摘要
风电的随机性和波动性给电力系统调度运行带来了一定的困难,以我国首个千万kW级风电基地甘肃酒泉风电基地为例,研究了基于神经网络的酒泉风电基地超短期风电功率预测方法,并对风速和风电功率实时数据进行了分析处理。在此基础上,基于神经网络算法和贝叶斯规则进行了超短期预测建模过程分析。最后,通过预测结果对预测模型进行了验证分析,验证结果表明预测模型合理、预测精度高,该预测结果可以为调度运行人员提供参考。
The randomness and volatility of wind power bring difficulties for power system dispatching and operation. Taking Jiuquan wind power base the first million kilowatt wind power base in China as an example, the ultra-short-term wind power prediction method based on neural network was studied, which analyzes and processes the real-time data of wind speed and wind power. On this basis, the modeling process of ultra-short-term prediction was analyzed based on the neural network algorithm and Bayes rule. Finally, the prediction model was validated through prediction results. The results show that the prediction model is reasonable, and has a high prediction accuracy, which can also provide a reference for dispatchers.
出处
《电力建设》
2013年第9期1-5,共5页
Electric Power Construction
基金
国家高技术研究发展计划(863计划)(2011AA05A104)
2009年中国电机工程学会"电力青年科技创新资助项目"
关键词
风电功率预测
超短期预测
神经网络
预测模型
wind power prediction
ultra-short-term prediction
neural network
prediction model
