Open AccessOptimisation of time window size for wind power ramps prediction
Author(s) -
Ouyang Tinghui,
Zha Xiaming,
Qin Liang,
Kusiak Andrew
Publication year - 2017
Publication title -
iet renewable power generation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.005
H-Index - 76
eISSN - 1752-1424
pISSN - 1752-1416
DOI - 10.1049/iet-rpg.2016.0341
Subject(s) - window (computing) , genetic algorithm , power (physics) , wind power , computer science , wind speed , point (geometry) , simulation , control theory (sociology) , engineering , mathematics , meteorology , artificial intelligence , machine learning , physics , geometry , quantum mechanics , electrical engineering , operating system , control (management)
A new long‐term wind power prediction approach based on time windows is proposed to improve the accuracy and efficiency of wind power ramp prediction. An optimisation model is built to select the optimal time window size which is the key point of the wind power forecasting. First, a swinging door algorithm is applied to identify historical ramp events, and historical data is divided into several sections by assumed time window size. Then, windows are classified into ramp windows and non‐ramp windows, and the non‐ramp data of ramp windows is required to be minimal. The variables, parameters, and constraints of the model are investigated in the study, and a kind of genetic algorithm is utilised to achieve the optimal solution. The model presented in this study is validated by the study case of actual wind farms, and evaluation and discussion demonstrate the validity of the proposed approach.