Day ahead Photovoltaic Power Forecasting: An Ensemble Method Augmented with Adaptive Weighting and Data Segmentation Technique

Razin Ahmed

doi:10.26182/w8z4-tx20

Day ahead Photovoltaic Power Forecasting: An Ensemble Method Augmented with Adaptive Weighting and Data Segmentation Technique

Razin Ahmed

Research output: Thesis › Doctoral Thesis

431 Downloads (Pure)

Abstract

The advent of photovoltaics (PV), while promising near limitless green energy, has a serious drawback: the influence of weather conditions on PV output. Accurate and reliable PV power prediction is crucial. Deep-learning algorithms are state-of-the-art methods to counter the non-linear and stochastic nature of PV output. However, such deep-learning models manifest acceptable forecasts only for specific forecast-horizons and data trends. The current study proposes two unique methods: LSTM-ensemble and Meta-Boosting-Network (MBN) using adaptive-weighting and data segmentation-technique. These methods can precisely and consistently predict day-ahead PV output generation. The results establish that the MBN outperforms benchmark models by an average of 50%.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Sreeram, Victor, Supervisor Togneri, Roberto, Supervisor Datta, Amitava, Supervisor
Thesis sponsors	Australian Government Research Training Program
Award date	6 Jul 2022
DOIs	https://doi.org/10.26182/w8z4-tx20
Publication status	Unpublished - 2022

UN SDGs

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

Access to Document

10.26182/w8z4-tx20

THESIS - DOCTOR OF PHILOSOPHY - AHMED, Razin - 2022
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

Cite this

@phdthesis{4ef4eacacc304f6aa635c61825774b4d,

title = "Day ahead Photovoltaic Power Forecasting: An Ensemble Method Augmented with Adaptive Weighting and Data Segmentation Technique",

abstract = "The advent of photovoltaics (PV), while promising near limitless green energy, has a serious drawback: the influence of weather conditions on PV output. Accurate and reliable PV power prediction is crucial. Deep-learning algorithms are state-of-the-art methods to counter the non-linear and stochastic nature of PV output. However, such deep-learning models manifest acceptable forecasts only for specific forecast-horizons and data trends. The current study proposes two unique methods: LSTM-ensemble and Meta-Boosting-Network (MBN) using adaptive-weighting and data segmentation-technique. These methods can precisely and consistently predict day-ahead PV output generation. The results establish that the MBN outperforms benchmark models by an average of 50%.",

keywords = "Solar energy, PV Forecasting, Deep Learning, LSTM-Ensemble, Meta Boosting Technique, Adaptive Weighting system",

author = "Razin Ahmed",

year = "2022",

doi = "10.26182/w8z4-tx20",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Day ahead Photovoltaic Power Forecasting: An Ensemble Method Augmented with Adaptive Weighting and Data Segmentation Technique

AU - Ahmed, Razin

PY - 2022

Y1 - 2022

N2 - The advent of photovoltaics (PV), while promising near limitless green energy, has a serious drawback: the influence of weather conditions on PV output. Accurate and reliable PV power prediction is crucial. Deep-learning algorithms are state-of-the-art methods to counter the non-linear and stochastic nature of PV output. However, such deep-learning models manifest acceptable forecasts only for specific forecast-horizons and data trends. The current study proposes two unique methods: LSTM-ensemble and Meta-Boosting-Network (MBN) using adaptive-weighting and data segmentation-technique. These methods can precisely and consistently predict day-ahead PV output generation. The results establish that the MBN outperforms benchmark models by an average of 50%.

AB - The advent of photovoltaics (PV), while promising near limitless green energy, has a serious drawback: the influence of weather conditions on PV output. Accurate and reliable PV power prediction is crucial. Deep-learning algorithms are state-of-the-art methods to counter the non-linear and stochastic nature of PV output. However, such deep-learning models manifest acceptable forecasts only for specific forecast-horizons and data trends. The current study proposes two unique methods: LSTM-ensemble and Meta-Boosting-Network (MBN) using adaptive-weighting and data segmentation-technique. These methods can precisely and consistently predict day-ahead PV output generation. The results establish that the MBN outperforms benchmark models by an average of 50%.

KW - Solar energy

KW - PV Forecasting

KW - Deep Learning

KW - LSTM-Ensemble

KW - Meta Boosting Technique

KW - Adaptive Weighting system

U2 - 10.26182/w8z4-tx20

DO - 10.26182/w8z4-tx20

M3 - Doctoral Thesis

ER -

Day ahead Photovoltaic Power Forecasting: An Ensemble Method Augmented with Adaptive Weighting and Data Segmentation Technique

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this