Sustainable NARMA-10 Benchmarking for Quantum Reservoir Computing
It addresses the problem of sustainable time-series AI for applications in resource-limited environments, but is incremental as it benchmarks existing methods.
This study compared Quantum Reservoir Computing (QRC) with classical and hybrid models on the NARMA-10 task, finding that QRC achieves competitive forecasting accuracy with potential sustainability benefits in resource-constrained settings.
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.