Apparatus for predicting photovoltaic power genertation using satellite image and method the same

Abstract

An apparatus and method for predicting solar power generation using satellite imagery according to an embodiment are disclosed. The solar power generation prediction apparatus comprises: a data construction unit that constructs big data for training based on satellite imagery; a model training unit that pre-trains a predetermined artificial intelligence model based on the constructed big data for training; and a power generation prediction unit that corrects the weather forecast solar radiation for a target area through the artificial intelligence model and predicts solar power generation based on the corrected solar radiation.

Description

Technology Field

[0001] The embodiment relates to an apparatus and a method for predicting solar power generation using satellite imagery. Background Technology

[0002] Recently, as global environmental issues such as climate change and abnormal temperatures have emerged as serious concerns, diverse technological developments and commercializations regarding the use of alternative energy are taking place. Among alternative energies, solar energy is gaining prominence as a pollution-free and eco-friendly energy source, and its installed capacity is rapidly increasing, particularly in developed countries.

[0003] Solar power generation is influenced by meteorological conditions such as solar radiation and temperature, the location of the solar panel installation site, and the orientation angle of the panels. Therefore, when installing solar panels, technology is required to acquire information affecting solar power generation and to predict solar power generation based on that acquired information. The problem to be solved

[0004] An embodiment of the present invention provides an apparatus and a method for predicting solar power generation using satellite imagery.

[0005] The problems intended to be solved in the embodiments are not limited thereto, and may also include objectives or effects that can be identified from the means of solving the problems or the forms of implementation described below. means of solving the problem

[0006] A solar power generation prediction device according to an embodiment may include: a data construction unit that constructs big data for training based on satellite images; a model training unit that pre-trains a predetermined artificial intelligence model based on the constructed big data for training; and a power generation prediction unit that corrects the weather forecast solar radiation for a target area through the pre-trained artificial intelligence model and predicts the solar power generation based on the corrected weather forecast solar radiation.

[0007] The above artificial intelligence model can correct the above weather forecast solar radiation to satellite solar radiation.

[0008] The above satellite solar radiation can be calculated based on the satellite image acquired in real time.

[0009] The solar power generation prediction device may further include a solar radiation correction unit that acquires satellite images in real time and inputs the acquired satellite images into the artificial intelligence model to correct the weather forecast solar radiation.

[0010] The above-described solar radiation correction unit can calculate satellite solar radiation from the acquired satellite image in a predetermined number of grid units and input the satellite solar radiation calculated in the predetermined number of grid units into the artificial intelligence model to correct the weather forecast solar radiation.

[0011] A solar power generation prediction method according to an embodiment may include: a data construction step of constructing big data for training based on satellite images; a model training step of pre-training a predetermined artificial intelligence model based on the constructed big data for training; and a power generation prediction step of correcting the weather forecast solar radiation for a target area through the pre-trained artificial intelligence model and predicting the solar power generation based on the corrected weather forecast solar radiation.

[0012] The above solar power generation prediction method may further include a solar radiation correction step of acquiring satellite images in real time and inputting the acquired satellite images into the artificial intelligence model to correct the weather forecast solar radiation.

[0013] The above solar radiation correction step can calculate satellite solar radiation from the acquired satellite image in a predetermined number of grid units and input the satellite solar radiation calculated in the predetermined number of grid units into the artificial intelligence model to correct the weather forecast solar radiation. Effects of the invention

[0014] According to an embodiment, by training an artificial intelligence model based on weather forecast information to predict the weather forecast solar radiation and then correcting the weather forecast solar radiation using satellite solar radiation obtained from satellite images to predict the solar power generation, it is possible to predict the solar power generation more accurately compared to the existing method using weather forecast solar radiation measured at a solar radiation measurement station.

