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

TL;DR

SunDown is a sensorless, model-driven method for detecting and classifying faults in residential solar panels by analyzing power correlations, achieving high accuracy without additional sensors.

Contribution

It introduces a novel sensorless fault detection approach that leverages power correlation models to identify and classify faults in residential solar arrays.

Findings

Achieves 2.98% MAPE in predicting panel output.

Detects faults with 99.13% accuracy, including snow, debris, and electrical issues.

Identifies multiple concurrent faults with 97.2% accuracy.

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 paper, 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 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 multiple concurrent faults with 97.2% accuracy.