摘要
由于风速具有间歇性、随机性及波动性等特点,导致大规模风电并网对电力系统的安全、稳定运行带来严重影响。文章提出一种基于最大相关最小冗余(Maximum Correlation Minimum Redundancy,MRMR)的离群鲁棒极限学习机(Outlier Robust Extreme Learning Machine,ORELM)的短期风速预测新方法。首先分析影响风速的属性特征,采用MRMR算法来衡量不同风速属性特征与风速的相关性,进而确定风速属性特征的输入维度;然后对极限学习机(Extreme Learning Machine,ELM)进行优化,构建ORELM风速预测模型。最后以美国某大型风电场实测数据为依据进行风速预测,仿真结果表明该方法具有较高的预测精度。
Because of the characteristics of intermittence, randomness and fluctuation, the large-scale wind power integration has important influence on the security and stable operation of power system. This paper puts forward a new method of short-term wind speed prediction of outlier robust extreme learning machine （Outlier Robust Extreme Learning Machine, ORELM）based on maximum correlation and minimum redundancy （Maximum Correlation Minimum Redundancy, MRMR）algorithm. Firstly, the attributes of wind speed are analyzed, and the MRMR algorithm is used to measure the correlation between the characteristics of different wind speed attributes and wind speed. And the input dimension of wind speed attributes is determined. Then,the extreme learning machine （Extreme Learning Machine, ELM）is optimized, and the ORELM wind speed prediction model is constructed. Finally, the wind speed prediction is carried out based on the measured data of a large wind farm in Northeast China. The simulation results show that the proposed method has higher prediction accuracy.
出处
《可再生能源》
CAS
北大核心
2018年第1期85-90,共6页
Renewable Energy Resources
基金
国家高技术研究发展计划"863"资助项目(SS2014AA052502)
国家自然科学基金资助项目(51507027)
