GSAGA: A hybrid algorithm for task scheduling in cloud infrastructure

Cloud computing is becoming a very popular form of distributed computing, in which digital resources are shared via the Internet. The user is provided with an overview of many available resources. Cloud providers want to get the most out of their resources, and users are inclined to pay less for better performance. Task scheduling is one of the most important aspects of cloud computing. In order to achieve high performance from cloud computing systems, tasks need to be scheduled for processing by appropriate computing resources. The large search space of this issue makes it an NP-hard problem, and more random search methods are required to solve this problem. Multiple solutions have been proposed with several algorithms to solve this problem until now. This paper presents a hybrid algorithm called GSAGA to solve the Task Scheduling Problem (TSP) in cloud computing. Although it has a high ability to search the problem space, the Genetic Algorithm (GA) performs poorly in terms of stability and local search. It is therefore possible to create a stable algorithm by combining the general search capacities of the GA with the Gravitational Search Algorithm (GSA). Our experimental results indicate that the proposed algorithm can solve the problem with higher efficiency compared with the state-of-the-art.

     

Multi-objective hybrid genetic algorithm for task scheduling problem in cloud computing

Neural Computing and Applications - The cloud computing systems are sorts of shared collateral structure which has been in demand from its inception. In these systems, clients are able to access...     

Tribological Characterization of Stir-cast Aluminium-TiB<Subscript>2</Subscript> Metal Matrix Composites

The present study considers friction and wear of aluminium matrix composites reinforced with TiB₂ micro particles processed through the stir casting method rather than in-situ techniques adopted by earlier studies. Different weight percentages of TiB₂ powders having average sizes of 5 - 40 micron were incorporated into molten LM4 aluminium matrix by stir casting method. The friction and wear behavior were studied for Al-TiB₂ composites prepared according to specific dimensions by using a block-on-roller type multi-tribotester at room temperature. Normal loads of 25 - 75 N and rotational speed of 400 – 600 rpm were used for determination of friction and wear behavior. It is found that friction and wear decrease with increase in percentage of TiB₂ reinforcement in the composite, while friction and wear increase with applied load and speed. Scanning electron microscopy studies the reveal presence of both abrasive and adhesive wear mechanisms with abrasive wear being predominant.     

Probabilistic response‐time analysis for real‐time systems in body area sensor networks

Advances in real‐time system and wireless communication have led to the deployment of body area sensor networks (BASNs) for effective real‐time healthcare applications. Real‐time systems in BASNs tend increasingly to be probabilistic and mixed critical to meet stringent requirements on space, weight, and power consumption. Response‐time analysis is an important and challenging task for BASNs to provide some critical services. In this paper, we propose a request‐based compositional probabilistic response‐time analysis framework for probabilistic real‐time task models with fixed‐priority preemptive scheduling in BASNs. In this method, each probabilistic real‐time task is abstracted as a probabilistic request function. Rough response‐time distribution is computed first based on the cumulative request distribution and then exact response‐time distribution is obtained by refinement based on the request increase distribution. Our strategy can effectively improve performance by reducing repetitive computational overhead for the probabilistic response‐time analysis of all tasks in the system. Our evaluation demonstrates that our proposed method significantly outperforms the existing probabilistic response‐time analysis algorithm in terms of analysis duration. Copyright © 2015 John Wiley & Sons, Ltd.