摘要
精确的云资源预测对计算平台实现安全运行具有十分重要的意义,针对新公司的云计算资源缺乏足够数据样本而造成预测模型精度降低的问题,提出一种基于WasserStein生成对抗网络(WasserStein generative adversarial network with gradient penalty,WGAN-GP)和双向门控循环单元网络(bidirectional gate recurrent unit,BiGRU)的少样本云计算资源预测模型。通过生成对抗网络去学习原始少样本数据的分布规律,以高斯噪声作为输入生成与原始数据具有相同分布的新样本数据,实现数据增强的行为;由于传统门控单元网络无法完全利用数据的时间信息,采用双向门控循环单元网络对数据的前向、反向时间信息进行双向提取并预测。以Google公开数据集进行仿真,对无增强数据和增强数据后的不同机器算法模型的预测结果进行对比。实验结果表明:使用WasserStein生成对抗网络数据增强后的双向门控循环单元网络模型精度的达到98.3%,所提方法适用于少样本数据的云计算资源预测。
Accurate cloud resources prediction for computing platform to realize the safe operation is of great significance.For the cloud computing resources lack of enough data of the new company and reduce the precision of forecasting model problem,a cloud computing resources prediction model was proposed based on WasserStein generative adversarial network with gradient penalty(WGAN-GP)and bidirectional gate recurrent unit(BiGRU).The WGAN-GP was used to learn the distribution of the original sample,and Guassian noise was used as input to generate new sample data with the same distribution as the original data,so as to realized the behavior of data enhancement.Because the traditional GRU cannot fully utilize the time information of the data,the bidirectional GRU was adopted to extract and predict the forward and reverse time information of the data.Simulation based on Google public data set,the prediction results of different machine algorithm models without enhanced data and with enhanced data were compared.The experimental results show that the accuracy of the BiGRU model enhances by WGAN-GP data reaches 98.3%,and the proposed method is suitable for cloud computing resource prediction with few sample data.
作者
陈基漓
张长晖
谢晓兰
CHEN Ji-li;ZHANG Chang-hui;XIE Xiao-lan(College of Information Science and Engineering,Guilin University of Technology,Guilin 541004,China;Guangxi Key Laboratory of Embedded Technology and Intelligent Systems,Guilin 541004,China)
出处
《科学技术与工程》
北大核心
2022年第36期16099-16107,共9页
Science Technology and Engineering
基金
国家自然科学基金(61762031)
广西科技重大专项(AA19046004)
广西自然科学基金(2021JJA170130)。
