Abstract We consider a resource allocation problem in a geographically distributed cloud network, where the goal is to obtain the capacities of the servers across the network in order to minimize the overall cost. In this study, the system resources (servers) are subject to failures, due to occasional breakdowns or cyber attacks. As a result, the servers supply is of a stochastic nature. From an optimization point of view, we are facing a non-convex multi-dimensional problem. For the solution, we propose an efficient algorithm to obtain the optimal capacities of the servers in all the regions in the network, where computational experience is presented and discussed. We then numerically analyze the effect of the supply stochastic properties, namely expected volume, variability and correlation across regions, on system performance. The methodology and the results can be used to evaluate the effect of cyber attacks on resource allocation in geographically distributed systems and on the planning of these systems.

中文翻译：

---

资源不可靠的云端资源分配

摘要 我们考虑了地理分布式云网络中的资源分配问题，其目标是获得整个网络中服务器的容量，以最小化总体成本。在本研究中，系统资源（服务器）会由于偶尔的故障或网络攻击而出现故障。因此，服务器供应具有随机性。从优化的角度来看，我们面临的是一个非凸的多维问题。对于该解决方案，我们提出了一种有效的算法来获得网络中所有区域中服务器的最佳容量，并在其中介绍和讨论了计算经验。然后，我们数值分析了供应随机属性对系统性能的影响，即跨区域的预期数量、可变性和相关性。