Sustainable NARMA-10 Benchmarking for Quantum Reservoir Computing

Abstract--This study compares Quantum Reservoir Computing (QRC) with classical (Echo State Networks, LSTMs) and hybrid quantum-classical methods (QLSTM) for the nonlinear autoregressive moving average task (NARMA-10). We evaluate forecasting accuracy (NRMSE), computational cost, and evaluation time. Results show QRC achieves competitive accuracy while offering potential sustainability advantages, particularly in resource-constrained settings, highlighting its promise for sustainable, time-series AI applications. Time-series forecasting is fundamental across science and engineering; the NARMA-10 benchmark probes temporal memory and nonlinear processing. We present a systematic comparison of Quantum Reservoir Computing (QRC) [4] against classical and hybrid baselines--Echo State Networks (ESN) [1], Long Short-Term Memory (LSTM) [2], and a quantum-inspired LSTM (QLSTM)--on NARMA-10.