Automatic fault detection on BIPV systems without solar irradiation data
BIPV systems are small PV generation units spread out over the territory, and whose characteristics are very diverse. This makes difficult a cost-effective procedure for monitoring, fault detection, performance analyses, operation and maintenance. As a result, many problems affecting BIPV systems go undetected. In order to carry out effective automatic fault detection procedures, we need a performance indicator that is reliable and that can be applied on many PV systems at a very low cost. The existing approaches for analyzing the performance of PV systems are often based on the Performance Ratio (PR), whose accuracy depends on good solar irradiation data, which in turn can be very difficult to obtain or cost-prohibitive for the BIPV owner. We present an alternative fault detection procedure based on a performance indicator that can be constructed on the sole basis of the energy production data measured at the BIPV systems. This procedure does not require the input of operating conditions data, such as solar irradiation, air temperature, or wind speed. The performance indicator, called Performance to Peers (P2P), is constructed from spatial and temporal correlations between the energy output of neighboring and similar PV systems. This method was developed from the analysis of the energy production data of approximately 10,000 BIPV systems located in Europe. The results of our procedure are illustrated on the hourly, daily and monthly data monitored during one year at one BIPV system located in the South of Belgium. Our results confirm that it is possible to carry out automatic fault detection procedures without solar irradiation data. P2P proves to be more stable than PR most of the time, and thus constitutes a more reliable performance indicator for fault detection procedures.
💡 Research Summary
The paper addresses a critical challenge in the monitoring of building‑integrated photovoltaic (BIPV) systems: the high cost and limited availability of accurate solar irradiation data, which hampers the reliability of traditional performance metrics such as the Performance Ratio (PR). BIPV installations are highly heterogeneous in terms of location, orientation, tilt, and building architecture, making a one‑size‑fits‑all monitoring approach impractical. Moreover, many small‑scale owners cannot afford dedicated pyranometers or the maintenance of weather stations, leading to frequent data gaps and, consequently, to mis‑diagnosis of faults when PR is used as the sole indicator.
To overcome these limitations, the authors propose a novel performance indicator called Performance to Peers (P2P). The core idea is to exploit the spatial and temporal correlations among neighboring PV systems that experience essentially the same solar resource. By constructing a peer network from a large dataset of approximately 10,000 BIPV installations across Europe, the method derives a reference production profile for each system without ever requiring explicit irradiation, temperature, or wind speed measurements.
The methodology proceeds as follows: (1) raw hourly energy production data are cleaned, with missing values interpolated and outliers removed; (2) each time series is normalized to remove seasonal and diurnal effects, typically by converting to z‑scores based on the mean and standard deviation for each hour of the day and month; (3) pairwise Pearson correlation coefficients are computed between all systems; (4) a weighting scheme combines correlation strength with geographic distance, so that only systems that are both close in space (e.g., within 5 km) and highly correlated (correlation ≥ 0.85) are retained as peers; (5) for a given target system i at time t, the weighted average production of its peers is calculated, and the P2P value is defined as the ratio of the target’s actual production to this weighted average. Mathematically:
\