Wet dust on the Photovoltaic (PV) surface is a persistent problem that is merely considered for rooftop based PV cleaning under a high humid climate like Malaysia. This paper proposes an Automated Water Recycle (AWR) method encompassing a water recycling unit for rooftop PV cleaning with the aim to enhance the electrical performance. This study makes a major contribution by developing a new model to correlate output power ($$P_{out}$$ P out ) and dust-fall factor. For model validation, we conducted an experiment of taking one set of Monocrystalline PV (mono) on a $$340\frac{W}{m^{2}}$$ 340 W m 2 of medium luminance day. One mono module was cleaned by AWR - pressurized water sprayed through 11 small holes over its front surface, while the other module was left with no-cleaning. The dust-contaminated water was filtered and collected back to the tank for recycling process. The water loss per cleaning cycle was achieved 0.32%, which was normalized to net loss of 28.8% at a frequency of 1 cycle/day for 90 days of operation. We observed that $$P_{out}$$ P out of no-cleaning PV was decreased by 29.44% than that of AWR method. From this experimental data also, a unique and more accurate model is created for $$P_{out}$$ P out prediction, which is much simpler compared to multivariables equation. Our investigation offers important insights into the accuracy of this regression model demonstrated by $$R^{2}=0.744$$ R 2 = 0.744 or a strong negative quadratic relationship between $$P_{out}$$ P out and dust-fall. The cleaning of PV modules is expected to save significant energy to reduce the payback period. Article Highlights An automated water recycle method for cleaning dust-fall in rooftop photovoltaic module is proposed. Both simulation and experimental models are developed to predict output power of the photovoltaic module. Proposed method can produce 24.40% more output power than a no-cleaning system with a mere water loss of 0.32%/cycle.