios also contain high levels of uncertainty.

[0007] One of the objectives of the embodiments disclosed in this document includes providing an energy analysis device and an energy analysis method capable of overcoming the limitations of development curves defined through simulation or computer modeling and the limitations of weather forecasts provided as a single scenario.

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

[0009] According to some embodiments, an energy analysis device comprises: a processor; and a memory configured to store instructions that, when executed by the processor, cause the processor to perform: an operation of generating weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs; an operation of generating a power generation estimation function based on the weather interpolation data and past power generation data of the renewable energy power plant; and an operation of estimating the expected power generation of the renewable energy power plant based on weather forecast data for the region of interest and the power generation estimation function.

[0010] According to some embodiments, the operation of generating the weather interpolation data includes the operation of generating the weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

[0011] According to some embodiments, the weather forecast data includes global forecast data and local forecast data, and the operation of estimating the expected power generation includes the operation of estimating the expected power generation based on the global forecast data, the local forecast data, and the power generation estimation function.

[0012] According to some embodiments, the operation of estimating the expected power generation amount includes: the operation of generating ensemble forecast data based on the global forecast data and the local forecast data; and the operation of estimating the expected power generation amount based on the ensemble forecast data and the power generation estimation function.

[0013] According to some embodiments, the operation of generating the ensemble forecast data includes: the operation of setting a forecast area including the region of interest among the forecast areas of the global forecast data having a first resolution as an initial background environment field; and the operation of applying the global forecast data to the initial background environment field to generate the local forecast data having a second resolution higher than the first resolution.

[0014] According to some embodiments, the local forecast data includes a plurality of second forecast data based on an AI prediction model, and the operation of generating the ensemble forecast data includes the operation of generating the ensemble forecast data by reflecting a plurality of probability densities of the plurality of second forecast data into the initial background environment field.

[0015] According to some embodiments, the local forecast data further includes first forecast data based on a numerical analysis model, and the AI ​​prediction model is configured to take the first forecast data as input and output the plurality of second forecast data.

[0016] According to some embodiments, the operation of estimating the expected power generation amount includes the operation of estimating the expected power generation amount in a probabilistic form based on the plurality of probability densities reflected in the ensemble forecast data.

[0017] According to some embodiments, an energy analysis method comprises: generating weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs; generating a power generation estimation function based on the weather interpolation data and past power generation data of the renewable energy power plant; and estimating the expected power generation of the renewable energy power plant based on weather forecast data for the region of interest and the power generation estimation function.

[0018] According to some embodiments, the step of generating the weather interpolation data includes the step of generating the weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

[0019] According to some embodiments, the weather forecast data includes global forecast data and local forecast data, and the step of estimating the expected power generation amount includes the step of estimating the expected power generation amount based on the global forecast data, the local forecast data, and the power generation estimation function.

[0020] According to some embodiments, the step of estimating the expected power generation amount includes: the step of generating ensemble forecast data based on the global forecast data and the local forecast data; and the step of estimating the expected power generation amount based on the ensemble forecast data and the power generation estimation function.

[0021] According to some embodiments, the step of generating the ensemble forecast data includes: setting a forecast area including the region of interest among the forecast areas of the global forecast data having a first resolution as an initial background environment field; and applying the global forecast data to the initial background environment field to generate the local forecast data having a second resolution higher than the first resolution.

[0022] According to some embodiments, the local forecast data includes a plurality of second forecast data based on an AI prediction model, and the step of generating the ensemble forecast data includes the step of generating the ensemble forecast data by reflecting a plurality of probability densities of the plurality of second forecast data into the initial background environment field.

[0023] According to some embodiments, the local forecast data further includes first forecast data based on a numerical analysis model, and the AI ​​prediction model is configured to take the first forecast data as input and output the plurality of second forecast data.

[0024] According to some embodiments, the step of estimating the expected power generation amount includes the step of estimating the expected power generation amount in a probabilistic form based on the plurality of probability densities reflected in the ensemble forecast data.

[0025] According to some embodiments, a computer program stored on a computer-readable medium comprises instructions that, when executed by a processor, cause the processor to: generate weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs; generate a power generation estimation function based on the weather interpolation data and past power generation data of the renewable energy power plant; and estimate the expected power generation of the renewable energy power plant based on weather forecast data for the region of interest and the power generation estimation function.

