Optimizing multiple services scheduling in cloud computing using progressive evolution

3^rd International Conference and Business Expo on Wireless & Telecommunication

July 20-21, 2017 Munich, Germany

Amjad Gawanmeh

Concordia University, Canada

Posters & Accepted Abstracts: Int J Sens Netw Data Commun

Abstract :

Cloud concepts have moved enterprise computing from the classical host-based architecture pattern into the elastic computing pattern. While QoS problems in service and cloud based systems have been addressed in the literature, it is believed that green based cloud computing problems have not received as much attention. In particular, when addressing the problem of constrained resource allocation, which is proven to be a difficult problem since it is affected by several parameters, such as assumptions about the services, tasks, subtasks, and communication between servers. The problem of scheduling multiple tasks for multiple users on given number of resources is considered NP complete problem and; therefore, it has been addressed in several research methods, yet, there are still many improvements can be done, since the problem has several optimization parameters and in addition, most proposed solutions are built on top of several assumptions and simplifications. This work proposes a green evolutionary based algorithm for task-oriented resource allocation in cloud computing, where the problem of scheduling multiple users with dependent subtasks on multiple available resources with different execution time and cost is addressed first. The proposed solution is provided by introducing a selection function based on subtasks completion time and task costs. Then, the proposed solution is further enhanced using an evolutionary based method. The proposed method runs in linear time vs. different design parameters. In addition, as compared to existing techniques, is applicable on scheduling problems without any restrictions on the execution time and price, in particular as compared to game theoretic approaches cite{wei2010game}, where the execution time must be given in ascending order, and the price in descending in order to find Nash equilibrium. Finally, the proposed method outputs schedule with better utility than game theoretic one.

Biography :

E-mail: amjad@ece.concordia.ca