Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting

TL;DR

This paper introduces a Quantum Fourier Transform-based kernel for short-term solar irradiance forecasting, demonstrating improved accuracy over classical kernels using quantum-enhanced methods on simulated data.

Contribution

It presents a novel quantum kernel leveraging QFT for time-series forecasting, integrating exogenous predictors, and validating its effectiveness on simulated solar irradiance data.

Findings

Improved median R2 and nRMSE over classical kernels

Reduced bias (nMBE) in forecasts

Tighter error margins with quantum kernel

Abstract

This study proposes a Quantum Fourier Transform (QFT)-enhanced quantum kernel for short-term time-series forecasting. Each signal is windowed, amplitude-encoded, transformed by a QFT, then passed through a protective rotation layer to avoid the QFT/QFT adjoint cancellation; the resulting kernel is used in kernel ridge regression (KRR). Exogenous predictors are incorporated by convexly fusing feature-specific kernels. On multi-station solar irradiance data across Koppen climate classes, the proposed kernel consistently improves median R2 and nRMSE over reference classical RBF and polynomials kernels, while also reducing bias (nMBE); complementary MAE/ERMAX analyses indicate tighter average errors with remaining headroom under sharp transients. For both quantum and classical models, the only tuned quantities are the feature-mixing weights and the KRR ridge alpha; classical hyperparameters (gamma, r, d) are fixed, with the same validation set size for all models. Experiments are conducted on a noiseless simulator (5 qubits; window length L=32). Limitations and ablations are discussed, and paths toward NISQ execution are outlined.