Clustering high dimensional meteorological scenarios: results and performance index

TL;DR

This paper explores clustering methods for high-dimensional climate time series data, emphasizing the impact of distance metrics and proposing a new index for better scenario selection in energy network planning.

Contribution

It introduces a novel methodology using a carefully designed index to improve clustering of climate scenarios, addressing the challenge of distance metric selection and dimension reduction.

Findings

Distance choice significantly affects clustering results.

Different distances highlight spatial or temporal patterns.

Proposed index enhances scenario selection accuracy.

Abstract

The Reseau de Transport d'Electricit\'e (RTE) is the French main electricity network operational manager and dedicates large number of resources and efforts towards understanding climate time series data. We discuss here the problem and the methodology of grouping and selecting representatives of possible climate scenarios among a large number of climate simulations provided by RTE. The data used is composed of temperature times series for 200 different possible scenarios on a grid of geographical locations in France. These should be clustered in order to detect common patterns regarding temperatures curves and help to choose representative scenarios for network simulations, which in turn can be used for energy optimisation. We first show that the choice of the distance used for the clustering has a strong impact on the meaning of the results: depending on the type of distance used, either spatial or temporal patterns prevail. Then we discuss the difficulty of fine-tuning the distance choice (combined with a dimension reduction procedure) and we propose a methodology based on a carefully designed index.