Stop wasting money on poorly timed cleanings
Cleaning decisions directly affect both energy yield and operating costs. PVRADAR helps asset managers determine when cleaning will generate a positive economic return, before taking action.
Fixed schedules ignore real soiling conditions
- Soiling varies continuously through and from year to year
- Calendar-based schedules can trigger unnecessary or suboptimal cleaning schedules
- The real question is not whether modules are dirty, but whether cleaning will pay off
Probabilistic optimization turns plant data into daily recommendations
PVRADAR forecasts future soiling conditions and identifies the most profitable upcoming cleaning dates.
- Reconstruct historical soiling conditions for specific site and design
- Identify the most profitable cleaning strategy for each historic year
- Forecast soiling using measurements and historical data
- Define the most profitable strategy for the current year based on similar historical years
- Update cleaning strategy and economic benefit as new data becomes available
Cleaning decisions backed by economics
- Maximize recovered energy and economic return
- Avoid unnecessary and poorly timed cleanings
- Quantify the expected benefit before cleaning
- Compare the optimal date with alternative cleaning windows
- Apply a consistent methodology across portfolios and regions
Custom deliverable for your operations
The workflow is customized to available measurements, weather data, cleaning costs, and operational requirements. Results can be delivered through interactive notebooks, APIs, or custom dashboards.
Trusted by energy leaders!
TotalEnergies conducted a blind validation of the PVRADAR soiling model across 9 U.S. PV sites. Using only location and mounting configuration inputs, PVRADAR achieved the highest accuracy (median RMSE = 1.9%), outperforming pvlib’s HSU (2.3%) and Kimber (3.1%), as presented at the 2025 PVPMC Workshop in Cyprus.
Leeward Renewable Energy and PVRADAR conducted a blind comparison of soiling models using I-V measurements at two PV plants in California. Results confirmed the accuracy of the PVRADAR model and its value for portfolio-wide decision-making.
Iberdrola partnered with PVRADAR to validate soiling models and define a consistent, data-driven approach to managing soiling risks across 15 PV projects in diverse climates. A customized web application enabled efficient model comparison, portfolio-wide analysis, and integration into internal workflows.