Uniport: A Uniform Programming Support Framework for Mobile Cloud Computing

Abstract

Personal mobile devices (PMDs) have become the most used computing devices for many people. With the introduction of mobile cloud computing, we can augment the storage and computing capabilities of PMDs via cloud support. However, there are many challenges in developing mobile cloud applications (MCAs) that incorporate cloud computing efficiently, especially for developers targeting multiple mobile platforms.This paper presents Uniport, a uniform framework for developing MCAs. We introduce a uniform architecture for MCAs based on the Model-View-Controller (MVC) pattern and a set of programming primitives and runtime libraries. Not only can Uniport support the creation of new MCAs, it can also help transform existing mobile applications to MCAs efficiently. We demonstrate the applicability and flexibility of Uniport in a case study to transform three existing mobile applications on iOS, Android and Windows Phone, to their mobile cloud versions respectively. Evaluation results show that, with very few modifications, we can easily transform mobile applications to MCAs that can exploit the cloud support to improve performance by 3-7x and save more than half of their energy consumption.

Review on Compute Augmentation Techniques in Mobile Cloud Computing

“…Pengfei Yuan et al, [16] presented a Uniport framework which is a Uniform Programming support framework for developing Mobile Cloud applications. The framework has MVC pattern architecture to apply the various applications on multiple platforms, a set of programming primitives and runtime libraries for creating new mobile cloud applications.…”

A Survey on Modeling Energy Consumption of Cloud Applications: Deconstruction, State of the Art, and Trade-Off Debates

“…the Cloud-client computing speed ratio) [75,71]. The bigger speedup might indicate the better offloading opportunity, and lead to the higher application performance and the lower energy consumption [42,41,70]. 3) CPU Utilization: The studies [53,29] considered the power consumption in a server to be an exponential function of its CPU utilization, and the high CPU utilization is related to the underlying large workload size.…”

“…For instance, the input data size is a major driver behind the computation workload [37,39]; the energy incurred by accessing activities mainly depends on the data length [60]; and the amount of data to be transmitted is one of the discriminating factors for communication energy cost [62,45,58]. In the context of communication, the relevant studies further distinguish between two scenes: The first is on the traffic volumes exchanged between the client and the Cloud [40,1,50,51,68,66,42,75,31,81,67,43,49,29,70], while the second is on the data segments involved in, and transferred between, individual application tasks [73,57,64,41,74,2,69]. 3) Transactional Data Size: Although the required energy increases proportionally to the overall data size, small-data transactions in a Cloud application show a negative correlation with the energy consumption.…”

“…Among the popular access point technologies, WiFi and Ethernet generally consume less energy than cellular wireless networks [24,44,68,43,29,69]; although providing lower data rate, Bluetooth could be 80% to 120% more energy efficient than WiFi [31]; as for the cellular networks, LTE (4G) consumes more power than UMTS (3G), followed by EDGE (2G) [33,49]. 2) Network Bandwidth: As indicating the maximum channel capacity, the network bandwidth is considered to have a positive impact on reducing both the transmission delay and the energy consumption of Cloud applications [58,70]. Consequently, bandwidth has become a critical concern for computational offloading in the context of mobile Cloud computing [71]: The offloading effort is not preferred until the connection has sufficient bandwidth, and the benefit of offloading enlarges as the network bandwidth increases [42,72].…”

Context-Aware Mobile Application Task Offloading to the Cloud

“…The µCloud [35] is another SDK intended to help developers in developing Java components that can be executed by a cloud orchestrator or a mobile orchestrator, but the developer has to partition the code to identify the different components and on which orchestrator each should be executed. The Uniport framework [36] is intended for developing applications that can run remotely based on the Model-View-Controller (MVC) architecture, but it only considers network availability as the trigger for remote execution of a replica of the application. The MobiByte system [37] allows developers to specify objectives for offloading each of the partitions of a given mobile application.…”