Optimized Cloud Based Scheduling | springerprofessional.de

Springer Professional

nach oben

2018 | Buch

Kapitel lesen Erstes Kapitel lesen

Optimized Cloud Based Scheduling

verfasst von: Rong Kun Jason Tan, John A. Leong, Prof. Amandeep S. Sidhu

Verlag: Springer International Publishing

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book presents an improved design for service provisioning and allocation models that are validated through running genome sequence assembly tasks in a hybrid cloud environment. It proposes approaches for addressing scheduling and performance issues in big data analytics and showcases new algorithms for hybrid cloud scheduling. Scientific sectors such as bioinformatics, astronomy, high-energy physics, and Earth science are generating a tremendous flow of data, commonly known as big data. In the context of growing demand for big data analytics, cloud computing offers an ideal platform for processing big data tasks due to its flexible scalability and adaptability. However, there are numerous problems associated with the current service provisioning and allocation models, such as inefficient scheduling algorithms, overloaded memory overheads, excessive node delays and improper error handling of tasks, all of which need to be addressed to enhance the performance of big data analytics.

Anzeige

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

Recent research has noted several trends in IT. First, there has been an increased application of IT across many sectors [1].

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 2. Background

Abstract

When measuring large data volumes and computations, working in the region of petabytes and petaflops is considered working in petascale (10¹⁵). Supercomputers achieved the feat of being able to compute at a petaflop in 2007, as listed in the Top500 List which ranks and keeps track of the 500 fastest computers annually [45].

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 3. Benchmarking

Abstract

Three public clouds was benchmarked which are Microsoft Azure, Amazon EC2 and the Australian National eResearch Collaboration Tools and Resources (NECTAR). NECTAR is an Australian Government project to provide public cloud resources to Australian Universities. The other player of choice among both Industry and Academic Institutions is Amazon Public Cloud or commonly known as Amazon EC2 which is a subsidiary of retail giant Amazon.com. The main reason the Amazon EC2 is popular with both academia and industry is because Amazon was an early pioneer in providing public cloud services. Compared to both NECTAR and Amazon Public Cloud, Microsoft Azure is a relative newcomer only starting to provide its services in 2012.

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 4. Computation of Large Datasets

Abstract

With our solution, existing IT solutions of enterprises can be integrated with the cloud hence increasing the breadth of applications supported and improving performance with reduced additional overhead since additional storage and computing power become easily available on demand. This capability will be demonstrated by the prototype created at the end of the project.

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 5. Optimized Online Scheduling Algorithms

Abstract

However, all algorithms mentioned in Chap. 2 are considered as concurrent processing but not parallel processing and all are suitable to handle non-data intensive applications in cloud environment as all are considered as complex algorithm which consumes relatively high amount of memory, bandwidth and computational power to maintain its data structure. The outcome of maintaining these data structures will cause the time of scheduling tasks unbounded and make loss in profit gains. Undeniably, profit gain by IaaS provider is inversely proportional to time consumed to finish a task. To encounter most of the aspects and issues which are mentioned in Chap. 3, this project propose an online scheduling algorithm is to overcome the various excessive overheads during process while maintaining service performance and comparable least time consuming approach for data intensive task to adapt in the future cloud system.

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 6. Performance Evaluation

Abstract

This chapter presents the evaluation of the proposed algorithms to verify the effectiveness. Thus, first analyse the time complexity of or proposed algorithms and present the experimental results.

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Chapter 7. Conclusion and Future Works

Abstract

Recent technological advancement have emerged the data intensive tasks in wide distinctive areas such as commerce, earth science, astronomy, computational biology and others in boosting trend. Due to the various characteristics of data, it is needed to develop a new data processing architecture for data acquisition, data analysis, data mining, data transmission between service instances, data storage and others, aiming to schedule it into a series of scalable tasks with holistic, viable and modern approach.

Rong Kun Jason Tan, John A. Leong, Amandeep S. Sidhu

Backmatter

Titel: Optimized Cloud Based Scheduling
verfasst von: Rong Kun Jason Tan
John A. Leong
Prof. Amandeep S. Sidhu
Copyright-Jahr: 2018
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-73214-5
Print ISBN: 978-3-319-73212-1
DOI: https://doi.org/10.1007/978-3-319-73214-5

Premium Partner