Tree-based Forecasting of Day-ahead Solar Power Generation from Granular Meteorological Features

TL;DR

This paper employs advanced tree-based machine learning models to improve day-ahead solar power forecasts by incorporating diverse meteorological and astronomical features at multiple spatial granularities, aiding grid stability and integration.

Contribution

It introduces a novel approach that accounts for meteorological and astronomical factors at various spatial scales using tree-based models for PV power forecasting.

Findings

Enhanced forecast accuracy with meteorological features

Effective modeling at multiple spatial granularities

Potential for improved grid management and integration

Abstract

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.