Apparatus and method for predicting power generation and controlling energy generation facility

By integrating predicted and observed weather data with machine learning models, the method enhances energy generation forecasting and control, addressing accuracy issues and stabilizing power grid operations.

KR103045486B1Active Publication Date: 2026-11-10SAMSUNG C&T CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
KR1020250136464
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2025-09-22
Publication Date
2026-11-10
Estimated Expiration
2045-09-22

AI Technical Summary

Technical Problem

Existing energy generation forecasting methods face limitations in accuracy due to the complex and non-linear nature of meteorological variables, leading to inefficiencies in energy generation systems and unstable power grid supply.

Method used

A method and apparatus that utilize predicted weather data, satellite data, and observed weather data from multiple cluster regions within an energy generation complex, employing machine learning models to enhance prediction accuracy and control energy generation facilities through an energy management system.

Benefits of technology

Improves energy generation prediction accuracy and stability by leveraging localized weather data, enabling efficient operation and storage of energy, and ensuring stable power grid supply.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112025108351379-PAT00002_ABST
    Figure 112025108351379-PAT00002_ABST
Patent Text Reader

Abstract

A method and apparatus for predicting the amount of energy generated by an energy generation complex and controlling energy generation facilities within the energy generation complex are disclosed. The method for predicting the amount of energy generated by an energy generation complex and controlling energy generation facilities within the energy generation complex may include the operation of obtaining predicted weather data including weather variable values ​​regarding a region where the energy generation complex is located from a weather forecasting agency—wherein the energy generation complex includes a plurality of cluster regions each including an energy generation facility—; the operation of obtaining satellite data regarding a region where the energy generation complex is located from a satellite data provider; the operation of obtaining observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device disposed in each of the cluster regions; the operation of providing the predicted weather data, satellite data, and observed weather data obtained from each of the cluster regions to a learned energy generation amount prediction model; and the operation of obtaining predicted data regarding the amount of energy generated by the energy generation complex from the energy generation amount prediction model.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present disclosure relates to a method and apparatus for predicting the amount of energy generated in an energy generation complex and controlling energy generation facilities within the energy generation complex. Background Technology

[0003] Renewable energy generation, such as solar and wind power, is attracting global attention as a core technology leading the era of energy transition, serving as an eco-friendly and sustainable energy source. Since renewable energy generation is significantly influenced by various meteorological conditions, such as solar radiation, temperature, and cloud cover, accurately predicting energy generation is an essential task for the efficient operation of energy generation systems and the stable supply of energy. While the precision of energy generation forecasting plays a crucial role in balancing supply and demand in the power grid, there may be limitations to prediction accuracy due to the complex changes and non-linear characteristics of meteorological variables. Accordingly, the field of energy generation forecasting is developing more efficient and reliable prediction techniques by applying machine learning methods based on meteorological variables, such as temperature or solar radiation, to reflect the non-linear nature of meteorological variables and improve prediction accuracy.

[0005] A method for predicting the amount of energy generated by an energy generation complex and controlling energy generation facilities within the energy generation complex according to one embodiment may include: acquiring predicted weather data including weather variable values ​​regarding a region where the energy generation complex is located from a weather forecasting agency - wherein the energy generation complex includes a plurality of cluster regions each including an energy generation facility -; acquiring satellite data regarding a region where the energy generation complex is located from a satellite data provider; acquiring observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device disposed in each of the cluster regions; providing the predicted weather data, satellite data, and observed weather data acquired from each of the cluster regions to a learned energy generation amount prediction model; and acquiring predicted data regarding the amount of energy generated by the energy generation complex from the energy generation amount prediction model.

[0006] The plurality of cluster regions above include at least a first cluster region and a second cluster region, and the operation of acquiring prediction data may include the operation of acquiring first prediction data for the amount of energy generated by the first cluster region from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data acquired regarding the second cluster region; the operation of acquiring second prediction data for the amount of energy generated by the second cluster region from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data acquired regarding the first cluster region; and the operation of acquiring prediction data for the amount of energy generated by an energy generation complex based on the first prediction data and the second prediction data.

[0007] The above method may further include the operation of transmitting observed weather data obtained from each of the cluster areas to an energy management system and the operation of controlling energy generation facilities included in each of the cluster areas using the energy management system based on the obtained prediction data.

[0008] The operation of controlling the energy generation facility may include controlling the energy generated from the energy generation facility included in each of the cluster regions to be stored in an energy storage device or to be discharged from the energy storage device based on acquired prediction data.

[0009] The operation of controlling the energy generation facility may include an operation of predicting a weather change in a second cluster area based on a time series pattern of observed weather data acquired with respect to a first cluster area, and an operation of controlling an energy generation facility included in the second cluster area using an energy management system based on the predicted weather change and the acquired prediction data.

[0010] The operation of controlling the energy generation facility may include an operation of predicting weather changes regarding a reduction in solar radiation or the occurrence of gusts due to rain clouds entering the second cluster area based on a time series pattern of observed weather data acquired regarding the first cluster area, and an operation of controlling the energy generation facility included in the second cluster area to limit its power output and store the generated energy in an energy storage device using an energy management system based on the predicted weather changes and acquired prediction data.

[0011] The operation of controlling the energy generation facility may include detecting a signal indicating weather recovery in the second cluster area based on a time series pattern of observed weather data acquired with respect to the first cluster area, and, when the signal is detected, controlling the normal power generation of the energy generation facility included in the second cluster area using an energy management system.

[0012] The above energy generation facility may include at least one of a solar power generation facility and a wind power generation facility.

[0013] The weather variable values ​​included in the above-mentioned predicted weather data include at least one of a predicted solar radiation value, a predicted temperature value, a predicted wind speed value, a predicted wind direction value, and a predicted humidity value for a future time point obtained from a weather forecasting agency, and the weather variable values ​​included in the observed weather data may include at least one of a observed solar radiation value, a observed temperature value, a observed wind speed value, a observed wind direction value, and a observed humidity value for a current time point obtained for each of the cluster regions.

[0014] The weather observation devices included in each of the above cluster regions may be capable of communicating with each other.

[0015] An electronic device for predicting the amount of energy generated by an energy power generation complex and controlling energy generation facilities within the energy power generation complex according to one embodiment includes a communication circuit that communicates with a plurality of weather observation devices, a memory that stores instructions, and a processor for executing instructions. When instructions are executed by the processor, the electronic device may obtain predicted weather data including weather variable values ​​regarding a region where the energy power generation complex is located from a weather forecasting agency - the energy power generation complex includes a plurality of cluster regions each including an energy generation facility -, obtain satellite data regarding a region where the energy power generation complex is located from a satellite data provider, obtain observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device placed in each of the cluster regions, provide the predicted weather data, satellite data, and the observed weather data obtained from each of the cluster regions to a learned energy generation amount prediction model, and obtain predicted data for the amount of energy generated by the energy power generation complex from the energy generation amount prediction model.

[0016] When instructions are executed by the above processor, the electronic device may obtain first prediction data for the amount of energy generated by the first cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the second cluster area, obtain second prediction data for the amount of energy generated by the second cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the first cluster area, and obtain prediction data for the amount of energy generated by the energy generation complex based on the first prediction data and the second prediction data.

[0017] When instructions are executed by the above processor, the electronic device transmits observed weather data acquired in each of the cluster areas to an energy management system and can control energy generation facilities included in each of the cluster areas using the energy management system based on the acquired forecast data.

[0018] When instructions are executed by the above processor, the electronic device can control to store energy generated from an energy generation facility included in each of the cluster regions in an energy storage device or to discharge energy from an energy storage device based on acquired prediction data.

[0019] When instructions are executed by the above processor, the electronic device can predict weather changes in the second cluster area based on the time series pattern of observed weather data acquired with respect to the first cluster area, and control energy generation facilities included in the second cluster area using an energy management system based on the predicted weather changes and acquired prediction data.

[0020] When instructions are executed by the above processor, the electronic device can predict weather changes regarding a reduction in solar radiation or the occurrence of gusts due to rain clouds entering the second cluster area based on the time series pattern of observed weather data acquired regarding the first cluster area, and control the energy management system to limit the power generation output of the energy generation facility included in the second cluster area and store the generated energy in an energy storage device based on the predicted weather changes and the acquired prediction data.

[0021] When instructions are executed by the above processor, the electronic device detects a signal indicating weather recovery in the second cluster area based on the time series pattern of observed weather data acquired with respect to the first cluster area, and when the signal is detected, it can control the resumption of normal power generation of the energy generation facility included in the second cluster area using an energy management system. Brief explanation of the drawing

[0023] FIG. 1 is a diagram illustrating an overview of a predictive control system for energy generation according to one embodiment. FIG. 2 is a diagram illustrating the architecture of a predictive control system according to one embodiment. FIG. 3 is a flowchart illustrating the operations of a method for predicting energy generation amount according to one embodiment. FIG. 4 is a flowchart illustrating the operations of a method for controlling an energy generation facility according to one embodiment. FIG. 5 is a block diagram illustrating the configurations of an electronic device according to one embodiment. Specific details for implementing the invention

[0024] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0025] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0026] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0027] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0028] 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. 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 specification.

[0029] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0031] FIG. 1 is a diagram illustrating an overview of a predictive control system for energy generation according to one embodiment.

[0032] Referring to FIG. 1, the predictive control system (100) for energy generation may be a system that predicts the amount of energy generated in an energy generation complex (e.g., the energy generation complex (200) of FIG. 2) using an electronic device (110). The predictive control system (100) may control the operation of an energy generation facility (e.g., a solar power facility and / or a wind power facility) equipped in the energy generation complex based on the predicted amount of energy generated.

[0033] In one embodiment, the electronic device (110) may include an energy generation amount prediction model (120) that predicts the amount of energy generated in an energy generation complex. The electronic device (110) may obtain prediction data (190) for the amount of energy generated by the energy generation complex based on predicted weather data (160) obtained from a weather forecasting agency (130), satellite data (170) obtained from a satellite data provider (140), and observed weather data (180) obtained from a weather observation device (150). The electronic device (110) may obtain the prediction data (190) by providing the predicted weather data (160), satellite data (170), and / or observed weather data (180) to the learned energy generation amount prediction model (120).

[0034] In one embodiment, the electronic device (110) may obtain predicted weather data (160) from a weather forecasting agency (130). The weather forecasting agency (130) may include, but is not limited to, a meteorological agency that provides predicted weather data (160) using a numerical weather prediction (NWP) model, such as a local forecasting model (LDAPS). The predicted weather data (160) may include a plurality of predicted weather variable values. The plurality of weather variable values ​​included in the predicted weather data (160) may include at least one of a predicted solar radiation value, a predicted temperature value, a predicted wind speed value, a predicted wind direction value, and a predicted humidity value for a future time point obtained from the weather forecasting agency (130). For example, the electronic device (110) may receive a predicted solar radiation value, a predicted temperature value, a predicted wind speed value, a predicted wind direction value, and a predicted humidity value for an energy power generation complex equipped with an energy generation facility from the meteorological agency.

[0035] In one embodiment, the electronic device (110) may obtain satellite data (170) from a satellite data provider (140). The satellite data (170) may be generated by a geostationary satellite (e.g., Korea's Cheollian satellite) that continuously observes a specific region of the Earth and transmits (or provides) image data or numerical data at regular intervals. The satellite data provider (140) may include, for example, a national weather satellite center that processes weather satellite data, but is not limited thereto. The satellite data (170) may include satellite image-based data regarding the region where the energy generation complex is located. The satellite data (170) may include image data including cloud movement images regarding the region where the energy generation complex is located, and numerical data including solar radiation observation values ​​based on cloud movement information. The satellite data (170) may be received from the satellite data provider (140) at regular time intervals. For example, cloud movement images can be acquired at 2-minute intervals in the Korean Peninsula region, 10-minute intervals in the East Asian region, and 10-minute intervals in the global region, and solar radiation observation values ​​can be acquired at 30-minute intervals. Cloud movement information and / or solar radiation change information can be updated at every hour interval according to satellite data (170) provided at regular time intervals.

