风力发电
涡轮机
粒子群优化
曲线拟合
非参数统计
功率优化器
功率(物理)
计算机科学
算法
风速
工程类
数学
机器学习
最大功率点跟踪
统计
气象学
电气工程
航空航天工程
物理
量子力学
电压
逆变器
作者
M. Lydia,A. Immanuel Selvakumar,S. Suresh Kumar,M. Lydia
出处
期刊:IEEE Transactions on Sustainable Energy
[Institute of Electrical and Electronics Engineers]
日期:2013-07-01
卷期号:4 (3): 827-835
被引量:198
标识
DOI:10.1109/tste.2013.2247641
摘要
A wind turbine power curve essentially captures the performance of the wind turbine. The power curve depicts the relationship between the wind speed and output power of the turbine. Modeling of wind turbine power curve aids in performance monitoring of the turbine and also in forecasting of power. This paper presents the development of parametric and nonparametric models of wind turbine power curves. Parametric models of the wind turbine power curve have been developed using four and five parameter logistic expressions. The parameters of these expressions have been solved using advanced algorithms like genetic algorithm (GA), evolutionary programming (EP), particle swarm optimization (PSO), and differential evolution (DE). Nonparametric models have been evolved using algorithms like neural networks, fuzzy c-means clustering, and data mining. The modeling of wind turbine power curve is done using five sets of data; one is a statistically generated set and the others are real-time data sets. The results obtained have been compared using suitable performance metrics and the best method for modeling of the power curve has been obtained.
科研通智能强力驱动
Strongly Powered by AbleSci AI