Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme
Recently, energy procurement by renewable energy sources has increased. In particular, as solar power generation has a high penetration rate among them, solar radiation predictions at the site are attracting much attention for efficient operation. Various approaches have been proposed to forecast so...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/6/1622 |
| _version_ | 1797609228663259136 |
|---|---|
| author | Jinwoong Park Sungwoo Park Jonghwa Shim Eenjun Hwang |
| author_facet | Jinwoong Park Sungwoo Park Jonghwa Shim Eenjun Hwang |
| author_sort | Jinwoong Park |
| collection | DOAJ |
| description | Recently, energy procurement by renewable energy sources has increased. In particular, as solar power generation has a high penetration rate among them, solar radiation predictions at the site are attracting much attention for efficient operation. Various approaches have been proposed to forecast solar radiation accurately. Recently, hybrid models have been proposed to improve performance through forecasting in the frequency domain using past solar radiation. Since solar radiation data have a pattern, forecasting in the frequency domain can be effective. However, forecasting performance deteriorates on days when the weather suddenly changes. In this paper, we propose a domain hybrid forecasting model that can respond to weather changes and exhibit improved performance. The proposed model consists of two stages. In the first stage, forecasting is performed in the frequency domain using wavelet transform, complete ensemble empirical mode decomposition, and multilayer perceptron, while forecasting in the sequence domain is accomplished using light gradient boosting machine. In the second stage, a multilayer perceptron-based domain hybrid model is constructed using the forecast values of the first stage as the input. Compared with the frequency-domain model, our proposed model exhibits an improvement of up to 36.38% in the normalized root-mean-square error. |
| first_indexed | 2024-03-11T05:57:34Z |
| format | Article |
| id | doaj.art-bfdde418122e49dbab51fdaea0983f6f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:57:34Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-bfdde418122e49dbab51fdaea0983f6f2023-11-17T13:39:40ZengMDPI AGRemote Sensing2072-42922023-03-01156162210.3390/rs15061622Domain Hybrid Day-Ahead Solar Radiation Forecasting SchemeJinwoong Park0Sungwoo Park1Jonghwa Shim2Eenjun Hwang3School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of KoreaRecently, energy procurement by renewable energy sources has increased. In particular, as solar power generation has a high penetration rate among them, solar radiation predictions at the site are attracting much attention for efficient operation. Various approaches have been proposed to forecast solar radiation accurately. Recently, hybrid models have been proposed to improve performance through forecasting in the frequency domain using past solar radiation. Since solar radiation data have a pattern, forecasting in the frequency domain can be effective. However, forecasting performance deteriorates on days when the weather suddenly changes. In this paper, we propose a domain hybrid forecasting model that can respond to weather changes and exhibit improved performance. The proposed model consists of two stages. In the first stage, forecasting is performed in the frequency domain using wavelet transform, complete ensemble empirical mode decomposition, and multilayer perceptron, while forecasting in the sequence domain is accomplished using light gradient boosting machine. In the second stage, a multilayer perceptron-based domain hybrid model is constructed using the forecast values of the first stage as the input. Compared with the frequency-domain model, our proposed model exhibits an improvement of up to 36.38% in the normalized root-mean-square error.https://www.mdpi.com/2072-4292/15/6/1622smart gridrenewable energy sourcessolar radiation forecastingwavelet transformcomplete ensemble empirical mode decomposition with adaptive noise |
| spellingShingle | Jinwoong Park Sungwoo Park Jonghwa Shim Eenjun Hwang Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme Remote Sensing smart grid renewable energy sources solar radiation forecasting wavelet transform complete ensemble empirical mode decomposition with adaptive noise |
| title | Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme |
| title_full | Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme |
| title_fullStr | Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme |
| title_full_unstemmed | Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme |
| title_short | Domain Hybrid Day-Ahead Solar Radiation Forecasting Scheme |
| title_sort | domain hybrid day ahead solar radiation forecasting scheme |
| topic | smart grid renewable energy sources solar radiation forecasting wavelet transform complete ensemble empirical mode decomposition with adaptive noise |
| url | https://www.mdpi.com/2072-4292/15/6/1622 |
| work_keys_str_mv | AT jinwoongpark domainhybriddayaheadsolarradiationforecastingscheme AT sungwoopark domainhybriddayaheadsolarradiationforecastingscheme AT jonghwashim domainhybriddayaheadsolarradiationforecastingscheme AT eenjunhwang domainhybriddayaheadsolarradiationforecastingscheme |