[0036] In one embodiment, the electronic device (110) may obtain observed weather data (180) from a weather observation device (150). The observed weather data (180) may include a plurality of weather variable values ​​obtained from various measurement sensors equipped in the weather observation device (150). The plurality of weather variable values ​​included in the observed weather data (180) may include, for example, at least one of the observed solar radiation value at the current time, the observed temperature value at the current time, the observed wind speed value at the current time, the observed wind direction value at the current time, and the observed humidity value at the current time obtained from the weather observation device (150). The plurality of weather variable values ​​may be values ​​measured using a solar radiation meter, an ambient air thermometer, an anemometer, a wind direction meter, and / or a hygrometer.

[0037] In one embodiment, the weather observation device (150) may include a permanent weather mast or a LiDAR-based wind speed observation device for measuring weather variables such as wind speed, wind direction, temperature, and humidity over a long period. The permanent weather mast may be designed to stably collect weather data over a long period by installing a plurality of weather observation sensors on a structure of a certain height. The LiDAR-based wind speed observation device may use a laser to remotely measure wind speed and wind direction at various altitudes in the sky.

[0038] The electronic device (110) can obtain energy generation prediction data (190) using an energy generation prediction model (120). For example, the energy generation prediction data (190) may include predicted data of potential generation of an energy generation complex corresponding to 15-minute, 30-minute, and 1-hour intervals. The energy generation prediction model (120) may include various machine learning models or deep learning models. Machine learning models may include, for example, XGBoost, NGBoost, CatBoost, ExtraTrees, Gradient Boosting, and Random Forest, but are not limited thereto. Deep learning models may include, for example, CNN (convolutional neural network), LSTM (long short-term memory), GRU (gated recurrent unit), and iTransformer, but are not limited thereto.

[0039] The energy generation prediction model (120) may be learned based on weather variable values ​​forecasted at a past point in time, weather variable values ​​observed at a past point in time, and actual energy generation obtained at a past point in time. As predicted weather data (160), satellite data (170), and / or observed weather data (180) are input, the energy generation prediction model (120) may extract the energy generation amount from a past point in time that was calculated from data similar to the input data and output it as a predicted value of the energy generation amount at a future point in time.

[0040] In one embodiment, assuming that the energy generation prediction model (120) is a deep learning model, the energy generation prediction model (120) can be trained according to a machine learning process. The machine learning process is a process that enables the energy generation prediction model (120) to recognize patterns in the input data and make predictions on its own using given data. In one embodiment, the machine learning process may include the steps of (1) data preparation, (2) model initialization, (3) forward calculation, (4) loss calculation, (5) backpropagation, and (6) parameter updating.

[0041] The data preparation process is a process of collecting and preprocessing training data for the energy generation prediction model (120) to learn. The preprocessing process may include refining the training data and, if necessary, performing tasks such as standardization, normalization, and feature selection to make the training data suitable for the energy generation prediction model (120). The model initialization process is a process of setting the initial parameters of the energy generation prediction model (120). For example, if the energy generation prediction model (120) is a neural network, the model initialization process may include a step of initializing weights and biases. The forward calculation process is a process of inputting the prepared training data into the energy generation prediction model (120) to calculate a predicted value for energy generation. In this process, the energy generation prediction model (120) may process the training data using current parameters and generate a predicted value as an output value. The loss calculation process is a process of calculating the difference between the predicted value of the energy generation prediction model (120) and the actual correct answer (label) through a loss function. The loss function is a function that allows for the calculation of a value indicating how accurate (or inaccurate) the prediction of the energy generation prediction model (120) is. The backpropagation process is a process of adjusting the parameters of the energy generation prediction model (120) to reduce the loss derived through the loss function. By differentiating (gradienting) the value of the loss function through the backpropagation algorithm, the amount each parameter of the energy generation prediction model (120) contributes to the loss is calculated, and the parameters of the energy generation prediction model (120) can be updated based on this value. The parameter update process is a process of updating the parameters of the energy generation prediction model (120) using the calculated gradient. Gradient descent or a variation thereof may usually be used in parameter updating.Through this process, the energy generation prediction model (120) can be trained to perform more accurate predictions step by step. The above processes (e.g., forward calculation, loss calculation, backpropagation, parameter update) can be repeated multiple times for a large amount of training data, and training can be performed over multiple cycles until the energy generation prediction model (120) is sufficiently trained. Through this training process, the energy generation prediction model (120) can learn patterns from given data and have the ability to predict new data.

[0042] In a large-scale energy generation complex, a number of weather observation devices (150) may be installed over a wide area. The energy generation complex may be divided into multiple cluster areas. An energy generation prediction model (120) can determine prediction data (190) for the amount of energy generated in each cluster area where a weather observation device (150) is installed, based on predicted weather data (160), satellite data (170), and / or observed weather data (180) obtained from multiple weather observation devices (150) located in the energy generation complex. The energy generation prediction model (120) can determine the prediction data (190) for the amount of energy generated in each of the multiple cluster areas individually for each cluster area. This is intended to utilize locally measured observed weather data (180) in determining the prediction data (190), out of concern that errors in energy generation prediction may occur if only the same predicted weather data (160) and a single observed weather data (180) are used in a large-scale energy generation complex.

[0043] The electronic device (110) can establish (or determine) an operation plan (195) for an energy generation facility based on prediction data (190) regarding the amount of energy generated. The electronic device (110) can perform control over the energy generation facility and the energy storage device. The electronic device (110) can use an energy management system (e.g., the energy management system (260) of FIG. 2) to enable a solar power generation device and / or a wind power generation device to operate in conjunction with an energy storage device. Through this, the electronic device (110) can ensure the stability of the energy generation facility, extend the lifespan of the energy generation facility, and enable stable operation of the power grid.

[0044] More detailed information regarding the prediction of energy generation and the control of energy generation facilities is explained with reference to Figure 2 below.

[0046] FIG. 2 is a diagram illustrating the architecture of a predictive control system according to one embodiment.

[0047] Referring to FIG. 2, the energy generation complex (200) may include various types of renewable energy generation facilities. For example, the energy generation complex (200) may include a solar power complex equipped with solar power generation facilities, a wind power complex equipped with wind power generation facilities, or a combination thereof.

