COAST: A COOPERATIVE STORAGE FRAMEWORK FOR MOBILE TRANSPARENT COMPUTING USING DEVICE-TO-DEVICE DATA SHARING
Abstract
TC is a promising network computing paradigm that offers an efficient way to make lightweight terminals more powerful, convenient, and secure. TC’s execution model separates data storage and application execution, letting terminals load applications from TC servers on demand via the Internet. With this approach, the network’s performance significantly affects the TC applications’ performance. To enhance TC applications’ performance, existing research typically deploys many cache servers on the Internet. However, such caching techniques are not ideal in a mobile environment, where the wireless networks that mobile terminals use for Internet access are expensive and have limited bandwidth. To address this problem, we propose COAST, a cooperative storage framework for MTC. Based on a deviceto- device data-sharing technique, COAST enables a mobile terminal to fetch applications from nearby terminals without accessing the Internet. In this article, we introduce COAST’s design, explore the opportunities and challenges of cooperative storage in MTC environments, and identify future research directions.
EXISTING SYSTEM:
With its efficiency, power, convenience, and security, transparent computing (TC) [1] proffers multiple attractive attributes. Notably, this network computing paradigm aims to provide cross-platform application execution with lightweight terminals from anywhere, at any time. It achieves its aim by separating data storage and application execution on different computers, where the networks are used as buses that connect the storage (i.e., servers) and computing units (i.e., terminals). This execution model largely benefits the lightweight terminals, because then the terminals can execute large-size applications on limited local storage space. Mobile transparent computing (MTC) has recently garnered much attention from the future computing research community. Proposed a scalable Internet of Things (IoT) architecture based on designed an MTC-based system for power-efficient wearable devices such as smart watches and smart glasses. Most wireless MTC terminals are lightweight, with limited computing, storage, and energy resources. Thus, to accomplish tasks, they need to intensively communicate with TC servers to obtain server-side data. As the number of MTC terminals increases, the immense amount of client-server traffic causes significant network congestion. Furthermore, the terminals typically use cellular networks to connect the servers, but the cellular networks are expensive and have limited bandwidth.
PROPOSED SYSTEM:
Usually, TC needs a high-performance network to support its execution model. In TC’s execution model, an application stored on the server side is split into multiple code blocks; when executing the application, the code blocks are transferred from a server to a terminal via networks. Recent research widely employs caching techniques to improve TC’s performance on low-per-formance networks (including networks with low bandwidth or high latency). The caches buffer code blocks on terminals, servers, and network middle boxes. On the terminal side, client caches buffer the code blocks sent from servers to reduce the I/O response time on the server side, the server caches buffer terminal requests to reduce the time for looking up in the code-block database on the network middle boxes, intermediate caches are used to reduce the servers’ workloads and the latencies for requesting code blocks. All the caches form a hierarchical cache structure managed by a multilevel cache framework. Recently, proposed a novel block-level caching optimization method for MTC terminals, which significantly increases the startup speed of terminals, reduces network traffic, and improves user experience. The existing TC/MTC caching techniques are mainly based on the traditional client-server execution model. Since the number of MTC terminals can be massive and the wireless networks are unstable, we have to address the following problems in MTC
CONCLUSION
Our cooperative storage framework is designed especially for lightweight MTC terminals. We based COAST on a D2D data sharing technique, and in this article, we explain the design of COAST’s storage and communication layers. Because of COAST’s demonstrated effectiveness, we hope it will become a standard component of the MTC terminal’s implementation.
REFERENCES:
[1] Y. Zhang et al., “A Survey on Emerging Computing Paradigms for Big Data,” Chinese J. Electronics, vol. 26, no. 1, 2017, pp. 1–12.
[2] J. Ren et al., “Serving at the Edge: A Scalable IoT Architecture Based on Transparent Computing,” IEEE Network, 2017.
[3] L. Yi, J. Li, and Y. Zhang, “Improving the Scalability of Wearable Devices via Transparent Computing Technology,” Computing in Science & Engineering, vol. 19, no. 1, 2016, pp. 29–37.
[4] H. Yin, W. Yang, and G. Wang, “Wireless Multicast for Mobile Transparent Computing.” Proc. 2013 IEEE 10th Int’l. Conf. High Performance Computing and Commun. & 2013 IEEE Int’l. Conf. Embedded and Ubiquitous Computing (HPCC_EUC 2013), 2014, pp. 1884–89.
[5] T. Qiu, R. Qiao, and D. Wu, “EABS: An Event-Aware Backpressure Scheduling Scheme for Emergency Internet of Things,” IEEE Trans. Mobile Computing, vol. PP, no. 99, 2017, pp. 1–1.
[6] M. Cha et al., “I Tube, You Tube, Everybody Tubes: Analyzing the World’s Largest User Generated Content Video System,” Proc. ACM SIGCOMM Conf. Internet Measurement, 2007, pp. 1–14.
[7] J. Ren et al., “Exploiting Mobile Crowdsourcing for Pervasive Cloud Services: Challenges and Solutions,” IEEE Commun. Mag., vol. 53, no. 3, 2015, pp. 98–105.
[8] F. Rebecchi et al., “Data Offloading Techniques in Cellular Networks: A Survey,” IEEE Commun. Surveys & Tutorials, vol. 17, no. 2, 2015, pp. 580–603.
[9] Y. Gao, Y. Zhang, and Y. Zhou, A Cache Management Strategy for Transparent Computing Storage System, Springer, 2013, pp. 651–58.
[10] J. Liu, Y. Zhou, and D. Zhang, “TranSim: A Simulation Framework for Cache-Enabled Transparent Computing Systems,” IEEE Trans. Computers, vol. 65, no. 10, 2016, pp. 3171–83.
[11] Y. Tang, K. Guo, and B. Tian, “A Block-Level Caching Optimization Method for Mobile Transparent Computing,” Peer-to-Peer Networking and Applications, vol. 1, 2017, pp. 1–12.