PROJECT TITLE :

Automatic Cloud I/O Configurator for I/O Intensive Parallel Applications

ABSTRACT:

As the cloud platform becomes a promising various to ancient HPC (high performance computing) centers or in-house clusters, the I/O bottleneck problem is highlighted in this new surroundings, usually with high-of-the-line compute instances but sub-par communication and that i/O facilities. It has been observed that changing the cloud I/O system configurations, like selections of file systems, variety of I/O servers and their placement methods, etc., can lead to a considerable variation within the performance and price efficiency of I/O intensive parallel applications. But, storage system configuration is tedious and error-prone to try to to manually, even for knowledgeable users, resulting in solutions that are grossly over-provisioned (low cost inefficiency), substantially beneath-performing (poor performance) or, in the worst case, each. This paper proposes ACIC, a system that automatically searches for optimized I/O system configurations from many candidates for every individual application running on a given cloud platform. ACIC takes advantage of machine learning models to perform performance/price predictions. To tackle the high-dimensional parameter exploration house, we have a tendency to enable cheap, reusable, and incremental training on cloud platforms, guided by the Plackett and Burman Matrices for experiment style. Our analysis results with four representative parallel applications indicate that ACIC consistently identifies optimal or near-optimal configurations among a giant group of candidate settings. The top ACIC-counseled configuration is capable of improving the applications’ performance by a factor of up to 10.5 (3.one on average), and cost saving of up to eighty nine % (51 % on average), compared with a commonly used baseline I/O configuration. In addition, we dole out a tiny-scale user study for one amongst the test applications, that found that ACIC consistently beat the user and even the appliance’s developer, usually by a vital margin, in sel- cting optimized configurations.


Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here


PROJECT TITLE :Smart Trailer : Automatic generation of movie trailer using only subtitles - 2018ABSTRACT:With the large growth rate in user-generated videos, it is changing into increasingly important to be able to navigate them
PROJECT TITLE :New Automatic Modulation Classifier Using Cyclic-Spectrum Graphs With Optimal Training Features - 2018ABSTRACT:A new feature-extraction paradigm for graph-based automatic modulation classification is proposed in
PROJECT TITLE :Automatic Modulation Classification Using Moments and Likelihood Maximization - 2018ABSTRACT:Motivated by the fact that moments of the received signal are easy to compute and can give a simple means to automatically
PROJECT TITLE :Automatic Feature Selection Technique for Next Generation Self-Organizing Networks - 2018ABSTRACT:Despite self-organizing networks (SONs) pursue the automation of management tasks in current cellular networks, the
PROJECT TITLE :Automatic Registration of Images With Inconsistent Content Through Line-Support Region Segmentation and Geometrical Outlier Remova - 2018ABSTRACT:The implementation of automatic image registration is still troublesome

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry