摘要
为了保证电网运行的安全可靠,对光伏发电出力进行准确描述至关重要。提出布谷鸟算法优化的灰狼算法对传统k-means聚类算法进行改进,并将其应用于光伏发电出力场景分析。仿真结果表明,利用改进k-means算法缩减后得到典型场景的累积分布曲线与初始场景的累积分布曲线走势相同,且两者之间的差距很小,差异度接近0。因此典型场景不仅能够保持初始场景的时序性,也能够很好拟合初始场景的出力波动性与随机性。
In order to ensure the safe and reliable operation of the power grid,it is essential to accurately describe the output of photovoltaic power generation.The gray wolf algorithm optimized by the cuckoo algorithm was proposed to improve the traditional k-means clustering algorithm,and it was applied to the analysis of photovoltaic power generation output scenarios.The simulation results show that the cumulative distribution curve of the typical scene and the cumulative distribution curve of the initial scene obtained by the improved k-means algorithm on reducing and merging have the same trend,and the gap between the two curves is very small,and the degree of difference is close to 0.Therefore,the typical scene can not only maintain the timing of the initial scene,but also fit well the output volatility and randomness of the initial scene.
作者
虞瑄
刘高维
Yu Xuan;Liu Gaowei(East China Electric Power Design Institute Co.,Ltd.of China Power Engineering Consulting Group,Shanghai 200001,China)
出处
《电气自动化》
2022年第1期20-23,共4页
Electrical Automation
关键词
K-MEANS聚类算法
光伏发电
场景分析
出力波动性
布谷鸟-灰狼算法
k-means clustering algorithm
photovoltaic power generation
scenario analysis
output volatility
cuckoo search-gray wolf optimizer(CS-GWO)algorithm