Cloud Detection for PV Power Forecast based on Colour Components of Sky Images

Elham Shirazi; Joris Lemmens; Mohammed Gofran Chowdhury; Arttu Tuomiranta; Francky Catthoor; Eszter Voroshazi; Ivan Gordon

doi:10.1109/PVSC43889.2021.9518667

Cloud Detection for PV Power Forecast based on Colour Components of Sky Images

Elham Shirazi^*
, Joris Lemmens
, Mohammed Gofran Chowdhury
, Arttu Tuomiranta
, Francky Catthoor
, Eszter Voroshazi
, Ivan Gordon

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

9 Citations (Scopus)

Abstract

Integrating and operating PV in a system-efficient way is the key to increasing penetration levels to evolve toward a more sustainable and clean energy system. Reliable generation forecasting is the solution to tackle fluctuations in PV power generation and its negative effects on power systems and energy markets. Clouds play a key role in solar power, so cloud detection is important in PV power generation forecast. A color-based cloud detection algorithm is proposed in this paper. It considers 12 different color channels together with the K-means algorithm to detect clouds in sky images from an All-Sky Camera. The result of the proposed method has been compared to both classic and state-of-the-art methods. The experimental results show that the proposed approach has better performance in comparison to state-of-the-art methods.

Original language	English
Title of host publication	2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021
Publisher	IEEE
Pages	2389-2391
Number of pages	3
ISBN (Electronic)	9781665419222
DOIs	https://doi.org/10.1109/PVSC43889.2021.9518667
Publication status	Published - 26 Aug 2021
Externally published	Yes
Event	48th IEEE Photovoltaic Specialists Conference, PVSC 2021 - Fort Lauderdale, United States Duration: 20 Jun 2021 → 25 Jun 2021 Conference number: 48

Publication series

Name	Conference Record of the IEEE Photovoltaic Specialists Conference
ISSN (Print)	0160-8371

Conference

Conference	48th IEEE Photovoltaic Specialists Conference, PVSC 2021
Abbreviated title	PVSC 2021
Country/Territory	United States
City	Fort Lauderdale
Period	20/06/21 → 25/06/21

Keywords

Clear Sky
Cloud Coverage
Cloud Detection
PV power forecast
Sky imager-based forecast
n/a OA procedure

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/PVSC43889.2021.9518667

Cite this

Shirazi, E., Lemmens, J., Gofran Chowdhury, M., Tuomiranta, A., Catthoor, F., Voroshazi, E., & Gordon, I. (2021). Cloud Detection for PV Power Forecast based on Colour Components of Sky Images. In 2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021 (pp. 2389-2391). (Conference Record of the IEEE Photovoltaic Specialists Conference). IEEE. https://doi.org/10.1109/PVSC43889.2021.9518667

@inproceedings{aafee231ea6d4f05a5bc5650c3d2099e,

title = "Cloud Detection for PV Power Forecast based on Colour Components of Sky Images",

abstract = "Integrating and operating PV in a system-efficient way is the key to increasing penetration levels to evolve toward a more sustainable and clean energy system. Reliable generation forecasting is the solution to tackle fluctuations in PV power generation and its negative effects on power systems and energy markets. Clouds play a key role in solar power, so cloud detection is important in PV power generation forecast. A color-based cloud detection algorithm is proposed in this paper. It considers 12 different color channels together with the K-means algorithm to detect clouds in sky images from an All-Sky Camera. The result of the proposed method has been compared to both classic and state-of-the-art methods. The experimental results show that the proposed approach has better performance in comparison to state-of-the-art methods.",

keywords = "Clear Sky, Cloud Coverage, Cloud Detection, PV power forecast, Sky imager-based forecast, n/a OA procedure",

author = "Elham Shirazi and Joris Lemmens and \{Gofran Chowdhury\}, Mohammed and Arttu Tuomiranta and Francky Catthoor and Eszter Voroshazi and Ivan Gordon",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 48th IEEE Photovoltaic Specialists Conference, PVSC 2021, PVSC 2021 ; Conference date: 20-06-2021 Through 25-06-2021",

year = "2021",

month = aug,

day = "26",

doi = "10.1109/PVSC43889.2021.9518667",

language = "English",

series = "Conference Record of the IEEE Photovoltaic Specialists Conference",

publisher = "IEEE",

pages = "2389--2391",

booktitle = "2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021",

address = "United States",

}

Shirazi, E, Lemmens, J, Gofran Chowdhury, M, Tuomiranta, A, Catthoor, F, Voroshazi, E & Gordon, I 2021, Cloud Detection for PV Power Forecast based on Colour Components of Sky Images. in 2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021. Conference Record of the IEEE Photovoltaic Specialists Conference, IEEE, pp. 2389-2391, 48th IEEE Photovoltaic Specialists Conference, PVSC 2021, Fort Lauderdale, United States, 20/06/21. https://doi.org/10.1109/PVSC43889.2021.9518667

Cloud Detection for PV Power Forecast based on Colour Components of Sky Images. / Shirazi, Elham; Lemmens, Joris; Gofran Chowdhury, Mohammed et al.
2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021. IEEE, 2021. p. 2389-2391 (Conference Record of the IEEE Photovoltaic Specialists Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Cloud Detection for PV Power Forecast based on Colour Components of Sky Images

AU - Shirazi, Elham

AU - Lemmens, Joris

AU - Gofran Chowdhury, Mohammed

AU - Tuomiranta, Arttu

AU - Catthoor, Francky

AU - Voroshazi, Eszter

AU - Gordon, Ivan

N1 - Conference code: 48

PY - 2021/8/26

Y1 - 2021/8/26

N2 - Integrating and operating PV in a system-efficient way is the key to increasing penetration levels to evolve toward a more sustainable and clean energy system. Reliable generation forecasting is the solution to tackle fluctuations in PV power generation and its negative effects on power systems and energy markets. Clouds play a key role in solar power, so cloud detection is important in PV power generation forecast. A color-based cloud detection algorithm is proposed in this paper. It considers 12 different color channels together with the K-means algorithm to detect clouds in sky images from an All-Sky Camera. The result of the proposed method has been compared to both classic and state-of-the-art methods. The experimental results show that the proposed approach has better performance in comparison to state-of-the-art methods.

AB - Integrating and operating PV in a system-efficient way is the key to increasing penetration levels to evolve toward a more sustainable and clean energy system. Reliable generation forecasting is the solution to tackle fluctuations in PV power generation and its negative effects on power systems and energy markets. Clouds play a key role in solar power, so cloud detection is important in PV power generation forecast. A color-based cloud detection algorithm is proposed in this paper. It considers 12 different color channels together with the K-means algorithm to detect clouds in sky images from an All-Sky Camera. The result of the proposed method has been compared to both classic and state-of-the-art methods. The experimental results show that the proposed approach has better performance in comparison to state-of-the-art methods.

KW - Clear Sky

KW - Cloud Coverage

KW - Cloud Detection

KW - PV power forecast

KW - Sky imager-based forecast

KW - n/a OA procedure

UR - https://www.scopus.com/pages/publications/85115933211

U2 - 10.1109/PVSC43889.2021.9518667

DO - 10.1109/PVSC43889.2021.9518667

M3 - Conference contribution

AN - SCOPUS:85115933211

T3 - Conference Record of the IEEE Photovoltaic Specialists Conference

SP - 2389

EP - 2391

BT - 2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021

PB - IEEE

T2 - 48th IEEE Photovoltaic Specialists Conference, PVSC 2021

Y2 - 20 June 2021 through 25 June 2021

ER -

Cloud Detection for PV Power Forecast based on Colour Components of Sky Images

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this