A Time-Driven Cloudlet Placement Strategy for Workflow Applications in Wireless Metropolitan Area Networks

With the rapid development of mobile technology, mobile applications have increasing requirements for computational resources, and mobile devices can no longer meet these requirements. Mobile edge computing (MEC) has emerged in this context and has brought innovation into the working mode of traditional cloud computing. By provisioning edge server placement, the computing power of the cloud centre is distributed to the edge of the network. The abundant computational resources of edge servers compensate for the lack of mobile devices and shorten the communication delay between servers and users. Constituting a specific forms of edge servers, cloudlets have been widely studied within academia and industry in recent years. However, existing studies have mainly focused on computation offloading for general computing tasks under fixed cloudlet placement positions. They ignored the impact on computation offloading results from cloudlet placement positions and data dependencies among mobile application components. In this paper, we study the cloudlet placement problem based on Workflow Applications (WAs) in Wireless Metropolitan Area Networks (WMANs). We devise a cloudlet placement strategy based on a Particle swarm optimization algorithm using Genetic algorithm operators with the Encoding Library updating mode (PGEL), which enables the cloudlet to be placed in appropriate positions. The simulation results show that the proposed strategy can obtain a near-optimal cloudlets placement scheme, and compared with other classic algorithms, this algorithm can reduce the execution time of WAs by 15.04%-44.99%.

Method for Effective Use of Cloudlet Network Resources

The article addresses the issue of balanced placement of mobile software applications of mobile users in cloudlets deployed near base stations of Wireless Metropolitan Area Networks (WMAN), taking into account their technical capabilities. It is noted that the proposed model is more efficient in meeting the demand for computing and memory resources of mobile devices, eliminating network delays and using a reliable communication channel. At the same time, a minimum of cloudlet-based communication channels with a mobile user was suggested, reducing the network load and reliability of the communication channel when using multimedia software on mobile devices. The article reviews the balanced distribution of the tasks in the cloudlet network. If a user offloads the task to the nearest cloud and resolves it there, then the delays and energy consumption will be less. When the cloudlet is far from the mobile device, as the number of communication channels increases the delays are observed. Moreover, the article discusses the issue of selecting the cloudlets that meet some of the user requirements. Using the possible values that determine the importance of cloudlets (vacant resources in cloudlets, closeness of cloudlets to the user, high reliability, etc.), the conditions, according to which the user's application is offloaded to the certain cloudlet, are studied and a method is proposed.

A Long-Term Cost-Oriented Cloudlet Planning Method in Wireless Metropolitan Area Networks

As an extension of remote cloud data centers, cloudlets process the workloads from mobile users at the network edge, thereby satisfying the requirements of resource-intensive and latency-sensitive applications. One of the fundamental yet important issues for cloudlet infrastructure providers (ISP) is how to plan the placement and capacities of cloudlets so that minimize their long-term cost with a guarantee on service delay. However, existing work mostly focuses on resource provision or resource management for mobile services on existing cloudlets, while very little attention has been paid to the cloudlet placement and capacity planning problem. In contrast to those studies, we aim to optimize the long-term total cost of cloudlets’ ISPs through intelligently planning the location and capacities of cloudlets under constraints on the service delay experienced by mobile users. This problem is then decomposed into two sub-problems and algorithms are devised to solve it. Evaluations on randomly generated traces and real traces exhibit the superior performance of the proposed solution on saving ISP’s long-term cost.