A Dual-Stage Solar Power Prediction Model That Reflects Uncertainties in Weather Forecasts

Jeongin Lee (), Jongwoo Choi, Wanki Park and Ilwoo Lee ()
Additional contact information
Jeongin Lee: Energy ICT Research Section, Industrial Energy Convergence Research Division, Digital Convergence Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea
Jongwoo Choi: Energy ICT Research Section, Industrial Energy Convergence Research Division, Digital Convergence Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea
Wanki Park: Energy ICT Research Section, Industrial Energy Convergence Research Division, Digital Convergence Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea
Ilwoo Lee: Energy ICT Research Section, Industrial Energy Convergence Research Division, Digital Convergence Laboratory, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea

Energies, 2023, vol. 16, issue 21, 1-19

Abstract: Renewable energy sources are being expanded globally in response to global warming. Solar power generation is closely related to solar radiation and typically experiences significant fluctuations in solar radiation hours during periods of high solar radiation, leading to substantial inaccuracies in power generation predictions. In this paper, we suggest a solar power generation prediction method aimed at minimizing prediction errors during solar time. The proposed method comprises two stages. The first stage is the construction of the Solar Base Model by extracting characteristics from input variables. In the second stage, the prediction error period is detected using the Solar Change Point, which measures the difference between the predicted output from the Solar Base Model and the actual power generation. Subsequently, the probability of a weather forecast state change within the error occurrence period is calculated, and this information is used to update the power generation forecast value. The performance evaluation was restricted to July and August. The average improvement rate in predicted power generation was 24.5%. Using the proposed model, updates to weather forecast status information were implemented, leading to enhanced accuracy in predicting solar power generation.

Keywords: solar power prediction; weather forecasts; Solar Change Point; Bayesian; deep learning (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/21/7321/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/21/7321/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:21:p:7321-:d:1269651

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().