[0026] According to some embodiments, the operation of generating the weather interpolation data includes the operation of generating the weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

[0027] According to some embodiments, the weather forecast data includes global forecast data and local forecast data, and the operation of estimating the expected power generation includes the operation of estimating the expected power generation based on the global forecast data, the local forecast data, and the power generation estimation function.

[0028] According to some embodiments, the operation of estimating the expected power generation amount includes: the operation of generating ensemble forecast data based on the global forecast data and the local forecast data; and the operation of estimating the expected power generation amount based on the ensemble forecast data and the power generation estimation function.

[0029] According to the embodiments disclosed in this document, an energy analysis device and an energy analysis method can be provided that can overcome the limitations of development curves defined through simulation or computer modeling and the limitations of weather forecasts provided as a single scenario.

[0030] The technical effects according to the embodiments disclosed in this document are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art in accordance with the disclosure of this document.

[0031] FIG. 1 illustrates a method of operation for an energy analysis device according to some embodiments.

[0032] FIG. 2 illustrates elements constituting an energy analysis device according to some embodiments.

[0033] Figure 3 illustrates a conventional method of generating a power generation curve and predicting power generation by considering it together with weather forecasts.

[0034] FIG. 4 illustrates a method for generating high-resolution weather forecast data using global forecast data and local forecast data according to some embodiments.

[0035] FIG. 5 illustrates a method of producing local forecast data against a global forecast data background to generate high-resolution weather forecast data according to some embodiments.

[0036] FIG. 6 illustrates a process of converting weather observation data and global forecast data to high resolution according to some embodiments.

[0037] FIG. 7 illustrates a method for estimating high-resolution weather observation data through data interpolation according to some embodiments.

[0038] FIG. 8 illustrates a method for predicting renewable energy generation using an ensemble method according to some embodiments.

[0039] FIG. 9 illustrates a power generation forecast based on an ensemble forecast from a probabilistic perspective according to some embodiments.

[0040] FIG. 10 illustrates steps constituting an energy analysis method according to some embodiments.

[0041] Hereinafter, embodiments described in this document are described with reference to the accompanying drawings. However, this is not intended to limit the disclosure of this document to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives to the embodiments described in this document.

[0042] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise.

[0043] 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. Terms such as “first,” “second,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used simply to distinguish a component from another component and, unless specifically stated otherwise, do not limit the components in any other aspect (e.g., importance or order).

[0044] In this document, where it is stated that any (e.g., 1) component is "connected," "coupled," or "joined" to another (e.g., 2) component, with or without the terms "functionally" or "communicationly," or where it is stated that the component is "coupled" or "connected," it means that the component may be connected to the other component directly (e.g., by wire or wirelessly) or indirectly (e.g., through a 3) component.

[0045] Methods according to the various embodiments disclosed in this document may be provided as part of 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 driver 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.

[0046] According to the embodiments disclosed in this document, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to the embodiments disclosed in this document, one or more of the components or operations of the aforementioned components 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 such a case, the integrated component may perform one or more functions of each of the components of the multiple components in the same or similar manner as those performed by the corresponding components among the multiple components prior to the integration. According to the embodiments disclosed in this document, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0047] FIG. 1 illustrates a method of operation for an energy analysis device according to some embodiments.

[0048] Referring to FIG. 1, an energy analysis device (130) can calculate the expected power generation amount (140) of a renewable energy power plant based on weather observation data (110) and weather forecast data (120). The operation of the energy analysis device (130) can be implemented in the form of a computer program, a mobile application, etc. The energy analysis device (130) can perform the process of calculating the expected power generation amount (140) by running the program and / or app.

[0049] Weather observation data (110) may include observed values ​​of weather variables such as temperature, humidity, and wind speed. Renewable energy power plants may include solar power plants, wind power plants, etc., and weather variables such as temperature, humidity, and wind speed may affect the amount of power generated by the renewable energy power plant. Weather observation data (110) may include observed values ​​for designated observation points. Since the observation points of the weather observation data (110) are limited, if the location of the renewable energy power plant is far from the observation points, the expected amount of power generated by the renewable energy power plant may not be accurately estimated.

[0050] Weather forecast data (120) may include values ​​of weather variables at a future point in time, and based thereon, an expected amount of power generation (140) may be estimated. Weather forecast data (120) may include global scale data and local scale data. Local scale data may have a higher resolution than the resolution of global scale data. Weather forecast data (120) may probabilistically consider various weather scenarios of global scale data and local scale data. The probabilistic weather scenarios of weather forecast data (120) may constitute an ensemble weather forecast.

[0051] The estimated power generation amount (140) can be calculated based on a power generation curve by an energy analysis device (130). The power generation curve may be a power generation estimation function representing the relationship between weather variables and power generation amount. According to an embodiment, the power generation curve can be generated based on weather observation data (110), and the estimated power generation amount (140) can be calculated by applying weather forecast data (120) to the power generation curve. The power generation curve can be estimated based on the values ​​of weather variables at past points in time according to the weather observation data (110) and the actual power generation amounts of renewable energy power plants at the same points in time. For example, the power generation curve can be generated through data fitting, machine learning training, etc., based on the values ​​of weather variables and power generation amounts. The power generation curve can most appropriately represent the relationship between past weather variables and power generation amounts, and when future weather forecast data (120) is applied to it, the estimated power generation amount (140) at a future point in time can be calculated.

[0052] FIG. 2 illustrates elements constituting an energy analysis device according to some embodiments.

[0053] Referring to FIG. 2, the energy analysis device (130) may include a memory (131) and a processor (132). However, it is not limited thereto, and some components may be omitted from the energy analysis device (130), or other components may be further included in the energy analysis device (130).

[0054] The processor (132) may have a structure for executing instructions that implement the operations of the energy analysis device (130). The processor (132) may be implemented as an array of logic gates or a general-purpose microprocessor for processing various operations, and may be composed of a single processor or multiple processors. For example, the processor (132) may be implemented in at least one form of a microprocessor, CPU, GPU, and AP.

[0055] The processor (132) can operate together with memory (131) configured to store various data, instructions, mobile applications, computer programs, etc. The memory (131) may be configured separately from or integrally with the processor (132). The memory (131) may store instructions for computer programs and / or mobile applications, and the processor (132) may execute instructions stored in the memory (131) to process various operations. For example, the memory (131) may be implemented as a non-volatile device such as ROM, PROM, EPROM, EEPROM, flash memory, PRAM, MRAM, RRAM, FRAM, etc., or as a volatile device such as DRAM, SRAM, SDRAM, PRAM, etc., and may be implemented in the form of an HDD, SSD, SD, Micro-SD, etc., or a combination thereof.

[0056] The processor (132) may be configured to generate weather interpolation data for a region of interest by performing data interpolation based on the observed values ​​of weather observation data (110) for a region of interest to which a renewable energy power plant belongs, by executing instructions stored in memory (131). The observed values ​​of the weather observation data (110) may be weather variable values ​​at observation points where observation equipment is installed. If the location of the observation equipment and the location of the renewable energy power plant are not close, the observed values ​​of the weather observation data (110) may differ from the weather variables that actually affect power generation at the power plant. To resolve this, data interpolation may be performed based on the observed values ​​of the weather observation data (110), and the weather variables that actually affect power generation at the power plant may be estimated.

[0057] The processor (132) can be configured to generate a power generation estimation function based on weather interpolation data and past power generation data of a renewable energy power plant by executing instructions stored in memory (131). The power generation estimation function can be generated in the form of a power curve. The power generation estimation function can be generated through data fitting, machine learning training, etc., and can express the relationship between past weather variables and past power generation data. Since weather interpolation data can be used as past weather variables, the power generation estimation function can have higher performance compared to the case where weather observation data (110), which has low accuracy due to location differences, is used.

[0058] A processor (132) may be configured to estimate the expected power generation of a renewable energy power plant based on weather forecast data (120) for a region of interest and a power generation estimation function by executing instructions stored in memory (131). The weather forecast data (120) may represent weather variables at a future point in time for the region of interest. By applying this to a power generation estimation function, the expected power generation of the renewable energy power plant can be estimated. According to an embodiment, the weather forecast data (120) may be a combination of global forecast data with a high scale and low resolution and local forecast data with a low scale and high resolution.

[0059] According to an embodiment, the energy analysis device (130) may be configured to generate weather interpolation data by performing data assimilation based on the Kriging interpolation technique on weather observation data (110). Data assimilation is a mathematical technique for estimating optimal values ​​at points where observations are not made, and can be utilized in the meteorological field to improve the accuracy of atmospheric numerical model data using atmospheric observation data. According to data assimilation based on the Kriging interpolation technique, even if actual observation values ​​do not exist at the location of a renewable energy power plant, the observation values ​​at that location can be estimated in an optimal form.

[0060] According to an embodiment, weather forecast data (120) may include global forecast data and local forecast data, and an energy analysis device (130) may be configured to estimate the expected power generation based on global forecast data, local forecast data, and a power generation estimation function. Global forecast data may show trends of weather phenomena on a global scale, but the spacing of the data grid may be wide, and the accuracy of the forecast regarding the location of renewable energy power plants may be low. Local forecast data specialized for a specific region may be additionally considered. Various weather scenarios can be handled by combining global forecast data and local forecast data, and in this case, the expected power generation (140) may be calculated in the form of a probabilistic distribution based on the probability values ​​of the scenarios.

[0061] According to an embodiment, the energy analysis device (130) may be configured to generate ensemble forecast data based on global forecast data and local forecast data, and to estimate the expected power generation based on the ensemble forecast data and a power generation estimation function. The ensemble forecast data may be forecast data that harmonizes the rough data of the global forecast data and the detailed data of the local forecast data. The ensemble forecast data may represent the probability distribution of various weather scenarios from a probabilistic perspective.

[0062] According to an embodiment, an energy analysis device (130) may be configured to set a forecast area including a region of interest among forecast areas of global forecast data having a first resolution as an initial background environment field, and to apply global forecast data to the initial background environment field to generate local forecast data having a second resolution higher than the first resolution. Since global forecast data has low resolution, it may not be able to accurately predict the actual weather of a renewable energy power plant. The initial background environment field may provide initial background data for generating local forecast data, and modification or optimization of the initial background environment field may be performed to generate more diverse ensemble forecast data.

[0063] According to an embodiment, local forecast data may include a plurality of second forecast data based on an AI prediction model, and an energy analysis device (130) may be configured to generate ensemble forecast data by reflecting a plurality of probability densities of the plurality of second forecast data into an initial background environment field. The plurality of second forecast data serving as the background of the local forecast data may correspond to various weather scenarios. Weather scenarios may be generated based on an AI prediction model. Each weather scenario may be expressed as the probability of a specific weather phenomenon occurring. Ensemble forecast data may be generated when the probability densities of the various weather scenarios are reflected into the initial background environment field of the global forecast data. For example, the AI ​​prediction model may include an artificial intelligence neural network model learned through various machine learning techniques. The learning of the AI ​​prediction model may be performed based on high-accuracy historical observation information accumulated over a long period through ground observation stations, radar, satellites, etc.

[0064] According to an embodiment, local forecast data may further include first forecast data based on a numerical analysis model, and the AI ​​prediction model may be configured to take the first forecast data as input and output a plurality of second forecast data. The numerical analysis model may have a higher amount of computation and complexity compared to the AI ​​prediction model. To increase the forecasting accuracy of the plurality of second forecast data based on the AI ​​prediction model, the first forecast data based on the numerical analysis model may be utilized as an input value for the AI ​​prediction model.

[0065] According to an embodiment, the energy analysis device (130) may be configured to estimate the expected power generation amount in a probabilistic form based on a plurality of probability densities reflected in ensemble forecast data. The ensemble forecast data may represent probability density values ​​for the realization of a plurality of weather scenarios, and the expected power generation amount may also be calculated in a probabilistic form. For example, the expected power generation amount in a probabilistic form may be a probability distribution that has a close relationship with the probability values ​​of various weather scenarios being realized.

[0066] Figure 3 illustrates a conventional method of generating a power generation curve and predicting power generation by considering it together with weather forecasts.

[0067] Referring to FIG. 3, a conventional technology (300) for generating a power generation curve and predicting the amount of power generated by considering it together with a weather forecast can be illustrated. In the conventional technology (300), a relationship (310) can be derived with respect to past weather conditions and the amount of renewable energy generated, and a power generation curve (320) can be generated therefrom. When a weather forecast (330) is applied to the power generation curve (320), a prediction of the amount of renewable energy generated (340) can be performed.

[0068] In the case of the conventional technology (300), the weather forecast (330) may use global forecast data as is. In this case, due to the low resolution of the global forecast data, a difference may occur between the forecast data and the location of the power plant, and the accuracy of the power generation prediction may be reduced. Additionally, since the weather forecast (330) provides a single scenario in a deterministic form, there may be uncertainty in the power generation prediction. Furthermore, since the past weather environment in the relationship derivation (310) represents only the designated observation points, the accuracy of the power generation prediction may be reduced if the location of the power plant is far from the observation points.

[0069] FIG. 4 illustrates a method for generating high-resolution weather forecast data using global forecast data and local forecast data according to some embodiments.

[0070] Referring to FIG. 4, an improved technique (400) illustrating a method for generating high-resolution weather forecast data using global forecast data and local forecast data may be illustrated. In the improved technique (400), the global weather forecast (410) can generate a weather forecast group based on a numerical model and an AI model and can be used as an initial field for the local weather forecast (420). The local weather forecast (420) can generate a high-resolution weather forecast group by utilizing the grid area to which the power plant belongs among the low-resolution data of the global weather forecast (410) as an initial field for the forecast. The local weather forecast (420) can operate based on a numerical model and an AI model and can generate a forecast group based on various weather scenarios.

[0071] Forecast data provided by existing domestic and international meteorological agencies, such as the Korea Meteorological Administration (KMA) and the European Centre for Medium-Range Weather Forecasts (ECMWF), is mostly based on global numerical models or global AI weather models. While the KMA provides some weather forecast data based on local numerical models, such as LDAPS (Local Data Assimilation and Prediction System), it offers only a single scenario. Forecast data derived from models based on a global scale has a spatial grid resolution of at least 10 km in latitude or longitude intervals, which corresponds to a relatively low resolution compared to the spatial scale of renewable energy power plants, which is only tens of meters. Furthermore, since forecast data from global models, like the KMA's LDAPS, generally provides only a single forecast scenario, additional scenarios may be required to ensure reliability.

[0072] Accordingly, as shown in Fig. 4, multiple weather forecast data can be generated independently by utilizing a local numerical model and a local AI weather model. Since the local numerical model and the local AI model simulate atmospheric movements in a limited region rather than the entire globe, they can produce forecast data by reflecting changes in local weather phenomena that cannot be realized in global models.

[0073] FIG. 5 illustrates a method of applying local forecast data to global forecast data to generate high-resolution weather forecast data according to some embodiments.

[0074] Referring to FIG. 5, a method of producing local forecast data (520) against a global forecast data (510) to generate high-resolution weather forecast data can be illustrated. Among the low-resolution grid regions of the global forecast data (510), the region where the power plant is located can be the initial background environment field, and high-resolution weather forecast data can be generated through the production of local forecast data (520) based on this. A local numerical model and a local AI model can generate high-resolution data by utilizing the initial background environment field.

[0075] Weather Research and Forecasting (WRF) models can be utilized as local numerical models. However, WRF models are based on traditional numerical simulation techniques that sequentially compute complex dynamic and physical equations, and processing high-resolution data can require massive amounts of computing power and costs. In contrast, AI weather models can produce forecast data with high accuracy while requiring lower costs and infrastructure compared to numerical models. Since it takes only minutes to tens of minutes for an AI weather model to generate a single forecast scenario, a large volume of scenarios can be generated compared to numerical models, and ensemble analysis can be performed on them. To accurately represent weather phenomena in a specific region, AI weather models can be trained based on high-accuracy historical observation data accumulated over long periods through ground stations, radar, and satellites. To enhance forecast accuracy, forecast data generated by local numerical models can be used as input for local AI weather models.

[0076] FIG. 6 illustrates a process of converting weather observation data and low-resolution global forecast data into high resolution according to some embodiments.

[0077] Referring to FIG. 6, a flow (600) illustrating a process of converting weather observation data and low-resolution global forecast data into high resolution can be illustrated. In the flow (600), existing data (610) may include existing past weather conditions and weather forecast sets, and resolution enhancement (620) may be performed based on the existing data (610). Resolution enhancement (620) may include data interpolation based on data assimilation methodologies. Improved data (630) may be generated by the resolution enhancement (620). Improved data (630) may include high-resolution past weather conditions and high-resolution weather forecast sets.

[0078] Excluding satellites operating outside the atmosphere, weather phenomena are observed relatively locally through ground stations, radar, and lidar. Consequently, there may be numerous regions where weather phenomena are not directly observed, and renewable energy power plants are highly likely to be located in these blind spots. Since accumulated observational data regarding past weather conditions does not exist in these blind spots, it may be necessary to estimate data for these areas based on observations from nearby regions.

[0079] Similarly, forecast data generated by domestic and international weather agencies using global numerical models and global AI weather models may be from regions far removed from the location of renewable energy power plants due to large grid spacing. Therefore, in order to construct a power generation curve by analyzing the relationship with power generation based on more accurate weather information, it may be necessary to convert the weather data to high resolution. Through a procedure as shown in Figure 6, historical weather observation data and weather forecast data located far from power plants can be converted into high-resolution data with grid units ranging from several kilometers to hundreds of meters using a 3D data assimilation methodology. Kriging can be utilized as a method for data assimilation.

[0080] FIG. 7 illustrates a method for estimating high-resolution weather observation data through data interpolation according to some embodiments.

[0081] Referring to FIG. 7, point data (710) can be converted into high-resolution grid data (720) by estimating high-resolution weather observation data through data interpolation.

[0082] Kriging-based data assimilation can estimate necessary values ​​by synthesizing three-dimensional spatial information on observation data located near the location where data generation is required, calculating statistical weights, and applying them. For example, if Kriging data assimilation reflecting topographic information is performed on temperature values ​​recorded at observation stations of point data (710), high-resolution grid data (720) with a high-resolution grid of 500 meters can be generated. High-resolution grid data (720) can clearly show the tendency for temperature to decrease as altitude increases. According to this data assimilation methodology, a more accurate power generation curve can be constructed even for power plants located in areas where data does not exist.

[0083] FIG. 8 illustrates a method for predicting renewable energy generation using an ensemble method according to some embodiments.

[0084] Referring to FIG. 8, a flow (800) regarding a method for predicting renewable energy generation in an ensemble manner may be illustrated. The improvement data (630) of the flow (800) may be the same as the improvement data (630) of FIG. 6. Once the improvement data (630) is generated, a weather environment field extraction (640) may be performed based thereon.

[0085] The relationship derivation (810) of FIG. 8 can be compared with the relationship derivation (310) of the prior art (300) of FIG. 3. In the relationship derivation (810), a relationship between the past weather environment converted to high resolution and the amount of power generation can be derived, and a power generation curve (820) can be generated based on this. When a high-resolution converted ensemble weather forecast (830) is applied to the power generation curve (820), a renewable energy power generation ensemble prediction (840) can be performed.

[0086] When meteorological observation data is converted to high resolution, information more suitable for the location of the power plant can be provided based on it. When meteorological observation data is provided as high-resolution grid values, terrain information weights can be applied to the grid values ​​based on the location of the power plant, and meteorological variables at the location can be estimated. Based on this, a power generation curve capable of performing more accurate power generation forecasting can be constructed.

[0087] FIG. 9 illustrates a power generation forecast based on an ensemble forecast from a probabilistic perspective according to some embodiments.

[0088] Referring to FIG. 9, an ensemble forecast (920) generated based on multiple forecast scenarios (910) provided by a local AI forecast model can be illustrated. The multiple forecast scenarios (910) can provide weather forecasts from a probabilistic perspective, and the ensemble forecast (920) can be generated in the form of a probability distribution.

