Sustainable NARMA-10 Benchmarking for Quantum Reservoir Computing

TL;DR

This paper evaluates Quantum Reservoir Computing against classical and hybrid models on the NARMA-10 task, emphasizing its competitive accuracy and sustainability benefits in resource-limited environments.

Contribution

It provides a comparative analysis of QRC with classical and hybrid models, highlighting its potential for sustainable AI in time-series forecasting.

Findings

QRC achieves competitive forecasting accuracy.

QRC offers sustainability advantages in resource-constrained settings.

The study demonstrates QRC's promise for sustainable time-series AI applications.

Abstract

This study compares Quantum Reservoir Computing (QRC) with classical models such as Echo State Networks (ESNs) and Long Short-Term Memory networks (LSTMs), as well as hybrid quantum-classical architectures (QLSTM), for the nonlinear autoregressive moving average task (NARMA-10). We evaluate forecasting accuracy (NRMSE), computational cost, and evaluation time. Results show that QRC achieves competitive accuracy while offering potential sustainability advantages, particularly in resource-constrained settings, highlighting its promise for sustainable time-series AI applications.