[0048] A solar power generation facility (or solar power generation device) may include at least one photovoltaic array (PV array) that performs solar power generation using sunlight. The photovoltaic array may be implemented by connecting a plurality of photovoltaic modules (PV modules), and a photovoltaic module may include a plurality of photovoltaic cells (PV cells). A wind power generation facility (or wind power generation device) may include at least one wind turbine that converts the kinetic energy of wind into electrical energy. The wind turbine may include a blade that rotates around a rotation axis, a gearbox that accelerates the rotational motion of the blade, and a generator that converts the rotational motion into electrical energy.

[0049] In the case of a solar power plant, the power generation efficiency can vary significantly depending on weather conditions such as solar radiation, cloud movement, and temperature changes. For example, if clouds move rapidly or occur locally, the amount of solar radiation reaching the solar power facility can fluctuate significantly, causing the power output to fluctuate greatly within a short period, which can lead to instability in the power grid. In high-temperature environments such as summer, the surface temperature of the solar power device rises, which not only reduces conversion efficiency but also causes thermal stress to accumulate in power conversion devices such as modules and inverters. In the case of a wind power plant, it can be significantly affected by weather conditions such as typhoons or sudden strong winds, and rapid changes in weather conditions can cause not only rapid fluctuations in power generation but also risks to the stability of the wind power device. In the case of a large-scale energy power plant (200), even if it is a single plant, the predicted weather data transmitted by the weather forecasting agency may differ significantly from the actual weather changes. Therefore, if the amount of energy generated is predicted based on the same weather data in all areas of the energy power plant (200), there is a possibility that a large error will occur compared to the actual amount of power generated.

[0050] In one embodiment, an electronic device (e.g., the electronic device (110) of FIG. 1) can divide a large-scale energy generation complex (200) into a plurality of cluster areas (215, 225, 235, 245, 255) and perform energy generation amount prediction for each cluster area. The electronic device can predict the energy generation amount of other cluster areas where weather changes occur rapidly or observational weather data is insufficient by utilizing observational weather data collected in a specific cluster area, predictional weather data obtained from a weather forecasting agency, and satellite data obtained from a satellite data provider. Through this, the electronic device can increase the prediction accuracy for the large-scale energy generation complex (200) and respond to local fluctuations in weather conditions. Through the electronic device, it is possible to make a more accurate prediction of energy generation amount based on observational weather data measured in real time, even in countries (or regions) where there is no weather observation agency in the country and there is a delay in the time when predictional weather data is obtained or the frequency of obtaining predictional weather data is insufficient. By utilizing the weather observation devices (210, 220, 230, 240, 250) owned within the energy generation complex (200), a more accurate prediction of energy generation can be performed without relying on predicted weather data even when the network with the outside is disconnected.

[0051] In the embodiment of FIG. 2, the energy generation complex (200) may be divided into a plurality of cluster areas (215, 225, 235, 245, 255). Each of the plurality of cluster areas (215, 225, 235, 245, 255) may be equipped with weather observation devices (210, 220, 230, 240, 250) for collecting observed weather data. The first cluster area (215) may include a first weather observation device (210). The second cluster area (225) may include a second weather observation device (220). The third cluster area (235) may include a third weather observation device (230). The fourth cluster area (245) may include a fourth weather observation device (240). The fifth cluster area (255) may include the fifth weather observation device (250). For convenience of explanation, the number of multiple cluster areas (215, 225, 235, 245, 255) is shown as five, but the number of cluster areas (215, 225, 235, 245, 255) is not limited thereto. Alternatively, for example, the energy generation complex (200) may be divided into cluster areas in four quartiles of east, west, north, and south. If the frequency of the prevailing wind direction is high, the energy generation complex (200) may be divided into two or three cluster areas.

[0052] Weather observation devices (210, 220, 230, 240, 250) can collect observed weather data in the cluster area where each weather observation device is located. Weather observation devices (210, 220, 230, 240, 250) can collect at least one of solar radiation observation values, temperature observation values, wind speed observation values, wind direction observation values, and humidity observation values ​​for each of the cluster areas (215, 225, 235, 245, 255). Each weather observation device installed in the multiple cluster areas (215, 225, 235, 245, 255) can collect different types of weather data considering the measurement range and cost.

[0053] The electronic device can provide predicted weather data obtained from a weather forecasting agency, satellite data obtained from a satellite data provider, and observed weather data obtained from each of the cluster areas (215, 225, 235, 245, 255) to a learned energy generation prediction model (e.g., energy generation prediction model (120)). The electronic device can obtain predicted data for the amount of energy to be generated by the energy generation complex (200) from the energy generation prediction model.

[0054] In one embodiment, the electronic device can obtain prediction data for the amount of energy generated by any one of the plurality of cluster regions (215, 225, 235, 245, 255). The electronic device can utilize observed weather data obtained from the remaining cluster regions to generate prediction data for any one cluster region. The electronic device can determine prediction data for the amount of energy generated in the entire energy generation complex (200) by combining the prediction data for each cluster region.

[0055] For example, the electronic device may obtain prediction data for the amount of energy generated by the first cluster area (215) from an energy generation prediction model based on observed weather data obtained in at least one of the second to fifth cluster areas (225, 235, 245, 255). The electronic device may obtain prediction data for the amount of energy generated by the second cluster area (225) from an energy generation prediction model based on observed weather data obtained in at least one of the first cluster area (215) and the third to fifth cluster areas (235, 245, 255). The electronic device may obtain prediction data for the amount of energy generated by the third cluster area (235) from an energy generation prediction model based on observed weather data obtained in at least one of the first cluster area (215), the second cluster area (225), the fourth cluster area (245), and the fifth cluster area (255). The electronic device can obtain prediction data for the amount of energy generated by the fourth cluster area (245) from an energy generation prediction model based on observed weather data obtained in at least one of the first to third cluster areas (215, 225, 235) and the fifth cluster area (255). The electronic device can obtain prediction data for the amount of energy generated by the fifth cluster area (255) from an energy generation prediction model based on observed weather data obtained in at least one of the first to fourth cluster areas (215, 225, 235, 245). The electronic device can obtain prediction data for the amount of energy generated by the entire energy generation complex (200) by combining prediction data regarding each of the plurality of cluster areas.

