88Sheer volumes of data, now frequently termed as “big data,” are being generated from various emerging applications of large-scale simulations, scientific experiments, and global-scale communications. Such extremely large amounts of data are normally generated at one data center and then need to be transferred to distributed data centers for data storage and analysis, within which fast, predictable, and reliable data transfer with guaranteed performance has become crucial to ensure success. Fortunately, reserving bandwidth as needed along selected paths in high-performance networks (HPNs) has proved to be an effective way to satisfy the requirements of such high-demanding data transfer. In this chapter, we first present the introduction and background of bandwidth reservation service in HPNs for big data transfer along with the challenges. The related works, and concepts and mechanisms of bandwidth reservation strategies are provided in Section 5.2 and Section 5.3, respectively. We show our algorithm’s design and illustration through simple examples for easy comprehension in Section 5.4, and conclude our work in Section 5.5.
|Title of host publication||Big Data and Computational Intelligence in Networking|
|Number of pages||20|
|State||Published - 1 Jan 2017|