云环境下Web应用带宽资源预测与管理

Bandwidth resource prediction and management of Web applications hosted on cloud

针对Web应用带宽资源管理问题,提出了一种基于网络仿真的Web应用带宽需求和服务质量(QoS)预测方法,该方法给出了适用于Web服务的建模框架与形式说明,采用简化的并行负载模型,并运用自动化数据挖掘方法从Web应用访问日志中提取模型参数,并使用网络仿真工具建立系统模型模拟复杂网络传输过程,能够预测不同负载强度下的带宽需求和QoS变化。通过TPC-W基准测试系统验证该方法预测结果的准确性,理论分析和仿真结果表明,与传统的线性回归预测相比,网络仿真可以稳定地模拟真实系统,其对总请求数和总字节数的预测平均相对误差分别为4.6%和3.3%。最后以TPC-W基准系统为例,对Web应用不同带宽伸缩方案进行仿真评估,评估结果可以为Web应用资源管理提供决策支持。

To address the problem of bandwidth resource management in Web applications, a prediction method for bandwidth requirement and Quality of Service(QoS) of Web applications based on network simulation was proposed. A modeling framework and formal specification were presented for Web services, a simplified parallel workload model was adopted, the model parameters were extracted from Web application access logs by means of automated data mining, and the complex network transmission process was simulated by using network simulation tool. As a result, the bandwidth requirement and changes on QoS were able to be predicted under different workload intensities. A classic benchmark system named TPC-W was used to evaluate the accuracy of prediction results. Theoretical analysis and simulation results show that compared with traditional linear regression prediction, network simulation can stably simulate real system, the predicted average relative error for total request number and total byte number is 4.6% and 3.3% respectively. Finally, with different bandwidth scaling schemes simulated and evaluated based on the TPC-W benchmark system, the results can provide decision support for resource management of Web applications.