[0015] The various and beneficial advantages and effects of the present invention are not limited to those described above and may be more easily understood in the process of explaining specific embodiments of the present invention. Brief explanation of the drawing

[0016] FIG. 1 is a drawing showing a device for predicting solar power generation according to an embodiment of the present invention. FIG. 2 is a drawing showing a satellite image according to an embodiment of the present invention. FIG. 3 is a drawing showing a solar radiation measuring station according to an embodiment of the present invention. FIG. 4 is a diagram showing a method for predicting solar power generation according to an embodiment of the present invention. Figures 5 and 6 are drawings showing the predicted results of solar power generation for comparative examples and embodiments. Specific details for implementing the invention

[0017] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0018] However, the technical concept of the present invention is not limited to some of the described embodiments but can be implemented in various different forms, and within the scope of the technical concept of the present invention, one or more of the components among the embodiments may be selectively combined or substituted.

[0019] In addition, terms used in the embodiments of the present invention (including technical and scientific terms) may be interpreted in a sense that is generally understood by those skilled in the art to which the present invention belongs, unless explicitly and specifically defined otherwise. Terms that are commonly used, such as terms defined in advance, may be interpreted in consideration of their meaning in the context of the relevant technology.

[0020] Furthermore, the terms used in the embodiments of the present invention are for the purpose of describing the embodiments and are not intended to limit the present invention.

[0021] In this specification, the singular form may include the plural form unless specifically stated otherwise in the text, and when described as “at least one of A and B, C (or more than one of them),” it may include one or more of all combinations that can be formed from A, B, and C.

[0022] In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention.

[0023] These terms are intended merely to distinguish a component from other components and are not limited by the nature, order, sequence, etc., of the said component.

[0024] And, where it is stated that a component is 'connected', 'combined', or 'joined' to another component, this may include not only cases where the component is directly connected, combined, or joined to the other component, but also cases where it is 'connected', 'combined', or 'joined' due to another component located between the component and the other component.

[0025] Furthermore, when described as being formed or placed on the “top or bottom” of each component, “top or bottom” includes not only cases where two components are in direct contact with each other, but also cases where one or more other components are formed or placed between the two components. Additionally, when expressed as “top or bottom,” it may include the meaning of a downward direction as well as an upward direction relative to a single component.

[0026] In the embodiment, a new method is proposed in which an artificial intelligence model is trained on weather forecast solar radiation based on weather forecast information, and the weather forecast solar radiation is corrected using satellite solar radiation obtained from satellite imagery to predict solar power generation.

[0027] FIG. 1 is a drawing showing an apparatus for predicting solar power generation according to an embodiment of the present invention, FIG. 2 is a drawing showing a satellite image according to an embodiment of the present invention, and FIG. 3 is a drawing showing a solar radiation measuring station according to an embodiment of the present invention.

[0028] Referring to FIG. 1, a device for predicting solar power generation according to an embodiment of the present invention may include an information collection unit (100), a data construction unit (200), a model learning unit (300), a solar radiation correction unit (400), and a power generation prediction unit (500).

[0029] The information collection unit (100) can collect weather forecast information, such as solar radiation, temperature, and atmospheric pressure.

[0030] The information collection unit (100) can collect satellite images in real time. At this time, the satellite images may include solar radiation by dividing the target area into grids of a predetermined size as shown in FIG. 2.

[0031] The data construction unit (200) can build big data for learning based on collected weather forecast information.

[0032] The model learning unit (300) can pre-train a predetermined artificial intelligence model based on the constructed big data for learning. The artificial intelligence model can learn the amount of solar radiation for weather forecasting based on temperature, atmospheric pressure, etc.

[0033] The solar radiation correction unit (400) can correct the weather forecast solar radiation by inputting real-time collected satellite images into an artificial intelligence model that has been pre-trained for a predetermined target area.

[0034] At this time, the satellite image may include solar radiation information in multiple grid units of a predetermined size. The reason for correcting the solar radiation in the weather forecast in this way is to supplement it with satellite imagery because solar radiation measurement is only possible in some areas as shown in Fig. 3.

