Multi-Plant Photovoltaic Energy Forecasting Challenge: Second place solution

Clément Gautrais (1, 2) , Yann Dauxais (1, 2) , Maël Guilleme (1, 2)

1 UR - Université de Rennes
2 LACODAM - Large Scale Collaborative Data Mining

This paper presents the approach we took to solve the Multi-Plant Photovoltaic Energy Forecasting Challenge for ECML/PKDD 2017. The approach we took granted us the second place of that challenge. In the paper, we will present how we moved from standard regression techniques to simple function optimization to tackle the challenge.

Domaines: Intelligence artificielle [cs.AI]

Clément Gautrais, Yann Dauxais, Maël Guilleme. Multi-Plant Photovoltaic Energy Forecasting Challenge: Second place solution. Discovery Challenges co-located with European Conference on Machine Learning - Principle and Practice of Knowledge Discovery in Database, Sep 2017, Skopje, Macedonia. ⟨hal-01639813⟩