SunDown: Model-driven Per-Panel Solar Anomaly Detection for Residential Arrays

Feng, Menghong

Publication:
SunDown: Model-driven Per-Panel Solar Anomaly Detection for Residential Arrays

dc.contributor.advisor	Menghong Feng
dc.contributor.advisor	Noman Bashir
dc.contributor.author	Feng, Menghong
dc.contributor.department	University of Massachusetts Amherst
dc.contributor.department	Mechanical Engineering
dc.date	2024-03-28T20:20:07.000
dc.date.accessioned	2024-04-26T18:28:56Z
dc.date.available	2024-04-26T18:28:56Z
dc.date.submitted	May
dc.date.submitted	2020
dc.description.abstract	There has been significant growth in both utility-scale and residential-scale solar installa- tions 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 thesis, 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 ap- proach that leverages correlations between the power produced by adjacent panels to de- tect 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 our approach has a MAPE of 2.98% when predicting per-panel output. Our results also 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 multi- ple concurrent faults with 97.2% accuracy.
dc.description.degree	Master of Science in Mechanical Engineering (M.S.M.E.)
dc.identifier.doi	https://doi.org/10.7275/16982742
dc.identifier.orcid	https://orcid.org/0000-0003-3942-5156
dc.identifier.uri	https://hdl.handle.net/20.500.14394/33958
dc.relation.url	https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1939&context=masters_theses_2&unstamped=1
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/
dc.source.status	published
dc.subject	Solar energy
dc.subject	machine learning
dc.subject	data-driven
dc.subject	data science
dc.subject	energy efficiency
dc.subject	Computer and Systems Architecture
dc.subject	Energy Systems
dc.title	SunDown: Model-driven Per-Panel Solar Anomaly Detection for Residential Arrays
dc.type	openaccess
dc.type	article
dc.type	thesis
digcom.contributor.author	isAuthorOfPublication\|email:mfeng@umass.edu\|institution:University of Massachusetts Amherst\|Feng, Menghong
digcom.identifier	masters_theses_2/894
digcom.identifier.contextkey	16982742
digcom.identifier.submissionpath	masters_theses_2/894
dspace.entity.type	Publication