A Model for joint probabilistic forecast of solar photovoltaic power and outdoor temperature

Raksha Ramakrishna, Anna Scaglione, Vijay Vittal, Emiliano Dall'Anese, Andrey Bernstein

Research output: Contribution to journalArticle

Abstract

In this paper, a stochastic model is proposed for a joint statistical description of solar photovoltaic (PV) power and outdoor temperature. The underlying correlation emerges from solar irradiance that is responsible in part for both the variability in solar PV power and temperature. The proposed model can be used to capture the uncertainty in solar PV power and its correlation with the electric power consumption of thermostatically controlled loads. First, a model for solar PV power that explicitly incorporates the stochasticity due to clouds via a regime-switching process between the three classes of sunny, overcast and partly cloudy is proposed. Then, the relationship between temperature and solar power is postulated using a second-order Volterra model. This joint modeling is leveraged to develop a joint probabilistic forecasting method for solar PV power and temperature. Real-world datasets that include solar PV power and temperature measurements in California are analyzed and the effectiveness of the joint model in providing probabilistic forecasts is verified. The proposed forecasting methodology outperforms several reference methods thus portraying that the underlying correlation between temperature and solar PV power is well defined and only requires a simple lower-complexity sampling space.

Original languageEnglish (US)
Article number8910466
Pages (from-to)6368-6383
Number of pages16
JournalIEEE Transactions on Signal Processing
Volume67
Issue number24
DOIs
StatePublished - Dec 15 2019

Fingerprint

Temperature
Stochastic models
Temperature measurement
Solar energy
Electric power utilization
Sampling
Uncertainty

Keywords

  • Dictionary learning
  • Hidden Markov Models
  • Probabilistic forecast solar power
  • Roof-Top solar panels
  • temperature forecast
  • Volterra system

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A Model for joint probabilistic forecast of solar photovoltaic power and outdoor temperature. / Ramakrishna, Raksha; Scaglione, Anna; Vittal, Vijay; Dall'Anese, Emiliano; Bernstein, Andrey.

In: IEEE Transactions on Signal Processing, Vol. 67, No. 24, 8910466, 15.12.2019, p. 6368-6383.

Research output: Contribution to journalArticle

Ramakrishna, Raksha ; Scaglione, Anna ; Vittal, Vijay ; Dall'Anese, Emiliano ; Bernstein, Andrey. / A Model for joint probabilistic forecast of solar photovoltaic power and outdoor temperature. In: IEEE Transactions on Signal Processing. 2019 ; Vol. 67, No. 24. pp. 6368-6383.
@article{0b1249297e184979b160ec0ac695960a,
title = "A Model for joint probabilistic forecast of solar photovoltaic power and outdoor temperature",
abstract = "In this paper, a stochastic model is proposed for a joint statistical description of solar photovoltaic (PV) power and outdoor temperature. The underlying correlation emerges from solar irradiance that is responsible in part for both the variability in solar PV power and temperature. The proposed model can be used to capture the uncertainty in solar PV power and its correlation with the electric power consumption of thermostatically controlled loads. First, a model for solar PV power that explicitly incorporates the stochasticity due to clouds via a regime-switching process between the three classes of sunny, overcast and partly cloudy is proposed. Then, the relationship between temperature and solar power is postulated using a second-order Volterra model. This joint modeling is leveraged to develop a joint probabilistic forecasting method for solar PV power and temperature. Real-world datasets that include solar PV power and temperature measurements in California are analyzed and the effectiveness of the joint model in providing probabilistic forecasts is verified. The proposed forecasting methodology outperforms several reference methods thus portraying that the underlying correlation between temperature and solar PV power is well defined and only requires a simple lower-complexity sampling space.",
keywords = "Dictionary learning, Hidden Markov Models, Probabilistic forecast solar power, Roof-Top solar panels, temperature forecast, Volterra system",
author = "Raksha Ramakrishna and Anna Scaglione and Vijay Vittal and Emiliano Dall'Anese and Andrey Bernstein",
year = "2019",
month = "12",
day = "15",
doi = "10.1109/TSP.2019.2954973",
language = "English (US)",
volume = "67",
pages = "6368--6383",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "24",

}

TY - JOUR

T1 - A Model for joint probabilistic forecast of solar photovoltaic power and outdoor temperature

AU - Ramakrishna, Raksha

AU - Scaglione, Anna

AU - Vittal, Vijay

AU - Dall'Anese, Emiliano

AU - Bernstein, Andrey

PY - 2019/12/15

Y1 - 2019/12/15

N2 - In this paper, a stochastic model is proposed for a joint statistical description of solar photovoltaic (PV) power and outdoor temperature. The underlying correlation emerges from solar irradiance that is responsible in part for both the variability in solar PV power and temperature. The proposed model can be used to capture the uncertainty in solar PV power and its correlation with the electric power consumption of thermostatically controlled loads. First, a model for solar PV power that explicitly incorporates the stochasticity due to clouds via a regime-switching process between the three classes of sunny, overcast and partly cloudy is proposed. Then, the relationship between temperature and solar power is postulated using a second-order Volterra model. This joint modeling is leveraged to develop a joint probabilistic forecasting method for solar PV power and temperature. Real-world datasets that include solar PV power and temperature measurements in California are analyzed and the effectiveness of the joint model in providing probabilistic forecasts is verified. The proposed forecasting methodology outperforms several reference methods thus portraying that the underlying correlation between temperature and solar PV power is well defined and only requires a simple lower-complexity sampling space.

AB - In this paper, a stochastic model is proposed for a joint statistical description of solar photovoltaic (PV) power and outdoor temperature. The underlying correlation emerges from solar irradiance that is responsible in part for both the variability in solar PV power and temperature. The proposed model can be used to capture the uncertainty in solar PV power and its correlation with the electric power consumption of thermostatically controlled loads. First, a model for solar PV power that explicitly incorporates the stochasticity due to clouds via a regime-switching process between the three classes of sunny, overcast and partly cloudy is proposed. Then, the relationship between temperature and solar power is postulated using a second-order Volterra model. This joint modeling is leveraged to develop a joint probabilistic forecasting method for solar PV power and temperature. Real-world datasets that include solar PV power and temperature measurements in California are analyzed and the effectiveness of the joint model in providing probabilistic forecasts is verified. The proposed forecasting methodology outperforms several reference methods thus portraying that the underlying correlation between temperature and solar PV power is well defined and only requires a simple lower-complexity sampling space.

KW - Dictionary learning

KW - Hidden Markov Models

KW - Probabilistic forecast solar power

KW - Roof-Top solar panels

KW - temperature forecast

KW - Volterra system

UR - http://www.scopus.com/inward/record.url?scp=85076813122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076813122&partnerID=8YFLogxK

U2 - 10.1109/TSP.2019.2954973

DO - 10.1109/TSP.2019.2954973

M3 - Article

AN - SCOPUS:85076813122

VL - 67

SP - 6368

EP - 6383

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 24

M1 - 8910466

ER -