Accurate modeling of Wind Speed (WS) data is essential in renewable energy, optimization of agriculture, and disaster risk reduction. However, in the presence of nonlinearity, non-stationarity, and noise in WS, the prediction becomes less efficient. A hybrid framework that combines denoising and decomposition has been developed using WS data from Lahore from 1986 to 2016. Four single-stage preprocessing techniques, namely Moving Average (MA), Singular Spectrum Analysis (SSA), Wavelet Transform (WAV), and Empirical Mode Decomposition (EMD), and a dual-stage denoising pipeline involving Variational Mode Decomposition (VMD) and Empirical Wavelet Transform (EWT) were considered. To model the denoised WS data, statistical models, i.e., Autoregressive Moving Average (ARIMA), machine learning models, including Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Random Forest (RF), and Support Vector Machine (SVM); and deep learning models, namely Long Short Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network-LSTM (CNN-LSTM) have been implemented. Furthermore, the data were split 80-20 to assess the performance of the proposed models. Different evaluation metrics, i.e., Mean Absolute Error (MAE), Mean Bias Error (MBE), and Nash Sutcliffe Efficiency (NSE), as well as the Taylor diagram and error prediction box plot, have been used to compare the performance of the proposed methodology. Results confirmed that a simple model, such as ARIMA, with all preprocessing methods, is not suitable for WS prediction. However, SSA along with LSTM (complex model) achieved the best accuracy with least MAE and NSE i.e. 0.0627 and 0.9947 respectively. The application of a dual-stage VMD-EWT somewhat improved the performance of the weaker preprocessing methods, but it did not outperform single-stage denoising methods. Single-stage SSA, when combined with deep learning, yields the most reliable WS predictions, whereas dual-stage denoising improves stability and performance under weaker preprocessing methods.