To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Theories of Real Time Stream Processing Architecture Using Task Forking Model |
|
Author |
Shiladitya Munshi, Sajal Saha, Radha Tamal Goswami |
| Citation |
Vol. 26 No. 3 pp. 120-132 |
|
Abstract |
In this work the theoretical aspects of stream processing and their impacts on real-time stream computing architecture are reported. Current study discusses the architecture as a complex directed graph model with various types of spouts, bolts and stream tuples than a non-real time stream processing architecture counterpart like Apache Storm. Stream processing performance issues in the real time stream computing architecture have been improved by optimizing time deadline management through task forking models. While a set of algorithms for optimization of task processing has been reported, the performance metrics of the architecture has also been identified and analyzed on the basis of queuing theories by expressing it through appropriate Kendalls notation. Experimental results, at the end, report considerable improvement of performance of the architecture by applying optimization algorithms on a standard dataset. |
|
Keywords |
Stream Processing, Real Time Processing, Task Forking Model, Queuing Theory, Kendalls Notation |
|
URL |
