Photovoltaic power generation output prediction device, power grid control system, supply and demand control system, solar radiation intensity prediction device, learning device, photovoltaic power generation output prediction method, and photovoltaic power generation output prediction program

The solar power generation output prediction device employs machine learning to enhance the temporal resolution of solar power output predictions beyond the limitations of existing solar radiation intensity forecasts, thereby supporting more precise power system control.

JP7664708B2Active Publication Date: 2025-04-18MITSUBISHI ELECTRIC CORP
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
JP2021019557
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-02-10
Publication Date
2025-04-18
Estimated Expiration
2041-02-10

AI Technical Summary

Technical Problem

Existing technologies for predicting solar power generation output are limited by the temporal resolution of predicted solar radiation intensity, which is not sufficient for high-resolution power system control applications.

Method used

A solar power generation output prediction device that uses machine learning to generate a trained model for predicting solar power generation output statistics with a higher time resolution than the input solar radiation intensity data, by incorporating actual solar radiation intensity statistics and external predicted values.

Benefits of technology

Enables prediction of solar power generation output with a higher time resolution than the input solar radiation intensity data, effectively supporting advanced power system control and management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007664708000001
    Figure 0007664708000001
  • Figure 0007664708000002
    Figure 0007664708000002
  • Figure 0007664708000003
    Figure 0007664708000003
Patent Text Reader

Abstract

To obtain a photovoltaic power generation output prediction device capable of performing prediction of photovoltaic power generation output with temporal resolution higher than temporal resolution of a prediction value of solar radiation intensity that is acquired.SOLUTION: A photovoltaic power generation output prediction device 10 comprises: a data acquisition unit 11 that acquires a solar radiation intensity prediction value being a prediction value of solar radiation intensity, and an actual value of a value indicating photovoltaic power generation output; a model generation unit 13 that calculates a statistic of the actual value within a time zone shorter than a time interval of the solar radiation intensity prediction value, and generates a learned model for predicting a statistic of solar radiation intensity, by taking the solar radiation intensity prediction value and a corresponding month as input data and using learning data including the input data and a statistic of the corresponding month, from the solar radiation intensity prediction value and the month; and a prediction unit 15 that, for each time zone, predicts a statistic of solar radiation intensity as output of the learned model by inputting, to the learned model, a solar radiation intensity prediction value and a corresponding month of a prediction target day acquired by the data acquisition unit 11.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Device, method, and program for prediction of electricity generation amount

    JP2011200040A

  • Solar radiation amount prediction device and program

    JP2013036820A

  • Information processor, power generation amount calculating method, and program

    JP2013073537A

  • Information processing device, and control method and program for the same

    JP2013253805A

  • Power generation amount prediction device, power generation amount prediction method and program

    JP2016136807A