One-Day-Ahead Wind Speed Forecasting Based on Advanced Deep and Hybrid Quantum Machine Learning

Electricity demand has been rising significantly over the past few years, making it crucial to integrate renewable energy sources (RES) into power networks on a wide scale. Among the most popular alternative energy sources with very high potential is wind energy. However, there is significant variability in wind speed, which results in significant fluctuations in the electricity production from the wind energy. As a result, it is challenging to integrate RES technology and especially wind energy into electricity networks. More accurate forecasts are necessary for the efficient operation of RES power plants, as well as the provision of high-quality electricity at the most affordable prices and the secure and stable operation of electrical networks. Four deep machine learning (ML) algorithms, i.e. multi-head CNN, hybrid quantum multi-head CNN, multi-channel CNN, and encoder–decoder LSTM were applied in this study to estimate medium-term (24 h ahead) wind speed using a real-time measurement dataset.