It is widely known that the uncertainty of wind speed time series has a detrimental effect on wind power generation. In this study, the instantaneous standard deviation of wind speed (ISDWS) and the instantaneous variogram of wind speed (IVGWS) are used as pre-evaluation indicators of the quality assessment of day-ahead wind power to quantify its uncertainty. Based on the original wind speed, the ISDWS and IVGWS can be obtained by the moving average method and smooth wavelet transform. Moreover, a hybrid approach in which time series decomposition, autocorrelation analysis, optimized algorithm, and basic forecasting models are combined in an optimization framework, is designed to forecast the indicators. The proposed method is verified from two perspectives by time and spatial scales; for this verification, seven datasets have been obtained. Meanwhile, three other models without decomposition are adopted for comparison with the proposed model. To evaluate the performance of the models, three statistical error measures and the improved percentage indices have been calculated. It is found that the forecasting error statistics of the proposed model are less than those of the other models for most data sequences but the smoother sequences. Generally, the improved percentages of the proposed model are larger than those of the other models. Through Fourier analysis, the proposed model is proven to be more suitable for forecasting unsmooth sequences. Finally, it is concluded that the proposed model can be a successful tool for forecasting the assessment indicators (ISDWS and IVGWS) of wind speed fluctuation, and it can serve as a basis of wind power quality assessment.