摘要
Providing precise and stable forecasts for wind speed is a priority for promoting the efficiency of the performance and the economic effectiveness of wind power generation systems. Based on this actual demand, various strategies have been proposed to solve complicated nonlinear forecasting problems like wind speed forecasting. However, the previous models ignore the decisive role of data preprocessing and the limitations of a single model, which is the main reason leading to the inaccurate prediction. Hence, an updated hybrid forecasting system built on a data preprocessing strategy is proposed to effectively predict the wind speed sequence, which includes a data preprocessing module, a multi-objective optimization module, and a forecast module. Data preprocessing contributes to better seizing the traits of the data, a multi-objective optimization algorithm is recommended to optimize the precision and stability of predictions simultaneously, and the different models are combined into a new model for accurate prediction. Moreover, a 10-min wind speed sequence is utilized to affirm the strengths of the hybrid forecasting system, and the empirical studies also affirm that the model proposed has higher exactness and stability over other models. Published under an exclusive license by AIP Publishing.
学科与关键词
- A Combined Forecasting System Based on Modified Multi-Objective Optimization for Short-Term Wind Speed and Wind Power ForecastingZhou, Qingguo; Lv, Qingquan*; Zhang, GaofengApplied Sciences-Basel, 2021, 11(20): 9383.被引 6
- Design of a combined system based on two-stage data preprocessing and multi-objective optimization for wind speed predictionWang, Ying; Wang, Jianzhou*; Li, Zhiwu; Yang, Hufang; Li, HongminEnergy, 2021, 231: 121125.被引 49
- An innovative combined model based on multi-objective optimization approach for forecasting short-term wind speed: A case study in ChinaLi, Jingrui; Wang, Jianzhou*; Zhang, Haipeng; Li, ZhiwuRENEWABLE ENERGY, 2022, 201: 766-779.被引 16