[0056] In one embodiment, the electronic device can predict weather changes in any one of the multiple cluster areas (215, 225, 235, 245, 255) based on the time series pattern of observed weather data obtained from the multiple cluster areas (215, 225, 235, 245, 255). In one embodiment, the electronic device can predict weather changes regarding a decrease in solar radiation or the occurrence of gusts due to rain clouds entering any one of the cluster areas based on the time series pattern of observed weather data obtained from the multiple cluster areas (215, 225, 235, 245, 255). For example, if strong rain clouds are observed in the third cluster area (235) while the wind is easterly, the rain clouds may move westward after a certain period of time, so the electronic device can predict the weather change of the adjacent area, the fifth cluster area (255), based on the observed weather data obtained from the third weather observation device (230) when predicting the energy generation amount for the fifth cluster area (255).

[0057] In one embodiment, the electronic device can predict weather changes in any one of a plurality of cluster regions (215, 225, 235, 245, 255) based on the time series pattern of observed weather data and satellite data. The electronic device can predict weather changes regarding a decrease in solar radiation or the occurrence of gusts due to rain clouds entering any one of the cluster regions based on cloud movement information (or cloud change information) and / or solar radiation change information at regular time intervals included in the satellite data. The electronic device can analyze the movement path of clouds through the time series pattern of observed weather data obtained directly from weather observation devices (210, 220, 230, 240, 250) and satellite data. The analyzed movement path of clouds can be shared with the weather observation devices (210, 220, 230, 240, 250).

[0058] The electronic device can control energy generation facilities included in each of the cluster areas (215, 225, 235, 245, 255) based on acquired prediction data. The electronic device can transmit observed weather data acquired from each of the multiple cluster areas (215, 225, 235, 245, 255) to the energy management system (260). The electronic device can control energy generation facilities included in each of the cluster areas (215, 225, 235, 245, 255) using the energy management system (260) based on the acquired prediction data. Weather observation devices placed in each of the multiple cluster areas (215, 225, 235, 245, 255) may also directly transmit observed weather data to the energy management system (260). The weather observation devices (210, 220, 230, 240, 250) can communicate with each other, so that weather data obtained from one weather observation device can be transmitted to the energy management system (260) through another weather observation device. For example, weather data obtained from the third weather observation device (230) can be transmitted to the energy management system (260) through the fifth weather observation device (250).

[0059] The energy management system (260) can control the operation of the energy generation facility installed in the energy generation complex (200). For example, the energy management system (260) can control the operation regarding whether to store energy generated from a solar power generation facility or a wind power generation facility in an energy storage device (not shown). The electronic device can determine whether to store energy generated from the energy generation facility through the energy management system (260) and control the operation of the energy generation facility.

[0060] The electronic device can control an energy generation facility included in any one of the multiple cluster areas (215, 225, 235, 245, 255) using an energy management system (260) based on predicted weather changes and acquired prediction data. In one embodiment, the electronic device can predict a weather change in a second cluster area (225) based on a time series pattern of observed weather data acquired with respect to a first cluster area (215), and control an energy generation facility included in the second cluster area (225) using an energy management system (260) based on the predicted weather changes and acquired prediction data.

[0061] The electronic device can control the energy generation output of an energy generation facility included in any one of the multiple cluster areas (215, 225, 235, 245, 255) and the generated energy to be stored in an energy storage device by using an energy management system (260) based on predicted weather changes and acquired prediction data. In one embodiment, the electronic device can predict weather changes regarding a decrease in solar radiation or the occurrence of gusts due to rain clouds entering the second cluster area (225) based on the time series pattern of observed weather data acquired regarding the first cluster area (215). The electronic device can control the energy generation output of an energy generation facility included in the second cluster area (225) and the generated energy to be stored in an energy storage device by using an energy management system (260) based on predicted weather changes and acquired prediction data. For example, if strong rain clouds are observed in the third cluster area (235) while the wind is easterly, the rain clouds may move westward after a certain period of time, so the electronic device can refer to the observed weather data obtained from the third weather observation device (230) when predicting the amount of energy generated for the fifth cluster area (255). At this time, the electronic device can control the energy generation device in the fifth cluster area (255) to store energy in the energy storage device in preparation for the rain clouds.

[0062] The electronic device can detect a signal indicating weather recovery in any one of the multiple cluster areas (215, 225, 235, 245, 255) based on a time series pattern of observed weather data obtained from the multiple cluster areas (215, 225, 235, 245, 255). When a signal of weather recovery is detected, the electronic device can control the resumption of normal power generation of an energy generation facility included in the corresponding cluster area using an energy management system (260). In one embodiment, the electronic device can detect a signal indicating weather recovery in the second cluster area (225) based on a time series pattern of observed weather data obtained regarding the first cluster area (215). For example, if a pattern is confirmed in which solar radiation data measured in the first cluster area (215) recovers stably for a certain period of time after rapidly decreasing due to clouds, the electronic device can predict that a similar recovery will occur in the second cluster area (225) within a few hours by considering the movement trend of the same weather phenomenon. The electronic device can detect a signal indicating weather recovery by performing a correlation analysis based on the geographical distance between adjacent clusters, the direction and speed of airflow movement, and past observation history. Upon detecting a signal regarding weather recovery, the electronic device can control the resumption of normal power generation of the energy generation facility included in the second cluster area (225) using the energy management system (260).

[0063] The electronic device enables the prediction of solar power generation by cluster area of ​​the energy generation complex (200), thereby providing immediate assistance in operational decision-making for the energy generation facility based on the predicted solar power generation. The electronic device can contribute to efficient plant operation by dividing the large-scale energy generation complex (200) into multiple cluster areas (215, 225, 235, 245, 255) for operation.

[0065] FIG. 3 is a flowchart illustrating the operations of a method for predicting energy generation amount according to one embodiment. In one embodiment, at least one of the operations of FIG. 3 may be performed simultaneously or in parallel with other operations, and the order between the operations may be changed. Additionally, at least one of the operations may be omitted, and other operations may be performed additionally. The operations of the method for predicting energy generation amount may be performed by an electronic device of the present disclosure (e.g., the electronic device (110) of FIG. 1 or the electronic device (500) of FIG. 5).