[0035] For example, weather forecast solar radiation can be corrected by replacing it with satellite solar radiation. Since satellite imagery solar radiation obtained through phase imaging reflects variables such as the sun's altitude based on region and date, it is possible to predict satellite solar radiation based on these variables and replace the weather forecast solar radiation for areas where forecast solar radiation is not measured.

[0036] The power generation prediction unit (500) can predict solar power generation based on corrected weather forecast solar radiation. Therefore, in the embodiment, a more accurate prediction of solar power generation may be possible.

[0037] FIG. 4 is a diagram showing a method for predicting solar power generation according to an embodiment of the present invention.

[0038] Referring to FIG. 4, a device for predicting solar power generation amount according to an embodiment of the present invention (hereinafter referred to as a power generation prediction device) can collect weather forecast information, namely solar radiation, temperature, atmospheric pressure, etc. (S100).

[0039] Next, the power generation prediction device can build big data for learning based on collected weather forecast information (S200).

[0040] Next, the power generation prediction device can train a predetermined artificial intelligence model based on the constructed big data for training to predict solar radiation according to temperature, atmospheric pressure, etc. (S300).

[0041] Next, the power generation prediction device acquires satellite images in real time (S400) and can calculate satellite solar radiation based on the acquired satellite images (S500).

[0042] Next, the power generation prediction device can correct the weather forecast solar radiation by inputting the solar radiation from satellites into an artificial intelligence model that has been pre-trained for a predetermined target area (S600).

[0043] Next, the power generation prediction device can predict solar power generation based on corrected weather forecast solar radiation (S700).

[0044] Figures 5 and 6 are drawings showing the predicted results of solar power generation for comparative examples and embodiments.

[0045] Referring to FIGS. 5 and 6, the prediction results of the comparative example of FIG. 5, which predicts solar power generation using satellite imagery, and the prediction results of the embodiment of FIG. 6, which predicts solar radiation after correcting the weather forecast solar radiation using satellite imagery, are shown.

[0046] As such, the example can predict solar power generation more accurately than the comparative example.

[0047] The term "part" as used in this embodiment refers to a software or hardware component, such as a field-programmable gate array (FPGA) or an ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0048] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols

[0049] 100: Information Gathering Department 200: Data Construction Department 300: Model learning section 400: Power generation prediction unit

Claims

Claim 1 A solar power generation prediction device comprising: a data construction unit that constructs big data for training based on weather forecast information; a model training unit that pre-trains a predetermined artificial intelligence model for weather forecast solar radiation based on the constructed big data for training; a solar radiation correction unit that acquires satellite images in real time, calculates satellite solar radiation in a predetermined number of grid units from the acquired satellite images, and inputs the satellite solar radiation calculated in the predetermined number of grid units into the artificial intelligence model to correct the weather forecast solar radiation; and a power generation prediction unit that predicts solar power generation based on the corrected weather forecast solar radiation, wherein the solar radiation correction unit calculates satellite solar radiation for a region where the weather forecast solar radiation is not measured and replaces the calculated satellite solar radiation with the weather forecast solar radiation for that region. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 A method for predicting solar power generation, comprising: a data construction step for constructing big data for training based on weather forecast information; a model training step for pre-training a predetermined artificial intelligence model for weather forecast solar radiation based on the constructed big data for training; a solar radiation correction step for acquiring satellite images in real time, calculating satellite solar radiation in a predetermined number of grid units from the acquired satellite images, and inputting the satellite solar radiation calculated in the predetermined number of grid units into the artificial intelligence model to correct the weather forecast solar radiation; and a power generation prediction step for predicting solar power generation based on the corrected weather forecast solar radiation, wherein the solar radiation correction step predicts satellite solar radiation for a region where the weather forecast solar radiation is not measured and replaces the predicted satellite solar radiation with the weather forecast solar radiation for that region. Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 delete

Images