摘要
文章基于气象数据分别利用多种不同的人工智能算法对华家岭风电场的风电功率进行了模拟。研究结果表明:几种人工智能算法都可以较好地模拟风电功率,且平均准确率都达到了88%以上;以平均绝对误差(MAE)为评价指标来看,经遗传算法优化的BP神经网络模拟效果最好,平均绝对误差为21.6MW;以均方根误差(RMSE)为评价指标来看,随机森林模拟效果最好,均方根误差为30.3MW,经遗传算法优化的BP神经网络模拟效果次之,均方根误差为30.4MW。
Based on meteorological data,various artificial intelligence algorithms are used to simulate the wind power of Huajialing Wind Farm in this paper.The research results show that several artificial intelligence algorithms can simulate wind power well,and the average accuracy rate has reached more than 88%;Taking the mean absolute error(MAE)as the evaluation index,the simulation effect of BP neural network optimized by the genetic algorithm is the best,with an average absolute error of 21.6 MW.Taking the root mean square error(RMSE)as the evaluation index,the random forest simulation has the best effect,with a root mean square error of 30.3 MW.The BP neural network simulation optimized by genetic algorithm's effect is second,and the root mean square error is 30.4 MW.
出处
《智慧农业导刊》
2021年第2期21-23,共3页
JOURNAL OF SMART AGRICULTURE
关键词
人工智能算法
风电功率
气象因子
模拟
artificial intelligence algorithm
wind power
meteorological factor
simulation
