1 0 0 0 OA AutoMLを用いた太陽光発電量予測の精度検証の検討
- 著者
- 古澤 陽 西嶋 瑛世 海野 真穂 堀田 裕弘
- 出版者
- 一般社団法人 エネルギー・資源学会
- 雑誌
- エネルギー・資源学会論文誌 (ISSN:24330531)
- 巻号頁・発行日
- vol.44, no.3, pp.152-159, 2023-05-10 (Released:2023-05-10)
- 参考文献数
- 23
In Japan, the active introduction of renewable energies is encouraged in order to achieve a decarbonized society. Among renewable energies, photovoltaic power generation, which can be introduced relatively easily in buildings and houses, is being used, and its further introduction is desired. Therefore, there is a need for technology to accurately predict the amount of electricity generated at potential sites for photovoltaic power generation facilities. In this study, we tried various machine learning methods for predicting the amount of electricity generated by photovoltaic power generation without using the information of the solar radiation meters, and examined the effect of the training period of machine learning on the accuracy of the estimation.
1 0 0 0 OA 機械学習を用いた文教施設の電力需要予測における最適モデルの構築
- 著者
- 西嶋 瑛世 古澤 陽 海野 真穂 堀田 裕弘
- 出版者
- 一般社団法人 エネルギー・資源学会
- 雑誌
- エネルギー・資源学会論文誌 (ISSN:24330531)
- 巻号頁・発行日
- vol.44, no.3, pp.145-151, 2023-05-10 (Released:2023-05-10)
- 参考文献数
- 21
Since the Paris Agreement in 2015, there has been growing interest in global warming around the world, and accelerated measures to global warming are required to realize a decarbonized society by declaring the goal of carbon neutrality. As one of the measures, Demand Response (DR) are being actively introduced and provided. DR is a system whereby electric power companies pay incentives through transactions to consumers who cooperate in saving electricity during peak periods of electricity demand, thereby reducing peak electricity demand. Electricity demand for individual buildings is easily affected by seasonal fluctuations, the presence or absence of events, and other factors, and the occurrence of electricity demand peaks tends to be irregular, so highly accurate electricity demand forecasting is needed. In this study, we focus on the educational facilities such as University campus. The objective of this study is to use machine learning to construct a highly accurate forecasting model for not only the steady electricity demand in daily life, but also the characteristic electricity demand during events.