Quantum-Resistant Highly Accurate Wind Speed Prediction Model

This study aims to address the increasing complexity of cyber attacks and the sensitivity of wind speed data by exploring the combination of Artificial Intelligence (AI) and cyber security measures for improved wind speed prediction accuracy and security. The collected wind speed dataset is pre-processed and encrypted using the ring learning with errors (ring-LWE) encryption algorithm, which is known for its high level of security. The encrypted data is then input to the Ensemble Empirical Mode Decomposition (EEMD) to split the encrypted signal and reduce the impact of encryption noise. The combination of Convolutional Neural Networks and Long Short-Term Memory (CNN-LSTM) models are also applied to each intrinsic mode function (IMFs) of the decomposition result. Furthermore, the parallel programming framework is also employed during the training phase, significantly improving the processing speed and efficiency. The results of the predictions are decrypted and compared with the testing set, and other works to evaluate the proposed model. The Mean Absolute Percent Error (MAPE) ranges from 7% to 10%, indicating a high level of accuracy. The findings of the study have practical implications for wind energy production and the development of smart grid systems. The study highlights the importance of considering both accuracy and security when using AI and suggests future directions for research in this area, including the development of more advanced encryption algorithms and the integration of AI and cyber security into real-world wind energy systems.