[0066] Referring to FIG. 3, in operation (310), the electronic device may obtain predicted weather data including weather variable values ​​regarding the region where the energy generation complex is located from a weather forecasting agency. The energy generation complex may include a plurality of cluster regions each containing an energy generation facility. The energy generation facilities may include at least one of a solar power generation facility and a wind power generation facility. The variable values ​​included in the predicted weather data may include at least one of a predicted solar radiation value, a predicted temperature value, a predicted wind speed value, a predicted wind direction value, and a predicted humidity value for a future time point obtained from a weather forecasting agency.

[0067] In operation (320), the electronic device may obtain satellite data regarding the region where the energy generation complex is located from a satellite data provider. The satellite data may include image data including cloud movement images regarding the region where the energy generation complex is located, and numerical data including solar radiation observation values ​​based on cloud movement information.

[0068] In operation (330), the electronic device may obtain observed weather data including weather variable values ​​for each of the cluster areas by a weather observation device placed in each of the cluster areas. The weather variable values ​​included in the observed weather data may include at least one of the observed solar radiation value at the current time, the observed temperature value at the current time, the observed wind speed value at the current time, the observed wind direction value at the current time, and the observed humidity value at the current time, all of which are obtained for each of the cluster areas.

[0069] In operation (340), the electronic device may provide predicted weather data, satellite data, and observed weather data obtained from each of the cluster areas to a learned energy generation prediction model. The energy generation prediction model may be learned based on weather variable values ​​forecasted at a past time, weather variable values ​​observed at a past time, and actual energy generation obtained at a past time. In one embodiment, if the electronic device cannot obtain predicted weather data and / or satellite data due to a failure in the external communication environment or the absence of a weather forecasting agency, it may provide observed weather data obtained from each of the cluster areas to the energy generation prediction model.

[0070] In operation (350), the electronic device can obtain prediction data for the amount of energy generated by the energy generation complex from an energy generation prediction model. As predicted weather data, satellite data, and / or observed weather data are input, the energy generation prediction model can extract the amount of energy generated at a past point in time that was calculated from data similar to the input data and output it as a predicted value of the amount of energy generated at a future point in time.

[0071] In one embodiment, the electronic device may utilize observed weather data obtained from the remaining cluster areas to generate predicted data for one cluster area. The electronic device may determine predicted data for the amount of energy generated in the entire energy generation complex by synthesizing the predicted data for each cluster area. For example, the electronic device may obtain first predicted data for the amount of energy generated by the first cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the second cluster area. The electronic device may obtain second predicted data for the amount of energy generated by the second cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the first cluster area. The electronic device may obtain predicted data for the amount of energy generated by the energy generation complex based on the first and second predicted data.

[0073] FIG. 4 is a flowchart illustrating the operations of a method for controlling an energy generation facility according to one embodiment. In one embodiment, at least one of the operations of FIG. 4 may be performed simultaneously or in parallel with other operations. Additionally, at least one of the operations may be omitted, and other operations may be performed additionally. The operations of the method for controlling an energy generation facility may be performed by an electronic device of the present disclosure (e.g., the electronic device (110) of FIG. 1 or the electronic device (500) of FIG. 5). The operation (410) of FIG. 4 may be performed after the operation (340) of obtaining prediction data for the amount of energy generated.

[0074] Referring to FIG. 4, in operation (410), the electronic device can transmit observed weather data obtained from each of the cluster areas to the energy management system. It is also possible for a weather observation device placed in each of the cluster areas to directly transmit the observed weather data to the energy management system. The weather observation devices included in each of the cluster areas may be able to communicate with each other.

[0075] In operation (420), the electronic device can control the energy generation facilities included in each of the cluster areas using an energy management system based on the acquired prediction data. The energy management system can control the operation of the energy generation facilities installed in the energy generation complex. For example, the energy management system can control the operation regarding whether to store energy generated from a solar power generation facility or a wind power generation facility in an energy storage device. The electronic device can determine whether to store energy generated from the energy generation facility and control the operation of the energy generation facility through the energy management system.

[0076] In one embodiment, the electronic device can control energy generated from an energy generation facility included in each of the cluster regions to be stored in an energy storage device or energy to be discharged from an energy storage device based on acquired prediction data.

[0077] In one embodiment, the electronic device can predict weather changes in a second cluster area based on the time series pattern of observed weather data acquired regarding a first cluster area. The electronic device can control energy generation facilities included in the second cluster area using an energy management system based on the predicted weather changes and the acquired prediction data. In one embodiment, the electronic device can predict weather changes regarding a decrease in solar radiation or the occurrence of gusts due to rain clouds entering the second cluster area based on the time series pattern of observed weather data acquired regarding the first cluster area. Based on the predicted weather changes and the acquired prediction data, the electronic device can control the energy generation facilities included in the second cluster area to limit their power output and store the generated energy in an energy storage device using an energy management system. In one embodiment, the electronic device can detect a signal indicating weather recovery in the second cluster area based on the time series pattern of observed weather data acquired regarding the first cluster area. When the signal is detected, the electronic device can control the energy generation facilities included in the second cluster area to resume normal power generation using an energy management system.

[0079] FIG. 5 is a drawing for explaining the configurations of an electronic device according to one embodiment.

[0080] Referring to FIG. 5, an electronic device (500) (e.g., the electronic device (110) of FIG. 1) may include a processor (510), memory (520), an input / output interface (530), a communication module (540), and storage (550). The electronic device (500) is a device that performs the operations of the method described in the present disclosure. In one embodiment, some of these components may be omitted from the electronic device (500), or other components may be added.

[0081] The memory (520) can store instructions executable by one or more processors (510). The memory (520) may include volatile memory such as DRAM (Dynamic RAM) and SRAM (Static RAM) or non-volatile memory such as magnetic hard disc, optical disc, floppy disc, flash memory, EPROM (electrically programmable memories), and EEPROM (electrically erasable and programmable).

[0082] The input / output interface (530) may be a means for interfacing with an input / output device. The input / output interface (530) may include, for example, an input device such as a microphone, a digital pen, a keyboard, or a mouse, and / or an output device such as a display or a speaker. The input / output interface (530) may also be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen.

[0083] The communication module (540) can establish a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (500) and another device, and perform communication functions through the established communication channel. The communication module (540) may include a communication circuit for performing communication functions. The communication module (540) may include a communication processor that operates independently of the processor (510) and supports direct (e.g., wired) communication or wireless communication. The communication module (540) may be an element that implements a wireless communication interface (e.g., Bluetooth communication interface, cellular communication interface, Wi-Fi communication interface, or GNSS communication interface) or a wired communication interface (e.g., LAN communication interface) that performs wireless communication.

