What is it about?

Spatio-temporal solar forecasting is a trending topic, exploiting solar time series from neighboring sites in order to anticipate incoming clouds. This work assesses the impact of having neighboring sensors/systems with diverse tilt and orientation angles (standard in residential systems).

Featured Image

Why is it important?

Before this work, all spatio-temporal forecasting papers focusing on this niche used horizontal irradiance data sets as PV data is commonly stored with coarser resolutions (around 15 minutes). Better understanding the implications of urban PV data sets is essential to identify future research directions and better implement PV forecasts in self-consumption and (future) peer-to-peer energy trading.

Perspectives

Having showed that forecast quality degrades for rooftop PV ensembles with diverse tilt and orientation angles, highlights the need to correct this by some pre- or post-processing step. It is possible that machine learning approaches can actually identify and deal with this issue. It was also interesting to note that although PV façades are more challenging to forecast, they are more resilient (and may even benefit) of this layout diversity.

Rodrigo Amaro e Silva
Faculty of Sciences, University of Lisbon

Read the Original

This page is a summary of: Spatio-temporal PV forecasting sensitivity to modules’ tilt and orientation, Applied Energy, December 2019, Elsevier,
DOI: 10.1016/j.apenergy.2019.113807.
You can read the full text:

Read

Contributors

The following have contributed to this page