skip to main content
research-article
Public Access

Model-driven Per-panel Solar Anomaly Detection for Residential Arrays

Published: 22 September 2021 Publication History

Abstract

There has been significant growth in both utility-scale and residential-scale solar installations in recent years, driven by rapid technology improvements and falling prices. Unlike utility-scale solar farms that are professionally managed and maintained, smaller residential-scale installations often lack sensing and instrumentation for performance monitoring and fault detection. As a result, faults may go undetected for long periods of time, resulting in generation and revenue losses for the homeowner. In this article, we present SunDown, a sensorless approach designed to detect per-panel faults in residential solar arrays. SunDown does not require any new sensors for its fault detection and instead uses a model-driven approach that leverages correlations between the power produced by adjacent panels to detect deviations from expected behavior. SunDown can handle concurrent faults in multiple panels and perform anomaly classification to determine probable causes. Using two years of solar generation data from a real home and a manually generated dataset of multiple solar faults, we show that SunDown has a Mean Absolute Percentage Error of 2.98% when predicting per-panel output. Our results show that SunDown is able to detect and classify faults, including from snow cover, leaves and debris, and electrical failures with 99.13% accuracy, and can detect multiple concurrent faults with 97.2% accuracy.

References

[1]
Solar Market Insight Report. 2018.Year In Review. Retrieved March 2020 from https://www.seia.org/research-resources/solar-market-insight-report-2018-year-review.
[2]
Solar Market Insight Report. 2019. Q4. Retrieved March 2020 from https://www.seia.org/research-resources/solar-market-insight-report-2019-q4.
[3]
Enphase Microinverters. Retrieved from https://enphase.com/en-us/products-and-services/microinverters.
[4]
SolarEdge Power Optimizer. Retrieved from https://www.solaredge.com/products/power-optimizer.
[5]
Y. Akiyama, Y. Kasai, M. Iwata, E. Takahashi, F. Sato, and M. Murakawa. 2015. Anomaly detection of solar power generation systems based on the normalization of the amount of generated electricity. In Proceedings of the IEEE 29th International Conference on Advanced Information Networking and Applications (2015).
[6]
M. Alsafasfeh, I. Abdel-Qader, B. Bazuin, Q. Alsafasfeh, and W. Su. 2018. Unsupervised fault detection and analysis for large photovoltaic systems using drones and machine vision. Energies 11, 9 (2018).
[7]
R. Andrews, J. Stein, C. Hansen, and D. Riley. 2014. Introduction to the open source PVlib for python photovoltaic system modelling package. In Proceedings of the IEEE Photovoltaic Specialist Conference (2014).
[8]
A. Arenella, A. Greco, A. Saggese, and M. Vento. 2017. Real time fault detection in photovoltaic cells by cameras on drones. In Proceedings of the International Conference on Image Analysis and Recognition (2017), Springer.
[9]
N. Bashir, D. Chen, D. Irwin, and P. Shenoy. 2019. Solar-TK: A. Data-driven toolkit for solar PV performance modeling and forecasting. In Proceedings of the IEEE International Conference on Mobile Ad-hoc and Smart Systems (MASS'19).
[10]
M. Benedetti, F. Leonardi, F. Messina, C. Santoro, and A. Vasilakos. 2018. Anomaly detection and predictive maintenance for photovoltaic systems. Neurocomputing (2018).
[11]
D. Chen and D. Irwin. 2017. Black-box solar performance modeling: Comparing physical, machine learning, and hybrid approaches. ACM SIGMETRICS Performance Evaluation Review (2017).
[12]
D. Chen and D. Irwin. 2017. Sundance: Black-box behind-the-meter solar disaggregation. In Proceedings of the ACM International Conference on Future Energy Systems(e-Energy'17).
[13]
W. Chine, A. Mellit, V. Lughi, A. Malek, G. Sulligoi, and A. A. Pavan. 2016. Novel fault diagnosis technique for photovoltaic systems based onArtificial Neural Networks. Renew. Energy (2016).
[14]
M. Dhimish, V. Holmes, and M. Dales. 2017. Parallel fault detection algorithm for grid-connected photovoltaic plants. Renew. Energy (2017).
[15]
N. Engerer and F. Mills. 2014. Kpv: A. Clear-sky index for photovoltaics. Solar Energy 105 (July 2014).
[16]
P. Gao, L. Golab, and S. Keshav. 2015. What's wrong with my solar panels: A data-driven approach. In Proceedings of the International Conference on Extending Database Technology/International Conference on Database Theory (EDBT/ICDT'15) Workshops.
[17]
E. Garoudja, F. Harrou, Y. Sun, K. Kara, A. Chouder, and S. Silvestre. 2017. Statistical fault detection in photovoltaic systems.Solar Energy (2017).
[18]
