Forecasting power output of photovoltaic system based on weather classification and support vector machine

Jie Shi; Wei Jen Lee; Yongqian Liu; Yongping Yang; Peng Wang

doi:10.1109/IAS.2011.6074294

Forecasting power output of photovoltaic system based on weather classification and support vector machine

Jie Shi, Wei Jen Lee, Yongqian Liu, Yongping Yang, Peng Wang

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

77 Scopus citations

Abstract

Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for the system reliability and promoting large scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machine. In the process, the weather conditions are firstly divided into four types which are clear sky, cloudy day, foggy and rainy day. One-day-ahead PV power output forecasting model for single station is derived based on the weather forecasting data and historically actual power output data as well as the principle of Support Vector Machine (SVM). After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected photovoltaic systems is effective and promising.

Original language	English
Title of host publication	2011 IEEE Industry Applications Society Annual Meeting, IAS 2011
DOIs	https://doi.org/10.1109/IAS.2011.6074294
State	Published - 2011
Externally published	Yes
Event	2011 46th IEEE Industry Applications Society Annual Meeting, IAS 2011 - Orlando, FL, United States Duration: 9 Oct 2011 → 13 Oct 2011

Publication series

Name	Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)
ISSN (Print)	0197-2618

Conference

Conference	2011 46th IEEE Industry Applications Society Annual Meeting, IAS 2011
Country/Territory	United States
City	Orlando, FL
Period	9/10/11 → 13/10/11

Keywords

Forecasting
Photovoltaic Systems
Photovoltaic cell radiation effects
Support Vector Machine
Weather Classification

Access to Document

10.1109/IAS.2011.6074294

Cite this

Shi, J., Lee, W. J., Liu, Y., Yang, Y., & Wang, P. (2011). Forecasting power output of photovoltaic system based on weather classification and support vector machine. In 2011 IEEE Industry Applications Society Annual Meeting, IAS 2011 Article 6074294 (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)). https://doi.org/10.1109/IAS.2011.6074294

@inproceedings{9795999cf03a4f37a13a787172ae8472,

title = "Forecasting power output of photovoltaic system based on weather classification and support vector machine",

abstract = "Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for the system reliability and promoting large scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machine. In the process, the weather conditions are firstly divided into four types which are clear sky, cloudy day, foggy and rainy day. One-day-ahead PV power output forecasting model for single station is derived based on the weather forecasting data and historically actual power output data as well as the principle of Support Vector Machine (SVM). After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected photovoltaic systems is effective and promising.",

keywords = "Forecasting, Photovoltaic Systems, Photovoltaic cell radiation effects, Support Vector Machine, Weather Classification",

author = "Jie Shi and Lee, {Wei Jen} and Yongqian Liu and Yongping Yang and Peng Wang",

year = "2011",

doi = "10.1109/IAS.2011.6074294",

language = "English",

isbn = "9781424494989",

series = "Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)",

booktitle = "2011 IEEE Industry Applications Society Annual Meeting, IAS 2011",

note = "2011 46th IEEE Industry Applications Society Annual Meeting, IAS 2011 ; Conference date: 09-10-2011 Through 13-10-2011",

}

Shi, J, Lee, WJ, Liu, Y, Yang, Y & Wang, P 2011, Forecasting power output of photovoltaic system based on weather classification and support vector machine. in 2011 IEEE Industry Applications Society Annual Meeting, IAS 2011., 6074294, Conference Record - IAS Annual Meeting (IEEE Industry Applications Society), 2011 46th IEEE Industry Applications Society Annual Meeting, IAS 2011, Orlando, FL, United States, 9/10/11. https://doi.org/10.1109/IAS.2011.6074294

Forecasting power output of photovoltaic system based on weather classification and support vector machine. / Shi, Jie; Lee, Wei Jen; Liu, Yongqian et al.
2011 IEEE Industry Applications Society Annual Meeting, IAS 2011. 2011. 6074294 (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)).

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

TY - GEN

T1 - Forecasting power output of photovoltaic system based on weather classification and support vector machine

AU - Shi, Jie

AU - Lee, Wei Jen

AU - Liu, Yongqian

AU - Yang, Yongping

AU - Wang, Peng

PY - 2011

Y1 - 2011

N2 - Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for the system reliability and promoting large scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machine. In the process, the weather conditions are firstly divided into four types which are clear sky, cloudy day, foggy and rainy day. One-day-ahead PV power output forecasting model for single station is derived based on the weather forecasting data and historically actual power output data as well as the principle of Support Vector Machine (SVM). After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected photovoltaic systems is effective and promising.

AB - Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for the system reliability and promoting large scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machine. In the process, the weather conditions are firstly divided into four types which are clear sky, cloudy day, foggy and rainy day. One-day-ahead PV power output forecasting model for single station is derived based on the weather forecasting data and historically actual power output data as well as the principle of Support Vector Machine (SVM). After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected photovoltaic systems is effective and promising.

KW - Forecasting

KW - Photovoltaic Systems

KW - Photovoltaic cell radiation effects

KW - Support Vector Machine

KW - Weather Classification

UR - http://www.scopus.com/inward/record.url?scp=82955180356&partnerID=8YFLogxK

U2 - 10.1109/IAS.2011.6074294

DO - 10.1109/IAS.2011.6074294

M3 - Conference contribution

AN - SCOPUS:82955180356

SN - 9781424494989

T3 - Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

BT - 2011 IEEE Industry Applications Society Annual Meeting, IAS 2011

T2 - 2011 46th IEEE Industry Applications Society Annual Meeting, IAS 2011

Y2 - 9 October 2011 through 13 October 2011

ER -

Forecasting power output of photovoltaic system based on weather classification and support vector machine

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this