Practical Quantum K-Means Clustering: Performance Analysis and Applications in Energy Grid Classification

TL;DR

This paper evaluates the performance of quantum k-means clustering for energy grid classification using cloud-based quantum computers, proposing improvements and demonstrating significant accuracy gains on real-world data.

Contribution

It introduces a parallelized quantum k-means algorithm optimized for noisy hardware and applies it to energy grid data, achieving notable accuracy improvements.

Findings

Quantum distance estimation methods vary in accuracy.

The proposed quantum k-means improves accuracy by 67.8%.

Performance differences between simulation and hardware are analyzed.

Abstract

In this work, we aim to solve a practical use-case of unsupervised clustering which has applications in predictive maintenance in the energy operations sector using quantum computers. Using only cloud access to quantum computers, we complete a thorough performance analysis of what some current quantum computing systems are capable of for practical applications involving non-trivial mid-to-high dimensional datasets. We first benchmark how well distance estimation can be performed using two different metrics based on the swap-test, using angle and amplitude data embedding. Next, for the clustering performance analysis, we generate sets of synthetic data with varying cluster variance and compare simulation to physical hardware results using the two metrics. From the results of this performance analysis, we propose a general, competitive, and parallelized version of quantum $k$-means clustering to avoid some pitfalls discovered due to noisy hardware and apply the approach to a real energy grid clustering scenario. Using real-world German electricity grid data, we show that the new approach improves the balanced accuracy of the standard quantum $k$-means clustering by $67.8\%$ with respect to the labeling of the classical algorithm.