Entropy, a new dynamics governing parameter in real time distributed system: a simulation study

Abstract

Interdisciplinary approach is very promising in the modern communication era. An interdisciplinary approach combines more than one discipline and creates something novel that enriches the overall educational experience. This paper is about applying information theoretic concepts of entropy in a real time distributed system (RTDS). Entropy is a very well known concept in thermodynamics, image processing, information theory and many other fields, since utilisation is a very important factor for all real time scheduling algorithms that govern the dynamics of a particular processor. Due to arrival or execution of tasks, the value of this utilisation factor varies, which creates uncertainty in the processor. Therefore, here a calculated entropy value tells the amount of uncertainty present in the particular processor as well as in the entire system. We have calculated entropy (uncertainty) values of the processor in per unit time with the aid of information provided by real time tasks. The resultant graph of these values with respect to time surprisingly ends up showing one-to-one mapping between utilisation and entropy. From these encouraging results, we thought of replacing the utilisation factor with entropy. To the best of our knowledge, this paper is the first that completely implements the role of entropy instead of utilisation in RTDS. After the accomplishment of entropy, based on success ratio, failure ratio, efficiency and tardiness, we compare the performance of the system. Lastly, we acquire similar or healthier results comparatively.

Keywords::

• real time distributed system
• earliest deadline first
• entropy
• task migration
• one-to-one mapping maximum entropy model

Notes

^1. Email: [email protected]

^2. Senior Member, IEEE.

Additional information

Funding

The authors would like to thank Jaypee University of Information Technology for funding the research work.