摘要
风电是一种最方便、最成熟的可再生能源。风力发电具有波动性、间歇性和随机性,大容量的风力发电接入电网,对电力系统的安全、稳定运行带来影响。通过风速风功率预测,对风电场的出力进行短期预报,是解决这一问题的有效途径。常用的预测方法中,要么预测结果偏差太大,要么存在过学习、维数灾难和局部极值问题。支持向量机(SVM)应用于风速风功率预测,明显优于常用方法,得到相当可观的结果。
Wind power is the most convenient and matured form of renewable energy.But wind power is fluctuant,intermittent and stochastic.The large capacity wind power connecting into grid will bring serious challenge to the safety and stabilization of power system.Wind speed and wind power prediction is an effective way to solve this problem.The commonly used forecasting methods,or the prediction error is too large,or there are the problems such as over-learning,dimensionality disasters and the local extremum.Applying the Support Vector Machine(SVM) in the wind speed wind power prediction,will be significantly better than the usual method,the results is positive.
出处
《可再生能源》
CAS
北大核心
2010年第4期25-28,32,共5页
Renewable Energy Resources
基金
国家基金自然科学项目(50867004
50767003)
新疆维吾尔自治区重大攻关计划项目(200732141-3)
关键词
支持向量机
核函数
风速
风功率
预测
support vector machine(SVM)
kernel
wind speed
wind power
prediction