摘要
随着移动通信技术的发展,4G、5G给人们带来了极大便利。移动互联网飞速发展,移动流量呈现爆炸式增长,基站的流量预测问题变得越来越重要。针对短期流量预测问题,本文在数据集上分别验证了ExtraTrees、Gradient Boosting、Bagging和AdaBoost四种树型学习算法预测的准确性,通过平均绝对误差(Mean Absolute Error,MAE)值衡量预测结果。MAE的值越大,模型准确度越低。实验结果表明GradientBoosting模型的MAE值最小,模型准确度最高,故应用GradientBoosting模型进行了短期流量的预测。
With the development of mobile communication technology,4G and 5G bring great convenience to people.With the rapid development of mobile Internet and the explosive growth of mobile traffic,the traffic prediction becomes more and more important.Aiming at the problem of short-term traffic prediction,this paper verifies the accuracy of Extratrees,Gradient Boosting,Bagging and AdaBoost algorithms on the data set,and measures the prediction results by mean absolute error (MAE).The higher the value of MAE,the lower the accuracy of the model.The MAE value of gradient boosting model is the smallest and the accuracy of the model is the highest,so it is used to predict the short-term traffic.
作者
李笑雪
张思凝
王娅娅
苗梦凡
Li Xiaoxue;Zhang Sining;Wang Yaya;Miao Mengfan(School of electronic information engineering,Shenyang Aerospace University,Shenyang Liaoning,110136)
出处
《电子测试》
2021年第19期48-50,共3页
Electronic Test
