Impact of Training Dataset Size for ML Load Flow Surrogates

TL;DR

This paper investigates how the size of training datasets affects the accuracy of machine learning models, specifically neural networks, in approximating load flow calculations in power systems, highlighting the importance of dataset size over model architecture.

Contribution

It provides a systematic analysis of sample efficiency for different neural network architectures in power load flow approximation, emphasizing dataset size as a key factor.

Findings

Graph Neural Networks outperform other models in accuracy.

Large training datasets significantly improve model performance.

Model architecture has less impact than dataset size.

Abstract

Efficient and accurate load flow calculations are a bedrock of modern power system operation. Classical numerical methods such as the Newton-Raphson algorithm provide highly precise results but are computationally demanding, which limits their applicability in large-scale scenario studies and optimization in time-critical contexts. Research has shown that machine learning approaches can approximate load flow results with high accuracy while substantially reducing computation time. Sample efficiency, i.e., the ability to achieve high accuracy with limited training dataset size, is still insufficiently researched, especially in grids with a fixed topology. This paper presents a systematic investigation of the sample efficiency of a Multilayer Perceptron and two Graph Neural Network variants on a dataset based on a modified IEEE 5-bus system. The results for this grid size show that Graph Neural Networks achieve the lowest losses. However, the availability of large training datasets remains the dominant factor influencing performance compared to architecture choice.