Work

Cloud computing for mobile environments

Year: 2016
Type: article
Abstract: Cloud computing provides a useful metaphor for combining capability at different scales. Such environments may therefore consist of devices ranging from handheld smart phones to supercomputers, to serve communities ranging from individuals to whole industries. Cloud computing requirements are also widely regarded as a key enabler for next generation network environments and are expected to drive the creation of both jobs and commercial products. Cloud computing is also sometimes referred synonymously as next generation data centers, with an architecture consisting of network of virtual services (hardware, database, user-interface, and application logic) so that users are able to deploy and access applications globally and on demand at competitive costs depending on user driven quality of service requirements. Developers with innovative ideas for new Internet services no longer require large capital outlays in hardware to deploy their services, or human expense to operate it 1-7. This technology is being driven by and used in a wide range of academic, research, and commercial application areas. This use is producing important new practical experience in a variety of different problem domains in each of these areas. There are also new computational methods, such as mobile agents, cellular automata, and massively parallel neural networks, which are particularly suited to concurrent execution. As an enabler, this technology is leading to a rapid growth in both scientific and information applications that will, in turn, enable additional requirements for cloud computing technologies to be identified. These will impact academia, business, and education 4-6, 8-12. Given this context, this special issue calls for high-quality research papers in the development of cloud computing technology for mobile environments. In particular, the special issue showcased the most recent achievements and developments in the realm of cloud computing. Original research articles were solicited covering theoretical studies, practical applications, new communication technology, and experimental prototypes. All submitted papers were peer reviewed and selected on the basis of both their quality and their relevance to the theme of this special issue. The published papers are expected to focus on novel approaches for advanced cloud computing of mobile environments for future computing environments and to present high-quality results for tackling problems arising from the ever-growing advanced cloud computing technologies and services for future computing environments. We have received many manuscripts. Only five manuscripts with high quality were finally selected for this special issue. Each manuscript selected was blindly reviewed by at least three reviewers consisting of guest editors and external reviewers. We present a brief overview of each manuscript in the following. Recent advances in cloud computing for mobile environments have created new topics of interest that included the following: (1) cloud economics in mobile and pervasive environments; (2) cloud computing programming and application development; (3) scalability, discovery of services, and data in cloud computing infrastructures; (4) trust and clouds for mobile infrastructure; (5)client-cloud computing challenges; (6) grid computing services and applications for cloud deployments; (7) virtualization, modeling, and metadata in grid; (8) cloud monitoring, control, and management; (9) traffic and load balancing in multi-vendor cloud environments; (10) user profile for cloud environments; (11) performance and security in pervasive and ubiquitous cloud environments; (12) fault tolerance, resilience, survivability, and robustness in cloud environments; and (13) geographical constraints for deploying clouds. And also, the special issues include manuscripts of applications of cloud computing for mobile environments as follows: (1) concurrent solutions to specific problems in academia, industry, and society; (2) concurrent algorithms and computational methods; (3) programming environments, operating systems, tools, concurrent languages, compilers, and interpreters; (4) performance prediction, analysis, models, and results; (5) applications, algorithms, and software technologies arising from the World Wide Web; (6) unification of computing and communication and unification of parallel and distributed computing; (7) social network analysis facilitated through cloud environments; (8) ad hoc and mesh networks via cloud systems; and (9) managing streaming content with cloud environments. In these several topics of cloud computing, some articles proposed the following: Park et al. 13 proposed and experimented the group classification for a dynamic environment, where information of mobile devices is changing. The existing studies, which provide arbitrary cutoff points, are not appropriate in a dynamic environment. The proposed method provides dynamic grouping by setting cutoff points and reflecting the changes of mobile devices after calculating the entropy values. We also proposed a fault tolerance technique for a dynamic environment based on our grouping algorithm. In the proposed algorithm, different fault tolerance techniques are applied to every group according to the different information of mobile devices of each group. Choi and Lim 14, in order to maximize the parallelism within a basic block, we exploit a novel register allocation approach, called as alternative register allocation. The alternative register allocation enables the target processors to improve the parallelism by eliminating the instruction dependency within a translated block. Alternative register allocation divides the register set of the target processor into two separate groups that are used to alternately handle translated blocks. This paper achieved performance improvement by using the two sets of register allocation orders. Alternative register allocation is to maximize the pipelining performance, which is a very popular technique for all modern microprocessors, eliminating the false data dependency. Thus, this paper resolves the false dependency problem and outperforms conventional approach by up to 26.3% for some cases. Sood 15 provided an efficient prediction model for adaptive resource provisioning in the cloud for dynamic resource management. The strategy used in this paper helps the cloud service provider for optimizing resource allocation as well as making the cloud cost-effective. Load-balancing algorithm is used to divide the resource requirements of application in different clouds and, at the same time, to minimize the cost to the best possible extent. The approach used in this paper is best suitable for making the decision to allocate or release a Virtual Machine (VM) in time. This paper had also evaluated the metrics described in manuscript in terms of cost and functionality by performing various experiments. These experiments validate the accuracy of the proposed method, and the results show that the prediction accuracy of the proposed technique is considerably effective. Thus, the proposed approach is highly effective in terms of both cost and functionality. Wang et al. 16 provided a dynamic power model based on division of computation and memory and a static power model based on real-time temperature perception. The evaluation of nine typical applications showed that with the method proposed in this research, about 35% of dynamic energy (within 10% error bounds) subject to performance constraint conditions can be saved, while about 21.6% of static energy could be saved with a performance loss of less than 2.8%. De and De 17 proposed a new mobile cloud architecture, where the interactions between mobile applications and mobile cloud services are decoupled during service invocation and delivery phases. The tuple space model is used in this architecture to decouple such interactions, thereby improving adaptability and robustness of mobile cloud computing. This paper also suggested an approach of modeling and formally verifying the correctness of the proposed architecture, which also validated its adaptability and robustness during interactions between mobile applications and mobile cloud services. The modeling and verification are carried out using the mobile UNITY model. Our special thanks go to Professor Geoffrey C. Fox and Professor David W. Walker who are editors-in-chief of Concurrency and Computation: Practical and Experience and all editorial staffs for their valuable supports throughout the preparation and publication of this special issue. We would like to thank all authors for their contributions to this special issue. We also extend our thanks to the external reviewers for their excellent help in reviewing the manuscripts.
Language: English
Open Access status: bronze
OpenAlex ID: W2312629392
FWCI: 0.354
Cites: 17
Cited by: 2
Related to: 10