融合Stacking框架的BiGRU-LGB云负载预测模型  

BiGRU-LGB cloud load prediction model incorporating stacking framework

作　　者：刘惠[1] 董锡耀 杨志涵 LIU Hui;DONG Xiyao;YANG Zhihan(School of Computer Science and Computing,Xidian University,Xi’an 710071,China;Guangzhou Research Institute,Xidian University,Guangzhou 510555,China)

机构地区：[1]西安电子科技大学计算机科学与计算学院,陕西西安710071 [2]西安电子科技大学广州研究院,广东广州510555

出　　处：《西安电子科技大学学报》2023年第3期83-94,104,共13页Journal of Xidian University

基　　金：国家自然科学基金(62272368,62032017);陕西省创新能力支撑计划(2023-CX-TD-08);陕西省重点研发计划项目(2021ZDLGY03-09,2021ZDLGY07-02);陕西省秦创原“科学家+工程师”队伍(2023KXJ-040);陕西省高校青年创新团队资助。

摘　　要：随着云计算技术的飞速发展,越来越多的用户将应用部署在云平台上.。平台内集群资源的调度可以提高云平台数据中心的实际利用率,而高效的云平台负载预测是解决集群资源调度问题的关键技术,因此本文建立了一种融合Stacking框架、多层BiGRU网络和LightGBM算法的云负载预测模型。该模型的结构主要包括两种学习器:首先是初级学习器,使用时间编码层处理原始负载序列并利用BiGRU网络参数少、信息学习完整的特点减少模型训练时间和隐藏层数,学习负载序列中的时间维度信息;使用经过特征工程处理的原始负载序列来高效训练LightGBM算法,学习负载序列中的特征维度信息。然后是次级学习器,利用GRU网络整合时间和特征维度的负载信息,完成整个负载预测模型的训练。通过两层学习器的共同学习提高整体负载预测模型的预测精度。在华为云集群数据集上进行实验,结果表明,与传统的单一预测模型BiGRU、LightGBM等以及现有的组合预测模型GRU-LSTM相比,融合Stacking的BiGRU-LGB模型的预测精度提升约13%,训练时间开销得到一定程度的降低。With the rapid development of cloud computing technology,more and more users deploy applications on cloud platforms.The scheduling of cluster resources within the platform can improve the actual utilization of the cloud platform data center,and efficient cloud platform load prediction is a key technology for solving the cluster resource scheduling problem,so this paper establishes a cloud load prediction model that incorporates the Stacking framework,multilayer bidirectional gated recurrent unit(BiGRU)network and light gradient boosting machine(LightGBM)algorithm.The structure of the model consists mainly of two kinds of learners:one is the primary learner,which uses a temporal encoding layer to process the original load sequence and reduces the training time and the number of hidden layers by taking advantage of the BiGRU network with fewer parameters and complete information learning,to learn the temporal dimension information in the load sequence with the original load sequence processed by feature engineering used to efficiently train the LightGBM algorithm to learn the load feature dimension information in the sequence.Then comes the other learner,which integrates the load information in temporal and feature dimensions using the GRU network to complete the training of the whole load prediction model.The prediction accuracy of the overall load prediction model is improved by joint learning of the two layers of learners.Experiments are conducted on Huawei Cloud Cluster dataset with the results showing that the prediction accuracy of the BiGRU-LGB model incorporating the Stacking is improved by about 13%and the training time overhead is reduced to some extent compared with the traditional single prediction models,such as BiGRU and LightGBM,and the existing combined prediction model GRU-LSTM.

关 键 词：云平台 负载预测 双向门控循环单元 LightGBM Stacking集成框架 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]