摘要
海上风电作为一种重要的新能源,准确的海上风电机组功率预测有利于电力系统的安全稳定运行。本文从数值天气预报(NWP)获得风速、风向、温度等自然条件的数据,使用Mean Shift聚类法和LSTM神经网络模型进行瞬时风功率的预测,通过该方法能有效地减少数据的处理量,精确地预测海上风电机组功率。
As an important new energy source,accurate off shore wind turbine power prediction is beneficial to the safe and stable operation of the power system.In this paper,we first obtain the data of wind speed,wind direction,temperature and other natural conditions from the weather forecast(NWP),we analyze the relationship between data and instantaneous wind power density using Mean shift clustering method and LSTM neural network model for the instantaneous wind power prediction,through which can effectively reduce the amount of data processing and the off shore wind turbine power is accurately predicted.
作者
李奂其
王天龙
罗婷
LI Huanqi;WANG Tianlong;LUO Ting(North China Electric Power University College of Electrical and Electronic Engineering,Beijing 102206;Beijing University of Agriculture College of International Education,Beijing 102206)
出处
《中国科技纵横》
2022年第10期129-131,150,共4页
China Science & Technology Overview
关键词
海上风电
风功率密度预测
聚类分析
LSTM神经网络
off shore wind power
wind power density prediction
cluster analysis
LSTM neural network
