HV

道 DAO · 風 WIND · 預測 FORECAST · LIVE DEMO, runs 100% in your browser

Hybrid VQC Wind Speed Forecasting

Reference implementation of my paper (Rishabh Aryan et al.), rebuilt in Python on synthetic data because the original SCADA data is confidential. Results will differ from the published numbers.

GitHub repository · Notebook

Disclaimer · 聲明: reference implementation of my paper (Rishabh Aryan et al.), rebuilt in Python because the original SCADA data is confidential. The model is a small demo trained briefly on synthetic SCADA-style data (not the confidential SCADA data used in the paper). These numbers do not reproduce the paper's results. Quantum circuits are simulated classically; no quantum hardware is used.

預測 Forecast vs. actual (synthetic test set, 10-min steps)

actual model (computed live in JS) persistence

風 Try it: next-step forecast

Forecast (next 10 min)–
Persistence–

The sliders build a 16-step history ending at the chosen speed; the power columns follow a generic cubic power curve.

衡 Test-set metrics (synthetic)

ModelPersistence

Persistence predicts "next = current". At 10 minutes ahead it is already very accurate, so it is the honest yardstick.

道 How it works

A Conv1D-LSTM encoder feeds a 3-qubit variational quantum circuit (RY/RZ rotations, circular CNOT entanglement); a small dense head turns the qubit read-outs into the forecast. The model predicts the 10-minute change in wind speed and adds it to the current reading.

Weights were trained in PyTorch, exported to JSON and re-implemented in plain JavaScript, including a small statevector simulator for the quantum circuit. A test checks that the JS and Python predictions match within 1e-4.