Heuristic Resource Reservation Policies for Public Clouds in the IoT Era

Abstract

With the advances in the IoT era, the number of wireless sensor devices has been growing rapidly. This increasing number gives rise to more complex networks where more complex tasks can be executed by utilizing more computational resources from the public clouds. Cloud service providers use various pricing models for their offered services. Some models are appropriate for the cloud service user’s short-term requirements whereas the other models are appropriate for the long-term requirements of cloud service users. Reservation-based price models are suitable for long-term requirements of cloud service users. We used the pricing schemes with spot and reserved instances. Reserved instances support a hybrid cost model with fixed reservation costs that vary with contract duration and an hourly usage charge which is lower than the charge of the spot instances. Optimizing resources to be reserved requires sufficient research effort. Recent algorithms proposed for this problem are generally based on integer programming problems, so they do not have polynomial time complexity. In this work, heuristic-based polynomial time policies are proposed for this problem. It is exhibited that the cost for the cloud service user which uses our approach is comparable to optimal solutions, i.e., it is near-optimal.

From Corrective to Predictive Maintenance—A Review of Maintenance Approaches for the Power Industry

“…Due to the commercial nature of the cloud services provided, an important issue is the reasonable use of resources in pricing schemes. A noteworthy solution uses heuristic-based polynomial time policies to optimize resources to be reserved [277]. A brief comparison of the edge and cloud approaches is shown in Table 5.…”