视频点播系统的软件老化估计和预测

针对视频点播系统,研究其软件老化模式.对系统资源和视频点播服务器的实时参数,采用Mann-Kendall方法来检测老化趋势以判断系统是否存在软件老化现象,并采用Sen的斜率估计方法来估计老化衰退速率;提出了基于径向基网络的软件老化预测模型,对老化趋势进行预测,并采用主成分分析方法来减少径向基网络的复杂度以提高效率.实验结果表明:视频点播系统中存在软件老化现象;基于径向基网络的软件老化预测模型预测效果优于时间序列模型.基于提出方法以及对视频点播系统的老化分析,可为进一步研究相应的软件再生策略提供理论依据.

Software Aging Pattern Analysis of the Video on Demand System

Video-on-demand (VOD) system is an essential and widely used multimedia application. The importance of software reliability and availability has been well recognized and demanded. The phenomenon of software aging refers to the exhaustion of operating system resource, fragmentation and accumulation of errors, which results in progressive performance degradation or transient failures or even crashes of applications. The software aging patterns of a real VOD system are investigated. Firstly, the data on several system resource usage and application server are collected. Then, the Mann-Kendall test method is adopted to detect aging trend, and Sen’s slope estimator is applied to estimate the aging degree in the data sets. Finally, radial basis function (RBF) network models are constructed to model the extracted data series of systematic parameters and to predict software aging of the VOD system. In order to reduce the complexity of RBF networks and to improve its efficiency, principal component analysis (PCA) is used to reduce the dimensionality of input variables of the networks. The experimental results show that the software aging exists in the VOD system and the software aging prediction model based on RBF network is superior to the time series models in the aspects of prediction precision. Based on the models employed here, software rejuvenation policies can be triggered by actual measurements.