Tailored algorithms for anomaly detection in photovoltaic systems

Pedro Branco, Francisco Gonçalves, Ana Cristina Costa

Research output: Contribution to journalArticle

Abstract

The fastest-growing renewable source of energy is solar photovoltaic (PV) energy, which is likely to become the largest electricity source in the world by 2050. In order to be a viable alternative energy source, PV systems should maximise their efficiency and operate flawlessly. However, in practice, many PV systems do not operate at their full capacity due to several types of anomalies. We propose tailored algorithms for the detection of different PV system anomalies, including suboptimal orientation, daytime and sunrise/sunset shading, brief and sustained daytime zero-production, and low maximum production. Furthermore, we establish simple metrics to assess the severity of suboptimal orientation and daytime shading. The proposed detection algorithms were applied to a set of time-series of electricity production in Portugal, which are based on two periods with distinct weather conditions. Under favourable weather conditions, the algorithms successfully detected most of the time-series labelled with either daytime or sunrise/sunset shading, and with either sustained or brief daytime zero-production. There was a relatively low percentage of false positives, such that most of the anomaly detections were correct. As expected, the algorithms tend to be more robust under favourable rather than under adverse weather conditions. The proposed algorithms may prove to be useful not only to research specialists, but also to energy utilities and owners of small- and medium-sized PV systems, who may thereby effortlessly monitor their operation and performance.

Original languageEnglish
Article number225
JournalEnergies
Volume13
Issue number1
DOIs
Publication statusPublished - 2 Jan 2020

Fingerprint

Photovoltaic System
Anomaly Detection
Shading
Weather
Energy
Electricity
Anomaly
Time series
Zero
False Positive
Solar energy
Percentage
Monitor
Maximise
Likely
Tend
Distinct
Metric
Alternatives

Keywords

  • Anomaly detection
  • Orientation
  • PV systems
  • Shading
  • Time-series

UN Sustainable Development Goals (SDGs)

  • SDG 7 - Affordable and Clean Energy

Cite this

Branco, Pedro ; Gonçalves, Francisco ; Costa, Ana Cristina. / Tailored algorithms for anomaly detection in photovoltaic systems. In: Energies. 2020 ; Vol. 13, No. 1.
@article{abbd7b97f211403f85cc7dc1a05cb406,
title = "Tailored algorithms for anomaly detection in photovoltaic systems",
abstract = "The fastest-growing renewable source of energy is solar photovoltaic (PV) energy, which is likely to become the largest electricity source in the world by 2050. In order to be a viable alternative energy source, PV systems should maximise their efficiency and operate flawlessly. However, in practice, many PV systems do not operate at their full capacity due to several types of anomalies. We propose tailored algorithms for the detection of different PV system anomalies, including suboptimal orientation, daytime and sunrise/sunset shading, brief and sustained daytime zero-production, and low maximum production. Furthermore, we establish simple metrics to assess the severity of suboptimal orientation and daytime shading. The proposed detection algorithms were applied to a set of time-series of electricity production in Portugal, which are based on two periods with distinct weather conditions. Under favourable weather conditions, the algorithms successfully detected most of the time-series labelled with either daytime or sunrise/sunset shading, and with either sustained or brief daytime zero-production. There was a relatively low percentage of false positives, such that most of the anomaly detections were correct. As expected, the algorithms tend to be more robust under favourable rather than under adverse weather conditions. The proposed algorithms may prove to be useful not only to research specialists, but also to energy utilities and owners of small- and medium-sized PV systems, who may thereby effortlessly monitor their operation and performance.",
keywords = "Anomaly detection, Orientation, PV systems, Shading, Time-series",
author = "Pedro Branco and Francisco Gon{\cc}alves and Costa, {Ana Cristina}",
note = "Branco, P., Gon{\cc}alves, F., & Costa, A. C. (2020). Tailored algorithms for anomaly detection in photovoltaic systems. Energies, 13(1), [225]. https://doi.org/10.3390/en13010225",
year = "2020",
month = "1",
day = "2",
doi = "10.3390/en13010225",
language = "English",
volume = "13",
journal = "Energies",
issn = "1996-1073",
publisher = "MDPI",
number = "1",

}

Tailored algorithms for anomaly detection in photovoltaic systems. / Branco, Pedro; Gonçalves, Francisco; Costa, Ana Cristina.

In: Energies, Vol. 13, No. 1, 225, 02.01.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Tailored algorithms for anomaly detection in photovoltaic systems

AU - Branco, Pedro

AU - Gonçalves, Francisco

AU - Costa, Ana Cristina

N1 - Branco, P., Gonçalves, F., & Costa, A. C. (2020). Tailored algorithms for anomaly detection in photovoltaic systems. Energies, 13(1), [225]. https://doi.org/10.3390/en13010225

PY - 2020/1/2

Y1 - 2020/1/2

N2 - The fastest-growing renewable source of energy is solar photovoltaic (PV) energy, which is likely to become the largest electricity source in the world by 2050. In order to be a viable alternative energy source, PV systems should maximise their efficiency and operate flawlessly. However, in practice, many PV systems do not operate at their full capacity due to several types of anomalies. We propose tailored algorithms for the detection of different PV system anomalies, including suboptimal orientation, daytime and sunrise/sunset shading, brief and sustained daytime zero-production, and low maximum production. Furthermore, we establish simple metrics to assess the severity of suboptimal orientation and daytime shading. The proposed detection algorithms were applied to a set of time-series of electricity production in Portugal, which are based on two periods with distinct weather conditions. Under favourable weather conditions, the algorithms successfully detected most of the time-series labelled with either daytime or sunrise/sunset shading, and with either sustained or brief daytime zero-production. There was a relatively low percentage of false positives, such that most of the anomaly detections were correct. As expected, the algorithms tend to be more robust under favourable rather than under adverse weather conditions. The proposed algorithms may prove to be useful not only to research specialists, but also to energy utilities and owners of small- and medium-sized PV systems, who may thereby effortlessly monitor their operation and performance.

AB - The fastest-growing renewable source of energy is solar photovoltaic (PV) energy, which is likely to become the largest electricity source in the world by 2050. In order to be a viable alternative energy source, PV systems should maximise their efficiency and operate flawlessly. However, in practice, many PV systems do not operate at their full capacity due to several types of anomalies. We propose tailored algorithms for the detection of different PV system anomalies, including suboptimal orientation, daytime and sunrise/sunset shading, brief and sustained daytime zero-production, and low maximum production. Furthermore, we establish simple metrics to assess the severity of suboptimal orientation and daytime shading. The proposed detection algorithms were applied to a set of time-series of electricity production in Portugal, which are based on two periods with distinct weather conditions. Under favourable weather conditions, the algorithms successfully detected most of the time-series labelled with either daytime or sunrise/sunset shading, and with either sustained or brief daytime zero-production. There was a relatively low percentage of false positives, such that most of the anomaly detections were correct. As expected, the algorithms tend to be more robust under favourable rather than under adverse weather conditions. The proposed algorithms may prove to be useful not only to research specialists, but also to energy utilities and owners of small- and medium-sized PV systems, who may thereby effortlessly monitor their operation and performance.

KW - Anomaly detection

KW - Orientation

KW - PV systems

KW - Shading

KW - Time-series

UR - http://www.scopus.com/inward/record.url?scp=85077450620&partnerID=8YFLogxK

U2 - 10.3390/en13010225

DO - 10.3390/en13010225

M3 - Article

VL - 13

JO - Energies

JF - Energies

SN - 1996-1073

IS - 1

M1 - 225

ER -