[0089] Compared to using existing single-scenario-based forecast data, power generation can be predicted from a probabilistic perspective by utilizing a multi-scenario forecast model provided through a combination of global and local forecast data. When applying ensemble forecasting from a probabilistic perspective to the power generation curve, ensemble power generation forecasting can be performed, which can improve the reliability of power generation forecasting based on a probability density function.

[0090] FIG. 10 illustrates steps constituting an energy analysis method according to some embodiments.

[0091] Referring to FIG. 10, the energy analysis method (1000) may include steps (1010) through (1030). However, it is not limited thereto, some steps may be omitted or other general steps may be added, and the steps of the energy analysis method (1000) may be executed in a different order than the illustrated order.

[0092] The energy analysis method (1000) may consist of steps processed sequentially in the energy analysis device (130). Therefore, even if the details are omitted below, the description of the energy analysis device (130) above may be equally applicable to the energy analysis method (1000).

[0093] Steps (1010) to (1030) of the energy analysis method (1000) can be performed by the memory (131) and processor (132) of the energy analysis device (130).

[0094] In step (1010), the energy analysis device (130) may perform the step of generating weather interpolation data for a region of interest by performing data interpolation based on the observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs.

[0095] In step (1020), the energy analysis device (130) may perform the step of generating a power generation estimation function based on weather interpolation data and past power generation data of a renewable energy power plant.

[0096] In step (1030), the energy analysis device (130) can perform the step of estimating the expected power generation of a renewable energy power plant based on weather forecast data for the area of ​​interest and a power generation estimation function.

[0097] According to an embodiment, the energy analysis method (1000) may be implemented in the form of a computer program stored on a computer-readable storage medium. That is, the computer program may include instructions for implementing the energy analysis method (1000), and the instructions of the program may be stored on a computer-readable storage medium. The computer program may include a mobile application.

[0098] According to an embodiment, a computer-readable storage medium may include magnetic media such as a hard disk, a floppy disk, and a magnetic tape, optical media such as a CD-ROM and a DVD, magneto-optical media such as a floptical disk, and a hardware device specifically configured to store and execute computer program instructions such as ROM, RAM, and flash memory. Computer program instructions may include machine code generated by a compiler and high-level language code that can be executed by a computer using an interpreter, etc.

[0099] Terms such as "include," "compose," or "have" as used above, unless specifically stated otherwise, mean that the relevant component may be inherent; therefore, 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 meaning in the context of the relevant technology and, unless explicitly defined in this document, should not be interpreted in an ideal or overly formal sense.

[0100] The foregoing description is merely an illustrative explanation of the technical concept disclosed in this document, and a person skilled in the art to which the embodiments disclosed in this document pertain can make various modifications and variations within the scope of the essential characteristics of the embodiments disclosed in this document. Accordingly, the embodiments disclosed in this document are intended to explain, not limit, the technical concept of the embodiments disclosed in this document, and the scope of the technical concept disclosed in this document is not limited by these embodiments. The scope of protection of the technical concept disclosed in this document shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this document.

Claims

1. Processor; and When executed by the above processor, the above processor: The operation of generating weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs, The operation of generating a power generation estimation function based on the above weather interpolation data and the past power generation data of the above renewable energy power plant, and An energy analysis device comprising: a memory configured to store instructions for performing an operation to estimate the expected power generation of the renewable energy power plant based on weather forecast data for the area of ​​interest and the power generation estimation function.

2. In Paragraph 1, The operation of generating the above weather interpolation data is, An energy analysis device comprising the operation of generating weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

3. In Paragraph 1, The above weather forecast data includes global forecast data and local forecast data, and The operation of estimating the above-mentioned expected power generation is, An energy analysis device comprising an operation of estimating the expected power generation amount based on the above global forecast data, the above local forecast data, and the above power generation estimation function.

4. In Paragraph 3, The operation of estimating the above-mentioned expected power generation is, An operation to generate ensemble forecast data based on the above global forecast data and the above local forecast data; and An energy analysis device comprising an operation of estimating the expected power generation amount based on the above ensemble forecast data and the above power generation estimation function.

5. In Paragraph 4, The operation of generating the above ensemble forecast data is, The operation of setting a forecast area including the region of interest among the forecast areas of the global forecast data having a first resolution as an initial background environment field; and An energy analysis device comprising the operation of applying the global forecast data to the initial background environment field to generate the local forecast data having a second resolution higher than the first resolution.