F. Harrou, A. Dairi, B. Taghezouit, and Y. Sun. 2019. An unsupervised monitoring procedure for detecting anomalies in photovoltaic systems using a one-class support vector machine. Solar Energy (2019).
[19]
B. Hu. 2012. Solar Panel Anomaly Detection and Classification. MS Thesis, University of Waterloo, Canada.
[20]
Y. Hu, B. Gao, X. Song, G. Tian, K. Li, and X. He. 2013. Photovoltaic fault detection using a parameter based model. Solar Energy (2013).
[21]
S. Iyengar, S. Lee, D. Sheldon, and P. Shenoy. [n. d.]. Solarclique: Detecting anomalies in residential solar arrays. In Proceedings of the ACM SIGCAS Conference on Computing and Sustainable Societies. pp. 1–10.
[22]
S. Iyengar, N. Sharma, D. Irwin, P. Shenoy, and K. Ramamritham. 2017. A cloud-based black-box solar predictor for smart homes. ACM Trans. Cyber-phys. Syst. (2017).
[23]
S. Kalayaraman. 2016. Cognitive Drones: Aerial Robotics and Nano Satellites in Cognitive iot Solutions. IBM Research Report.
[24]
B. Kang, S. Kim, S. Bae, and J. Park. 2012. Diagnosis of output power lowering in a PV array by using the kalman-filter algorithm. IEEE Trans. Energy Convers (2012).
[25]
K. Kim, G. Seo, B. Cho, and P. Krein. 2015. Photovoltaic hot-spot detection for solar panel substrings using AC parameter characterization. IEEE Trans. Power Electr. (2015).
[26]
G. Liu and W. A. Yu. 2017. Fault detection and diagnosis technique for solar system based on elman neural network. In Proceedings of the IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC'17). IEEE.
[27]
G. Liu, W. Yu, and L. Zhu. 2018. Condition classification and performance of mismatched photovoltaic arrays via a pre-filtered elman neural network decision making tool. Solar Energy (2018).
[28]
E. Lorenz, D. Heinemann, H. Wickramarathne, H. Beyer, and S. Bofinger. 2007. Forecast of ensemble power production by grid-connected pv systems. In Proceedings of the 20th European PV Conference (2007), Milano.
[29]
E. Lorenz, J. Hurka, D. Heinemann, and H. Beyer. 2009. Irradiance forecasting for the power prediction of grid-connected photovoltaic ssystems. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. (2009).
[30]
H. Mekki, A. Mellit, and H. Salhi. 2016. Artificial neural network-based modelling and fault detection of partial shaded photovoltaic modules. In Simulation Modelling Practice and Theory (2016).
[31]
J. Pereira and M. Silveira. 2018. Unsupervised anomaly detection in energy time series data using variational recurrent autoencoders with attention. In Proceedings of the IEEE International Conference on Machine Learning and Applications (ICMLA'18), IEEE.
[32]
R. Perez, J. Schlemmer, S. Kivalov, J. Dise, P. Keelin, M. Grammatico, T. Hoff, and A. A. Tuohy 2018. New version of the suny solar forecast model: A scalable approach to site-specific model training. In Proceedings of the IEEE 45th Photovoltaic Specialists Conference (PVSC'18).
[33]
B. Schölkopf, D. Hogg, D. Wang, D. Foreman-Mackey, D. Janzing, C. Simon-Gabriel, and J. Peters. 2016. Modeling confounding by half-sibling regression. Proc. Natl. Acad. Sci. U.S.A. (2016).
[34]
N. Sharma, P. Sharma, D. Irwin, and P. Shenoy. 2011. Predicting solar generation from weather forecasts using machine learning. In Proceedings of the IEEE International Conference on Smart Grid Communications (SmartGridComm'11).
[35]
S. Vergura. 2018. Hypothesis tests-based analysis for anomaly detection in photovoltaic systems in the absence of environmental parameters. Energies (2018).
[36]
Y. Zhao, Q. Liu, D. Li, D. Kang, Q. Lv, and L. Shang. 2018. Hierarchical anomaly detection and multimodal classification in large-scale photovoltaic systems. IEEE Trans. Sust. Energy (2018).
[37]
H. Zhu, L. Lu, J. Yao, S. Dai, and Y. Hu. 2018. Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model. Solar Energy (2018).

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Cyber-Physical Systems
ACM Transactions on Cyber-Physical Systems  Volume 5, Issue 4
October 2021
312 pages
ISSN:2378-962X
EISSN:2378-9638
DOI:10.1145/3481689
  • Editor:
  • Chenyang Lu
Issue’s Table of Contents
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Journal Family

Publication History

Published: 22 September 2021
Accepted: 01 April 2021
Revised: 01 March 2021
Received: 01 August 2020
Published in TCPS Volume 5, Issue 4

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Solar anomaly detection
  2. data-driven modeling
  3. machine learning

Qualifiers

  • Research-article
  • Refereed

Funding Sources

  • NSF
  • DOE
  • Massachusetts Department of Energy Resources

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 255
    Total Downloads
  • Downloads (Last 12 months)131
  • Downloads (Last 6 weeks)15
Reflects downloads up to 17 Jan 2025

Other Metrics

Citations

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Login options

Full Access

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media