[0084] Requests, commands, data, files, etc. generated by the processor (510) of the electronic device (500) according to program code stored in a recording device such as memory (520) can be transmitted to another device via a network under the control of a communication interface. Conversely, signals, instructions, data, files, etc. from another device can be received by the electronic device (500) through the communication interface of the electronic device (500) via a network. Signals, instructions, data, etc. received through the communication interface can be transmitted to the processor (510) or memory (520), and instructions, files, etc. can be stored in a storage medium that the electronic device (500) may further include.

[0085] The processor (510) can execute instructions stored in memory (520). The processor (510) may include a central processing unit (CPU), a graphics processing unit (GPU), a neural network processing unit (NPU), a media processing unit (MPU), a data processing unit (DPU), a vision processing unit (VPU), a video processor, an image processor, a display processor, a microprocessor, a processor core, a multi-core processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or any combination thereof. When instructions are executed by the processor (510), the processor (510) can control the electronic device (500) to perform operations of the method described in this disclosure.

[0086] The electronic device (500) can obtain predicted weather data including weather variable values ​​regarding the region where the energy generation complex is located from a weather forecasting agency (e.g., the weather forecasting agency (130) of FIG. 1). The energy generation complex may include a plurality of cluster regions, each containing an energy generation facility. The electronic device (500) can obtain satellite data regarding the region where the energy generation complex is located from a satellite data provider (e.g., the satellite data provider (140) of FIG. 1). The electronic device (500) can obtain observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device (e.g., the weather observation device (150) of FIG. 1) placed in each of the cluster regions. The electronic device (500) can provide the predicted weather data, satellite data, and the observed weather data obtained from each of the cluster regions to a learned energy generation amount prediction model (e.g., the energy generation amount prediction model (120) of FIG. 1). The electronic device (500) can obtain predicted data on the amount of energy generated by the energy generation complex from an energy generation amount prediction model.

[0087] In one embodiment, the electronic device (500) can obtain first prediction data for the amount of energy generated by the first cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the second cluster area. The electronic device (500) can obtain second prediction data for the amount of energy generated by the second cluster area from an energy generation prediction model based on predicted weather data, satellite data, and observed weather data obtained regarding the first cluster area. The electronic device (500) can obtain prediction data for the amount of energy generated by the energy generation complex based on the first prediction data and the second prediction data.

[0088] The electronic device (500) can transmit observed weather data obtained from each of the cluster areas to an energy management system (e.g., the energy management system (260) of FIG. 2). The electronic device (500) can control energy generation facilities included in each of the cluster areas using the energy management system based on the obtained prediction data.

[0089] In one embodiment, the electronic device (500) can control to store energy generated from an energy generation facility included in each of the cluster regions in an energy storage device or to discharge energy from an energy storage device based on acquired prediction data.

[0090] In one embodiment, the electronic device (500) can predict weather changes in a second cluster area based on the time series pattern of observed weather data acquired with respect to a first cluster area. The electronic device (500) can control energy generation facilities included in the second cluster area using an energy management system based on the predicted weather changes and acquired prediction data.

[0091] In one embodiment, the electronic device (500) can predict weather changes regarding a reduction in solar radiation or the occurrence of gusts due to rain clouds entering the second cluster area based on the time series pattern of observed weather data acquired with respect to the first cluster area. Based on the predicted weather changes and acquired prediction data, the electronic device (500) can control the energy generation output of the energy generation facility included in the second cluster area using an energy management system to limit the output and store the generated energy in an energy storage device.

[0092] In one embodiment, the electronic device (500) can detect a signal indicating weather recovery in the second cluster area based on a time series pattern of observed weather data acquired with respect to the first cluster area. When the signal is detected, the electronic device (500) can control the resumption of normal power generation of an energy generation facility included in the second cluster area using an energy management system.

[0093] Storage (550) can store various data used by components of the electronic device (500) (e.g., processor (510), memory (520), input / output interface (530), and communication module (540)). The data may include, for example, input or output data for a program (e.g., application), related commands, and log data of a computing system. For example, storage (550) can store prediction data regarding the amount of energy generated by an energy generation complex. Storage (550) can store an energy generation prediction model that outputs the prediction data. Additionally, storage (550) can store training data including past prediction weather data, satellite data, observational weather data, and generation data that are used to train the energy generation prediction model.

[0095] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0096] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be stored on any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.