6. In Paragraph 5, The above local forecast data includes multiple second forecast data based on an AI prediction model, and The operation of generating the above ensemble forecast data is, An energy analysis device comprising the operation of generating ensemble forecast data by reflecting a plurality of probability densities of the plurality of second forecast data into the initial background environment field.

7. In Paragraph 6, The above local forecast data further includes first forecast data based on a numerical analysis model, and An energy analysis device configured such that the above AI prediction model takes the above first forecast data as input and outputs the above plurality of second forecast data.

8. In Paragraph 6, The operation of estimating the above-mentioned expected power generation is, An energy analysis device comprising an operation of estimating the expected power generation amount in a probabilistic form based on the plurality of probability densities reflected in the ensemble forecast data.

9. A step of generating weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs; A step of generating a power generation estimation function based on the above weather interpolation data and the past power generation data of the above renewable energy power plant; and An energy analysis method comprising: a step of estimating the expected power generation of the renewable energy power plant based on weather forecast data for the area of ​​interest and the power generation estimation function.

10. In Paragraph 9, The step of generating the above weather interpolation data is, An energy analysis method comprising the step of generating weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

11. In Paragraph 9, The above weather forecast data includes global forecast data and local forecast data, and The step of estimating the above-mentioned expected power generation is, An energy analysis method comprising the step of estimating the expected power generation based on the above global forecast data, the above local forecast data, and the above power generation estimation function.

12. In Paragraph 11, The step of estimating the above-mentioned expected power generation is, A step of generating ensemble forecast data based on the global forecast data and the local forecast data; and An energy analysis method comprising the step of estimating the expected power generation based on the ensemble forecast data and the power generation estimation function.

13. In Paragraph 12, The step of generating the above ensemble forecast data is, A step of setting a forecast area including the region of interest among the forecast areas of the global forecast data having a first resolution as an initial background environment field; and An energy analysis method comprising the step of applying the global forecast data to the initial background environment field to generate the local forecast data having a second resolution higher than the first resolution.

14. In Paragraph 13, The above local forecast data includes multiple second forecast data based on an AI prediction model, and The step of generating the above ensemble forecast data is, An energy analysis method comprising the step of generating ensemble forecast data by reflecting multiple probability densities of the multiple second forecast data into the initial background environment field.

15. In Paragraph 14, The above local forecast data further includes first forecast data based on a numerical analysis model, and An energy analysis method in which the above AI prediction model is configured to take the above first forecast data as input and output the above plurality of second forecast data.

16. In Paragraph 14, The step of estimating the above-mentioned expected power generation is, An energy analysis method comprising the step of estimating the expected power generation amount in a probabilistic form based on the plurality of probability densities reflected in the ensemble forecast data.

17. When executed by a processor, the processor: The operation of generating weather interpolation data for a region of interest by performing data interpolation based on observed values ​​of weather observation data for a region of interest to which a renewable energy power plant belongs; The operation of generating a power generation estimation function based on the above weather interpolation data and the past power generation data of the above renewable energy power plant; and A computer program stored on a computer-readable medium, comprising instructions for performing an operation to estimate the expected power generation of the renewable energy power plant based on weather forecast data for the area of ​​interest and the power generation estimation function.

18. In Paragraph 17, The operation of generating the above weather interpolation data is, A computer program stored on a computer-readable medium, comprising the operation of generating weather interpolation data by performing data assimilation based on the Kriging interpolation technique on the weather observation data.

19. In Paragraph 17, The above weather forecast data includes global forecast data and local forecast data, and The operation of estimating the above-mentioned expected power generation is, A computer program stored on a computer-readable medium, comprising the operation of estimating the expected power generation based on the above global forecast data, the above local forecast data, and the above power generation estimation function.

20. In Paragraph 19, The operation of estimating the above-mentioned expected power generation is, An operation to generate ensemble forecast data based on the above global forecast data and the above local forecast data; and A computer program stored on a computer-readable medium, comprising the operation of estimating the expected power generation amount based on the ensemble forecast data and the power generation estimation function.

Images