TY - GEN
T1 - Day-Ahead Forecasting of Solar Irradiance & PV Power Output Through Statistical Machine Learning Methods
AU - Kamarianakis, Yiannis
AU - Pantazis, Yannis
AU - Kalligiannaki, Evangelia
AU - Katsaounis, Theodoros D.
AU - Kotsovos, Konstantinos
AU - Gereige, Issam
AU - Abdullah, Marwan
AU - Jamal, Aqil
AU - Tzavaras, Athanasios
N1 - KAUST Repository Item: Exported on 2023-08-14
Acknowledged KAUST grant number(s): OSR–2020-4433.02
Acknowledgements: Τhe authors acknowledge the support of KAUST and Saudi Aramco R&D Center - Carbon Management Division for their financial support in developing this work. This work was partially supported by grant #OSR–2020-4433.02 from KAUST and Saudi Aramco.
PY - 2022/12/12
Y1 - 2022/12/12
N2 - Energy production from solar photovoltaic (PV) plants is unpredictable, mainly due to the stochastic formation and movement of clouds or aerosol - dust particles which scatter or disperse solar radiation. Accurate forecasts of PV output are essential to Distribution and Transportation System Operators as they assist efficient solar energy trading and management of electricity grids. This work evaluates an autoregressive, computationally-light KNN-regression scheme (TSFKNN) for hourly, day-ahead forecasts of solar irradiance and energy yield of various PV technologies. The model is being tested and validated using data measured in Thuwal, Saudi Arabia. The available measured records span a 60-month period. The developed forecasting models are designed for online systems and provide increased levels of accuracy and low computational cost. Several parametric and nonparametric specifications, coupled with conventional versus outlier-robust estimation procedures are tested, in order to derive an optimal month-specific daily profile (MDP). Current results demonstrate that including intraday variability to the monthly-based irradiance models achieve improved predictive accuracy between 10% and 25% on average.
AB - Energy production from solar photovoltaic (PV) plants is unpredictable, mainly due to the stochastic formation and movement of clouds or aerosol - dust particles which scatter or disperse solar radiation. Accurate forecasts of PV output are essential to Distribution and Transportation System Operators as they assist efficient solar energy trading and management of electricity grids. This work evaluates an autoregressive, computationally-light KNN-regression scheme (TSFKNN) for hourly, day-ahead forecasts of solar irradiance and energy yield of various PV technologies. The model is being tested and validated using data measured in Thuwal, Saudi Arabia. The available measured records span a 60-month period. The developed forecasting models are designed for online systems and provide increased levels of accuracy and low computational cost. Several parametric and nonparametric specifications, coupled with conventional versus outlier-robust estimation procedures are tested, in order to derive an optimal month-specific daily profile (MDP). Current results demonstrate that including intraday variability to the monthly-based irradiance models achieve improved predictive accuracy between 10% and 25% on average.
UR - http://hdl.handle.net/10754/693541
UR - https://ieeexplore.ieee.org/document/10199879/
U2 - 10.1109/sasg57022.2022.10199879
DO - 10.1109/sasg57022.2022.10199879
M3 - Conference contribution
BT - 2022 Saudi Arabia Smart Grid (SASG)
PB - IEEE
ER -
