基于时间卷积网络的云平台负载预测方法

Cloud Platform Load Prediction Method Based on Temporal Convolutional Network

针对云平台资源负载数据高度非平稳以及存在着随机噪声导致预测准确度较低等问题,结合信号分解和深度学习等技术,提出了一种云平台资源负载预测方法。首先利用经验模态分解(Empirical Mode Decomposition, EMD)方法对原始数据进行分解,得到多个IMF分量;然后构建出基于时间卷积网络(Temporal Convolutional Network, TCN)的预测模型,分别对IMF分量进行预测;最后将预测结果进行合并以得到最终的预测值。将所提方法与传统的预测方法及深度学习预测方法进行比较,并在阿里巴巴开源的数据中心资源监控日志数据集上进行了对比实验。实验结果表明,所提方法的预测误差分别比ARIMA,Bi-LSTM,GRU,TCN降低了36.75%,23.5%,24.44%,24.53%,预测结果具有最优的准确度。

Aiming at the problems of highly non-stationary cloud platform resource load data and low prediction accuracy due to random noise,a cloud platform resource load prediction method is proposed by combining signal decomposition and deep learning technologies.Firstly,the original data is decomposed using empirical mode decomposition(EMD)method to obtain multiple IMF components;then a prediction model based on temporal convolutional network(TCN)is constructed to predict the IMF components separately;finally,the prediction results are combined to obtain the final prediction value.The proposed method is compared with traditional prediction methods and deep learning prediction methods,and a comparative experiment is carried out on Alibaba’sopen source data center resource monitoring log data set.Experimental data results show that the prediction errors of the proposed method reduces by 36.75%,23.5%,24.44%,and 24.53%compared with ARIMA,Bi-LSTM,GRU and TCN,respectively,and the prediction results have the best accuracy.