Generation and evaluation of space-Time trajectories of photovoltaic power

Faranak Golestaneh, Hoay Beng Gooi , Pierre Pinson

Research output: Contribution to journalJournal articleResearchpeer-review

207 Downloads (Pure)

Abstract

In the probabilistic energy forecasting literature, emphasis is mainly placed on deriving marginal predictive densities for which each random variable is dealt with individually. Such marginals description is sufficient for power systems related operational problems if and only if optimal decisions are to be made for each lead-time and each location independently of each other. However, many of these operational processes are temporally and spatially coupled, while uncertainty in photovoltaic (PV) generation is strongly dependent in time and in space. This issue is addressed here by analysing and capturing spatio-temporal dependencies in PV generation. Multivariate predictive distributions are modelled and space-time trajectories describing the potential evolution of forecast errors through successive lead-times and locations are generated. Discrimination ability of the relevant scoring rules on performance assessment of space-time trajectories of PV generation is also studied. Finally, the advantage of taking into account space-time correlations over probabilistic and point forecasts is investigated. The empirical investigation is based on the solar PV dataset of the Global Energy Forecasting
Competition (GEFCom) 2014.
Original languageEnglish
JournalApplied Energy
Volume176
Pages (from-to)80-91
ISSN0306-2619
DOIs
Publication statusPublished - 2016

Keywords

  • Stochastic dependence
  • Multivariate distribution
  • Photovoltaic energy
  • Space-time correlation

Cite this

Golestaneh, Faranak ; Gooi , Hoay Beng ; Pinson, Pierre. / Generation and evaluation of space-Time trajectories of photovoltaic power. In: Applied Energy. 2016 ; Vol. 176. pp. 80-91.
@article{db079ea043054bb1bee0d58529a6ce63,
title = "Generation and evaluation of space-Time trajectories of photovoltaic power",
abstract = "In the probabilistic energy forecasting literature, emphasis is mainly placed on deriving marginal predictive densities for which each random variable is dealt with individually. Such marginals description is sufficient for power systems related operational problems if and only if optimal decisions are to be made for each lead-time and each location independently of each other. However, many of these operational processes are temporally and spatially coupled, while uncertainty in photovoltaic (PV) generation is strongly dependent in time and in space. This issue is addressed here by analysing and capturing spatio-temporal dependencies in PV generation. Multivariate predictive distributions are modelled and space-time trajectories describing the potential evolution of forecast errors through successive lead-times and locations are generated. Discrimination ability of the relevant scoring rules on performance assessment of space-time trajectories of PV generation is also studied. Finally, the advantage of taking into account space-time correlations over probabilistic and point forecasts is investigated. The empirical investigation is based on the solar PV dataset of the Global Energy ForecastingCompetition (GEFCom) 2014.",
keywords = "Stochastic dependence, Multivariate distribution, Photovoltaic energy, Space-time correlation",
author = "Faranak Golestaneh and Gooi, {Hoay Beng} and Pierre Pinson",
year = "2016",
doi = "10.1016/j.apenergy.2016.05.025",
language = "English",
volume = "176",
pages = "80--91",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Pergamon Press",

}

Generation and evaluation of space-Time trajectories of photovoltaic power. / Golestaneh, Faranak; Gooi , Hoay Beng; Pinson, Pierre.

In: Applied Energy, Vol. 176, 2016, p. 80-91.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Generation and evaluation of space-Time trajectories of photovoltaic power

AU - Golestaneh, Faranak

AU - Gooi , Hoay Beng

AU - Pinson, Pierre

PY - 2016

Y1 - 2016

N2 - In the probabilistic energy forecasting literature, emphasis is mainly placed on deriving marginal predictive densities for which each random variable is dealt with individually. Such marginals description is sufficient for power systems related operational problems if and only if optimal decisions are to be made for each lead-time and each location independently of each other. However, many of these operational processes are temporally and spatially coupled, while uncertainty in photovoltaic (PV) generation is strongly dependent in time and in space. This issue is addressed here by analysing and capturing spatio-temporal dependencies in PV generation. Multivariate predictive distributions are modelled and space-time trajectories describing the potential evolution of forecast errors through successive lead-times and locations are generated. Discrimination ability of the relevant scoring rules on performance assessment of space-time trajectories of PV generation is also studied. Finally, the advantage of taking into account space-time correlations over probabilistic and point forecasts is investigated. The empirical investigation is based on the solar PV dataset of the Global Energy ForecastingCompetition (GEFCom) 2014.

AB - In the probabilistic energy forecasting literature, emphasis is mainly placed on deriving marginal predictive densities for which each random variable is dealt with individually. Such marginals description is sufficient for power systems related operational problems if and only if optimal decisions are to be made for each lead-time and each location independently of each other. However, many of these operational processes are temporally and spatially coupled, while uncertainty in photovoltaic (PV) generation is strongly dependent in time and in space. This issue is addressed here by analysing and capturing spatio-temporal dependencies in PV generation. Multivariate predictive distributions are modelled and space-time trajectories describing the potential evolution of forecast errors through successive lead-times and locations are generated. Discrimination ability of the relevant scoring rules on performance assessment of space-time trajectories of PV generation is also studied. Finally, the advantage of taking into account space-time correlations over probabilistic and point forecasts is investigated. The empirical investigation is based on the solar PV dataset of the Global Energy ForecastingCompetition (GEFCom) 2014.

KW - Stochastic dependence

KW - Multivariate distribution

KW - Photovoltaic energy

KW - Space-time correlation

U2 - 10.1016/j.apenergy.2016.05.025

DO - 10.1016/j.apenergy.2016.05.025

M3 - Journal article

VL - 176

SP - 80

EP - 91

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -