A Robust Hybrid Classical and Quantum Model for Short-Term Wind Speed Forecasting

Abstract

Power scheduling by power utilities is more difficult than in the past decades because of a high penetration of renewable power generation, such as wind power generation, with highly uncertain and stochastic characteristics. To address this issue, a highly accurate technique for forecasting wind speed must be developed. In this work, a hybrid classical–quantum model is developed to exploit the advantages of two powerful models, a long short-term memory (LSTM) and a quantum neural network. Quantum neural networks, also known as parameterized quantum circuits, act like machine learning models but with greater expressive power. They comprise quantum gates that apply the principles of quantum mechanics in order to achieve quantum advantage. Additionally, to obtain a robust design that is insensitive to seasonal changes in the data, the Taguchi method is used to set up orthogonal experiments to set the hyperparameters of the proposed model. Historical data from seven sites in various countries (Taiwan, the Philippines, China, and South Korea) are used to forecast 24-hour-ahead wind speeds at the Fuhai wind farm near Taiwan. Comparative simulation results show that the proposed robust hybrid classical-quantum model outperforms current state-of-art models, such as classical nonlinear autoregressive network, random forest, extreme gradient boosting, support vector regression, and classical LSTM.

Keywords

• Deep learning model
• quantum neural network
• robust design
• wind speed forecasting