Streaming IoT Data and the Quantum Edge: A Classic/Quantum Machine Learning Use Case

TL;DR

The paper addresses urgent analytics on streaming IoT data beyond Moore's Law by proposing Quantum Edge Analytics to integrate quantum machine learning (QML) into an edge-cloud continuum. It focuses on data encoding via feature maps and automatic hyperparameter tuning within Variational Quantum Algorithms for regression, evaluated on a bike-sharing dataset using Qiskit Aer simulations where the cost is minimized by adjusting parameters in a quantum circuit, i.e. the cost function $oldsymbol{ ho}(oldsymbol{ heta})$. Preliminary results compare feature maps such as ZFeatureMap and ZZFeatureMap and explore circuit hyperparameters, reporting metrics like MSE and MAE alongside runtime across 672 configurations. The work identifies fast data encoding, edge-aware hyperparameter optimization, and edge error mitigation as core challenges and argues that an edge layer can enable practical QML deployment in streaming IoT scenarios, providing a foundation for hardware-aware, low-latency quantum analytics.

Abstract

With the advent of the Post-Moore era, the scientific community is faced with the challenge of addressing the demands of current data-intensive machine learning applications, which are the cornerstone of urgent analytics in distributed computing. Quantum machine learning could be a solution for the increasing demand of urgent analytics, providing potential theoretical speedups and increased space efficiency. However, challenges such as (1) the encoding of data from the classical to the quantum domain, (2) hyperparameter tuning, and (3) the integration of quantum hardware into a distributed computing continuum limit the adoption of quantum machine learning for urgent analytics. In this work, we investigate the use of Edge computing for the integration of quantum machine learning into a distributed computing continuum, identifying the main challenges and possible solutions. Furthermore, exploring the data encoding and hyperparameter tuning challenges, we present preliminary results for quantum machine learning analytics on an IoT scenario.

Figures (4)

• Figure 1: Variational Quantum Algorithms.
• Figure 2: The Quantum Edge Analytics.
• Figure 3: MSE of Training w.r.t. Feature Map
• Figure :