Tree-based Forecasting of Day-ahead Solar Power Generation from Granular Meteorological Features
This work addresses the need for reliable solar power forecasts to optimize grid operations and integrate distributed PV power, though it appears incremental by applying existing methods to new data.
The paper tackled the problem of forecasting day-ahead solar power generation by using tree-based machine learning methods to account for meteorological and astronomical features at granular spatial locations, achieving accurate forecasts that support grid stability and high PV penetration.
Accurate forecasts for day-ahead photovoltaic (PV) power generation are crucial to support a high PV penetration rate in the local electricity grid and to assure stability in the grid. We use state-of-the-art tree-based machine learning methods to produce such forecasts and, unlike previous studies, we hereby account for (i) the effects various meteorological as well as astronomical features have on PV power production, and this (ii) at coarse as well as granular spatial locations. To this end, we use data from Belgium and forecast day-ahead PV power production at an hourly resolution. The insights from our study can assist utilities, decision-makers, and other stakeholders in optimizing grid operations, economic dispatch, and in facilitating the integration of distributed PV power into the electricity grid.