Estimation of Soiling Losses in Unlabeled PV Data

TL;DR

This paper introduces an automatic method to estimate soiling losses in PV systems using only historical power data, enabling scalable analysis of large, heterogeneous rooftop PV fleets without needing site or meteorological information.

Contribution

It presents a novel, fully automatic approach for estimating soiling losses from unlabeled PV data, eliminating the need for performance indices or additional site data.

Findings

Validated on a small rooftop PV fleet

Effective in heterogeneous, real-world conditions

Scalable to large PV fleets

Abstract

We provide a methodology for estimating the losses due to soiling for photovoltaic (PV) systems. We focus this work on estimating the losses from historical power production data that are unlabeled, i.e. power measurements with time stamps, but no other information such as site configuration or meteorological data. We present a validation of this approach on a small fleet of typical rooftop PV systems. The proposed method differs from prior work in that the construction of a performance index is not required to analyze soiling loss. This approach is appropriate for analyzing the soiling losses in field production data from fleets of distributed rooftop systems and is highly automatic, allowing for scaling to large fleets of heterogeneous PV systems.