Multi-objective algorithm for the design of prediction intervals for wind power forecasting model

• Published in: Applied Mathematical Modelling Vol. 67; pp. 101 - 122
• Main Authors: Jiang, Ping, Li, Ranran, Li, Hongmin
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.03.2019; Elsevier BV
• Subjects: Algorithms; Best compromise solution; Datasets; Electric power generation; Feature extraction; Forecasting; Fuzzy set theory; Fuzzy sets; Interval forecasting; Intervals; Least square support vector machine; Machine learning; Multi-objective salp swarm algorithm; Multiple objective analysis; Pareto optimization; Variation; Wind power; Wind power generation; Wind speed; Fuzzy set theory; Least square support vector machine; Interval forecasting; Multi-objective salp swarm algorithm; Best compromise solution
• ISSN: 0307-904X; 1088-8691; 0307-904X
• DOI: 10.1016/j.apm.2018.10.019

•A new algorithm based on multi-objective formulation is applied to design the prediction intervals for wind power.•Data pre-process strategy based on feature extraction is built to reduce the complexity and determine the input forms.•The wind speed prediction intervals are estimated through machine learning method.•Fuzzy set theory selection method is applied to extract the best compromise solution. A composite forecasting framework is designed and implemented successfully to estimate the prediction intervals of wind speed time series simultaneously through machine learning method embedding a newly proposed optimization method (multi-objective salp swarm algorithm). In this study, data pre-process strategy based on feature extraction is served for reducing the fluctuations of wind power generation and select appropriate input forms of wind speed datasets for the sake of improving the overall performance. Besides, fuzzy set theory selection technique is used to determine the best compromise solutions from Pareto front set deriving from the optimization phase. To test the effectiveness of the proposed composite forecasting framework, several case studies based on different time-scale wind speed datasets are conducted. The corresponding results present that the proposed framework significantly outperforms other benchmark methods, and it can provide very satisfactory results in both goals between high coverage and small width.