Soiling is the accumulation of dirt in solar panels which leads to a decreasing trend in solar energy yield and may be the cause of vast revenue losses. The effect of soiling can be reduced by washing the panels, which is, however, a procedure of non-negligible cost. Moreover, soiling monitoring systems are often unreliable or very costly. We study the problem of estimating the soiling ratio in photo-voltaic (PV) modules, i.e., the ratio of the real power output to the power output that would be produced if solar panels were clean. A key advantage of our algorithms is that they estimate soiling, without needing to train on labelled data, i.e., periods of explicitly monitoring the soiling in each park, and without relying on generic analytical formulas which do not take into account the peculiarities of each installation. We consider as input a time series comprising a minimum set of measurements, that are available to most PV park operators. Our experimental evaluation shows that we significantly outperform current state-of-the-art methods for estimating soiling ratio.

The purpose of this post is to show how the application of data science methodologies can be used to solve problems within the renewable energy sector. I will discuss techniques to gain tangible value from a dataset by using hypothesis testing, feature engineering, time-series modelling methods and much more. I will also address issues such as data leakage and data preparation for different time series models and they can be managed. The energy sector has seen a rise in harnessing renewable energy to provide homes with electricity, however, whether it be on a large scale or for domestic use, the problems remain the same. Power plants which provide electricity sourced from renewable sources, face the difficulty of intermittency and need constant maintenance.