基于多准则决策的风速组合预测

Combination Forecasting of Wind Speed Based on Multi-criteria Decision Making

风速预测对有效利用风能资源具有重要意义。为提高风速预测精度,提出一种基于多准则决策的风速组合预测方法。首先,引入预测有效度、熵值法和相关度3种方法评价单模型,由3个评价准则得到综合评价值,决策出参与组合预测的单模型集合。然后,采用诱导有序加权平均算子对单模型集合进行风速组合预测。采用山西省某风电场的测风塔数据进行仿真研究,并将该方法与单模型及基于预测误差平方和倒数法的组合预测模型对比,仿真结果表明该方法能够有效提高风速预测精度。

Wind speed forecasting is of great importance to effective use of wind energy. In order to improve the wind speed forecasting accuracy, a combination forecasting method based on multi-criteria decision making was proposed.Firstly, three criteria covering forecasting effectiveness, entropy method and correlation degree were used to evaluate the performances of individual forecasting models.And, the set of individual forecasting models for combination forecasting was gotten by integrating the three evaluation methods.Then,the induced ordered weighted averaging （IOWA） operator was used to achieve the combination forecasting of wind speed with the set of selected individual forecasting models.The data from a wind tower in Shanxi province were used to verify the validity of the proposed method.Compared with individual forecasting models and the combination forecasting model based on the reciprocal of error sum of squares, the simulation results reveal that the proposed method can improve the forecasting accuracy.