基于Cloud-P2P云存储结构，针对云中心和P2P节点存储层数据副本的访问机制，考虑节点存储层数据副本的修复过程，建立一个三维连续时间 Markov 链模型。使用矩阵几何解方法导出该模型的稳态解，并给出节点存储层传输率，数据访问延迟和副本修复率等系统性能指标的表达式。通过数值实验和系统仿真定量刻画数据副本数等系统参数对Cloud-P2P云存储结构性能的影响。构造利润函数，进行用户存储层副本数的优化设置。%Based on the Cloud-P2P storage architecture, taking into account the data access mechanism with both the data center and the peer-based layer, considering the repair process of the replica, a three-dimensional Markov chain model was constructed. The steady-state analysis of the model is obtained by using a matrix-geometric method. Then, the per-formance measures in terms of peer-based traffic load, the average access time, and the repair rate are given. Moreover, numerical results with analysis and simulation are provided to demonstrate the influence of the system parameters on the system performance. By constructing a benefit function, the number of replicas in peer-based layer is optimized.
展开▼
