农业工程学报2017，Vol.33Issue(z1)：225-230,6.DOI:10.11975/j.issn.1002-6819.2017.z1.034
农业云视频平台虚拟机负荷预测半监督偏最小二乘法模型
Virtual machine load prediction model for agricultural cloud video platform based on semi-supervised partial least squares
摘要
Abstract
In order to optimize the infrastructure resource of agricultural cloud video platform efficiently, the virtual machine (VM) placement algorithms need to know the current and future efficiency of VM resource as accurately as possible for potential actions such as service deployment, VM deployment, migration or cancellation. However, there is limited data available for analysis as the samples used in prediction are usually very small. In this paper, a sliding window model was designed to learn from small data sets considering time factor. More importantly, the existing prediction algorithms still have much room to reduce the error. So a sliding window based mathematical method was provided to calculate the aforementioned forecasts, which was combined with PLS and semi-supervised learning (semi-supervised partial least squares, SS-PLS). The feasibility and advantages were analyzed in VM load forecasting with mothod SS-PLS. Compared with auto regression moving average (ARMA), experimental results showed that the sliding-window-based model combined with SS-PLS made noticeable improvements to the forecasting accuracies, including root mean square error (RMSE) which was 1.77786, mean absolute error (MAE) which was 1.3312, and mean absolute percentage error (MAPE) which was 0.23836, with the increment of 5.47%, 6.37% and 6.12% respectively. The numerical results demonstrated that the proposed algorithm is effective in terms of the forecast accuracy.关键词
负荷/预测/算法/半监督学习/虚拟机/偏最小二乘法/滑窗Key words
load/forecasting/algorithms/semi-supervised learning/virtual machine/partial least squares/sliding-windows分类
农业科技引用本文复制引用
高万林,胡慧,徐东波,张港红..农业云视频平台虚拟机负荷预测半监督偏最小二乘法模型[J].农业工程学报,2017,33(z1):225-230,6.基金项目
National Spark Program Key Project (2015GA600002) （2015GA600002）
