Improving Spatial Allocation for Energy System Coupling with Graph Neural Networks

TL;DR

This paper introduces a self-supervised graph neural network approach to improve spatial allocation in energy systems by integrating multiple geographic features, surpassing traditional proximity-based methods in accuracy and scalability.

Contribution

It presents a novel self-supervised GNN model that generates meaningful weights for spatial allocation, enhancing traditional Voronoi-based methods with multiple geographic attributes.

Findings

Enhanced accuracy and physical plausibility in spatial allocation.

Significant improvements in scalability and precision over traditional methods.

Effective integration of diverse geographic features using GNNs.

Abstract

In energy system analysis, coupling models with mismatched spatial resolutions is a significant challenge. A common solution is assigning weights to high-resolution geographic units for aggregation, but traditional models are limited by using only a single geospatial attribute. This paper presents an innovative method employing a self-supervised Heterogeneous Graph Neural Network to address this issue. This method models high-resolution geographic units as graph nodes, integrating various geographical features to generate physically meaningful weights for each grid point. These weights enhance the conventional Voronoi-based allocation method, allowing it to go beyond simply geographic proximity by incorporating essential geographic information.In addition, the self-supervised learning paradigm overcomes the lack of accurate ground-truth data. Experimental results demonstrate that applying weights generated by this method to cluster-based Voronoi Diagrams significantly enhances scalability, accuracy, and physical plausibility, while increasing precision compared to traditional methods.