[0097] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program instructions, data files, data structures, etc., either individually or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0098] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0099] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for predicting the energy generation amount of an energy generation complex and controlling energy generation facilities within the energy generation complex comprises: an operation of obtaining predicted weather data including weather variable values ​​regarding a region where the energy generation complex is located from a weather forecasting agency - wherein the energy generation complex includes a plurality of cluster regions each containing an energy generation facility -; an operation of obtaining satellite data regarding a region where the energy generation complex is located from a satellite data provider; an operation of obtaining observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device placed in each of the cluster regions; and an operation of providing the predicted weather data, the satellite data, and the observed weather data obtained from each of the cluster regions to a learned energy generation amount prediction model. A method comprising the operation of obtaining prediction data for the amount of energy generated by the energy generation complex from the energy generation amount prediction model, wherein the plurality of cluster areas include at least a first cluster area and a second cluster area, and the operation of obtaining the prediction data includes: the operation of obtaining first prediction data for the amount of energy generated by the first cluster area from the energy generation amount prediction model based on the predicted weather data, the satellite data and the observed weather data obtained regarding the second cluster area; the operation of obtaining second prediction data for the amount of energy generated by the second cluster area from the energy generation amount prediction model based on the predicted weather data, the satellite data and the observed weather data obtained regarding the first cluster area; and the operation of obtaining the prediction data for the amount of energy generated by the energy generation complex based on the first prediction data and the second prediction data. Claim 2 delete Claim 3 A method according to claim 1, further comprising: the operation of transmitting observed weather data obtained in each of the cluster regions to an energy management system (EMS); and the operation of controlling the energy generation facilities included in each of the cluster regions using the energy management system based on the obtained prediction data. Claim 4 In paragraph 3, the operation of controlling the energy generation facility comprises controlling to store energy generated from the energy generation facility included in each of the cluster regions in an energy storage system (ESS) or to discharge energy from the energy storage system based on the acquired prediction data. Claim 5 In paragraph 3, the operation of controlling the energy generation facility comprises: an operation of predicting a weather change in the second cluster area based on a time series pattern of observed weather data obtained with respect to the first cluster area; and an operation of controlling the energy generation facility included in the second cluster area using the energy management system based on the predicted weather change and the obtained prediction data. Claim 6 In claim 5, the operation of controlling the energy generation facility comprises: an operation of predicting a weather change regarding a reduction in solar radiation or the occurrence of a gust due to rain clouds entering the second cluster area based on a time series pattern of observed weather data obtained with respect to the first cluster area; and an operation of controlling the energy generation facility included in the second cluster area to limit the power generation output and store the generated energy in an energy storage device using the energy management system based on the predicted weather change and the obtained prediction data. Claim 7 In claim 6, the operation of controlling the energy generation facility comprises: detecting a signal indicating weather recovery in the second cluster area based on a time series pattern of observed weather data acquired with respect to the first cluster area; and, when the signal is detected, controlling the normal power generation of the energy generation facility included in the second cluster area using the energy management system. Claim 8 A method according to claim 1, wherein the energy generation facility comprises at least one of a solar power generation facility and a wind power generation facility. Claim 9 A method according to claim 1, wherein the weather variable values ​​included in the predicted weather data include at least one of a future time point solar radiation prediction value, future time point temperature prediction value, future time point wind speed prediction value, future time point wind direction prediction value, and future time point humidity prediction value obtained from the weather forecasting agency, and the weather variable values ​​included in the observed weather data include at least one of a current time point solar radiation observation value, current time point temperature observation value, current time point wind speed observation value, current time point wind direction observation value, and current time point humidity observation value obtained for each of the cluster regions. Claim 10 A method according to claim 1, wherein the weather observation devices included in each of the cluster regions are capable of communicating with each other. Claim 11 An electronic device for predicting the energy generation amount of an energy generation complex and controlling energy generation facilities within the energy generation complex, comprising: a communication circuit that communicates with a plurality of weather observation devices; a memory that stores instructions;The electronic device includes a processor for executing the above instructions, and when the instructions are executed by the processor, the electronic device obtains predicted weather data including weather variable values ​​regarding the region where the energy power complex is located from a weather forecasting agency - the energy power complex includes a plurality of cluster regions each including an energy power generation facility -, obtains satellite data regarding the region where the energy power complex is located from a satellite data provider, obtains observed weather data including weather variable values ​​regarding each of the cluster regions by a weather observation device placed in each of the cluster regions, provides the predicted weather data, the satellite data, and the observed weather data obtained from each of the cluster regions to a learned energy generation amount prediction model, and obtains predicted data for the amount of energy generated by the energy power complex from the energy generation amount prediction model, wherein the plurality of cluster regions include at least a first cluster region and a second cluster region, and when the instructions are executed by the processor, the electronic device obtains from the energy generation amount prediction model the first cluster region based on the predicted weather data, the satellite data, and the observed weather data obtained regarding the second cluster region An electronic device that obtains first prediction data for the amount of energy generated by, obtains second prediction data for the amount of energy generated by the second cluster area from the energy generation prediction model based on the predicted weather data, the satellite data and the observed weather data obtained regarding the first cluster area, and obtains the prediction data for the amount of energy generated by the energy generation complex based on the first prediction data and the second prediction data. Claim 12 delete Claim 13 In claim 11, when the instructions are executed by the processor, the electronic device transmits observed weather data obtained in each of the cluster regions to an energy management system and controls the energy generation facilities included in each of the cluster regions using the energy management system based on the obtained predicted data. Claim 14 In paragraph 13, when the instructions are executed by the processor, the electronic device controls the energy generated from the energy generation facility included in each of the cluster regions to be stored in an energy storage device or to be discharged from the energy storage device based on the acquired prediction data. Claim 15 In paragraph 13, when the instructions are executed by the processor, the electronic device predicts a weather change in the second cluster area based on a time series pattern of observed weather data obtained with respect to the first cluster area, and controls the energy generation facility included in the second cluster area using the energy management system based on the predicted weather change and the obtained prediction data. Claim 16 In paragraph 15, when the instructions are executed by the processor, the electronic device predicts a weather change regarding a reduction in solar radiation or the occurrence of a gust due to rain clouds entering the second cluster area based on a time series pattern of observed weather data obtained with respect to the first cluster area, and controls the energy management system to limit the power generation output of the energy generation facility included in the second cluster area and to store the generated energy in an energy storage device based on the predicted weather change and the obtained prediction data. Claim 17 In claim 16, when the instructions are executed by the processor, the electronic device detects a signal indicating weather recovery in the second cluster area based on a time series pattern of observed weather data acquired with respect to the first cluster area, and when the signal is detected, controls the normal power generation of the energy generation facility included in the second cluster area using the energy management system. Claim 18 In paragraph 11, the energy generation facility comprises at least one of a solar power generation facility and a wind power generation facility, an electronic device. Claim 19 An electronic device according to claim 11, wherein the weather variable values ​​included in the predicted weather data include at least one of a predicted solar radiation value at a future time point, a predicted temperature value at a future time point, a predicted wind speed value at a future time point, a predicted wind direction value at a future time point, and a predicted humidity value at a future time point obtained from the weather forecasting agency, and the weather variable values ​​included in the observed weather data include at least one of a observed solar radiation value at a current time point, a observed temperature value at a current time point, a observed wind speed value at a current time point, a observed wind direction value at a current time point, and a observed humidity value at a current time point obtained for each of the cluster regions. Claim 20 In paragraph 11, the weather observation device included in each of the cluster regions is an electronic device capable of communicating with one another.

Citation Information

Patent Citations

  • Forecasting solar power generation using weather forecasts

    US20180101147A1

  • System for predicting energy production

    KR1020140087965A

  • Electric power control system of solar module and the method using it

    KR1020240038179A

  • Method for predicting real-time renewable energy output with high accuracy

    KR1020240151683A