基于压缩因子的宽度学习系统的虚拟机性能预测EI北大核心CSCD

在基于基础设施即服务的云服务模式下,精准的虚拟机性能预测,对于用户在众多资源提供商之间进行虚拟机租用策略的制定具有十分重要的意义.针对基于宽度学习系统(Broad learning system,BLS)的预测模型存在许多降低虚拟机性能预测准确性和效率的冗余节点,通过引入压缩因子,构建基于压缩因子的宽度学习系统,使预测结果更逼近输出样本,能够减少BLS的冗余特征节点与增强节点,从而加快BLS的网络收敛速度,提高BLS的泛化性能.

Virtual Machine Performance Prediction Using Broad Learning System Based on Compression Factor

In cloud service models which is based on IaaS, from the user＇s perspective, how to accurately predict performance of virtual machine is very important for making renting strategy of virtual machines between many physical servers. However, broad learning system (BLS) includes too many redundant feature nodes and enhancement nodes, resulting in decreased efficiency and accuracy of virtual machine performance prediction. Connecting compression factor to BLS, the paper builds intelligent prediction model of BLS based on compression factor (CF-BLS), and uses the model for predicting virtual machine performance.