Exploring the Impact of Data Quality and Availability on PV Power Plant Yield Prediction Using Machine Learning and Analytical Models

Alexander Prüller; Marcus Rennhofer; Bernhard Kubicek; Martin Gröschl

Exploring the Impact of Data Quality and Availability on PV Power Plant Yield Prediction Using Machine Learning and Analytical Models

Alexander Prüller
, Marcus Rennhofer (Speaker)
, Bernhard Kubicek
, Martin Gröschl

Power and Renewable Gas Systems

Research output: Poster presentation without proceedings

Abstract

While using machine learning models for predictions of PV yield
is increasing in popularity, attention and awareness of the used
training data is becoming essential. This study investigates the
robustness of photovoltaic (PV) power plant yield predictions
under diverse data scenarios

Original language	English
Publication status	Accepted/In press - 25 Sept 2024

Research Field

Hybrid Power Plants

Cite this

@conference{3d8f9e5b7c1646ae8868fd34f4404cdd,

title = "Exploring the Impact of Data Quality and Availability on PV Power Plant Yield Prediction Using Machine Learning and Analytical Models",

abstract = "While using machine learning models for predictions of PV yield is increasing in popularity, attention and awareness of the used training data is becoming essential. This study investigates the robustness of photovoltaic (PV) power plant yield predictions under diverse data scenarios",

keywords = "Photovoltaics, Machine Learning, Yield, Forecast, sparse data",

author = "Alexander Pr{\"u}ller and Marcus Rennhofer and Bernhard Kubicek and Martin Gr{\"o}schl",

year = "2024",

month = sep,

day = "25",

language = "English",

}

TY - CONF

T1 - Exploring the Impact of Data Quality and Availability on PV Power Plant Yield Prediction Using Machine Learning and Analytical Models

AU - Prüller, Alexander

AU - Kubicek, Bernhard

AU - Gröschl, Martin

A2 - Rennhofer, Marcus

PY - 2024/9/25

Y1 - 2024/9/25

N2 - While using machine learning models for predictions of PV yield is increasing in popularity, attention and awareness of the used training data is becoming essential. This study investigates the robustness of photovoltaic (PV) power plant yield predictions under diverse data scenarios

AB - While using machine learning models for predictions of PV yield is increasing in popularity, attention and awareness of the used training data is becoming essential. This study investigates the robustness of photovoltaic (PV) power plant yield predictions under diverse data scenarios

KW - Photovoltaics

KW - Machine Learning

KW - Yield

KW - Forecast

KW - sparse data

M3 - Poster presentation without proceedings

ER -

Exploring the Impact of Data Quality and Availability on PV Power Plant Yield Prediction Using Machine Learning and Analytical Models

Abstract

Research Field

Other files and links

Cite this