Estimation of Maintenance Reliability for a Cloud Computing Network

Considering nodes failure cases, this paper mainly proposes an algorithm for the cloud computing network (CCN) to evaluate the capability that the CCN can send d units of data from the cloud to the client through two paths under both the maintenance budget and time constraints. To guarantee a good quality of service (QoS), the CCN should be maintained while falling to a failed state such that it cannot afford enough capacity to satisfy demand. Thus, the maintenance reliability is proposed in this paper. To estimate the maintenance reliability, a bounding approach is utilized to generate two sets of capacity vectors, {UB-MPs} and {LB-MPs}, where a UB-MP is the minimal capacity vector satisfying demand d and time constraint T while a LB-MP is the minimal capacity vector satisfying demand d, maintenance budget B, and time constraint T. Subsequently, the upper and lower bounds of maintenance reliability can be computed in terms of such vectors by applying the recursive sum of disjoint products algorithm. Keywords ─ Maintenance reliability, Node failure, Cloud computing network (CCN), Estimation, Minimal paths.