Abstract With the increase in the number of Internet of Things (IoT) devices having limited resources, an extension of the cloud‐computing paradigm has emerged so‐called fog computing, where all the fog cells are located at the edge of the network and the latency can be reduced. Meanwhile, an important challenge has attracted much attention with the definition of fog computing is service placement problem that is still at its very beginning research. It allows to deployment IoT applications on computational fog resources, with the objective of optimizing quality of service (QoS) requirements of applications while taking into account maximizing the utilization of fog resources. In this paper, an autonomous IoT service placement methodology including four phases of monitoring, analysis, decision‐making, and execution is proposed called as (MADE). First, the available resources and application services' status are monitored at run time. Next, the requested services are prioritized with respect to application services' deadline. Then, the Strength Pareto Evolutionary Algorithm II is applied to take decisions about the application services placement as a multi‐objective optimization problem. Finally, the decisions made in the previous phases are executed in a fog environment. The experiment results indicate that the proposed methodology outperforms its counterparts in terms of different performance metrics.

Summary The development of a communication infrastructure has made possible the expansion of the popular massively multiplayer online games. In these games, players all over the world can interact with one another in a virtual environment. The arrival rate of new players to the game environment causes fluctuations and players always expect services to be available and offer an acceptable service‐level agreement (SLA), especially in terms of response time and cost. Cloud computing emerged in the recent years as a scalable alternative to respond to the dynamic changes of the workload. In massively multiplayer online games applications, players are allowed to lease resources from a cloud provider in an on‐demand basis model. Proactive management of cloud resources in the face of workload fluctuations and dynamism upon the arrival of players are challenging issues. This paper presents a self‐learning fuzzy approach for proactive resource provisioning in cloud environment, where key is to predict parameters of the probability distribution of the incoming players in each period. In addition, we propose a self‐learning fuzzy autoscaling decision‐maker algorithm to compute the proper number of resources to be allocated to each tier in the massively multiplayer online games by applying the predicted workload and user SLA. We evaluate the effectiveness of the proposed approach under real and synthetic workloads. The experimental results indicate that the proposed approach is able to allocate resources more efficiently than other approaches.

Summary Recent advancements in web‐based application, especially in cloud computing environment, allows cloud service providers to deploy and provide web‐based services in the form of multitier applications. One of the most suitable infrastructure for the running of multitier applications is a cloud computing infrastructure. Since the arrival rate of users to the multitier applications varies over the time, deciding about the right amount of resources required to handle the each tier of multitier applications is not trivial, and it depends on the current workload of its each tier. Therefore, it is necessary to automatically provision resources to deal with fluctuating demands of the multitier applications. In this paper, we propose a hybrid resource provisioning approach for multitier applications based on a combination of the concept of the autonomic computing and the fuzzy analytical hierarchy process approach. Moreover, we present a framework based on MAPE‐k control loop for autonomous resource provisioning of multitier applications in cloud computing environments. The effectiveness of the proposed approach under real and synthetic workloads was evaluated. The experimental results indicate that the proposed solution outperforms in terms of allocated virtual machines, response time, and cost compared with the other approaches.