Abstract
Objective: This study implements a combination of heuristicbased algorithm and finding variable neighborhoods, thereby reducing make-span and improving reliability. Methods/statistical analysis: The bi-objective algorithm is proposed for a static planning strategy to achieve high performance in heterogeneous multiprocessor systems. The reliability of a system is based on the probability in which resources of the system execute tasks without any failure. Findings: Here, a genetic algorithm integrated using single neighborhood structure Genetic Variable Neighbourhood Search (GVNS) is implemented to improve the efficient search quality. Applications and improvements: Simulation is performed to maintain better performance parameters when compared with conventional algorithms. Keywords: Directed Acyclic Graph, Inter Process Communication, Evolutionary Algorithm.
Highlights
Computational requirements today have increased the issues in parallel processing and traditional sequential processing [1,2]
The population in Genetic Variable Neighbourhood Search (GVNS) consists of a group of individuals with each representing a potential solution to the given scheduling
The proposed GVNS achieves a consistent performance for the various parameter sensitive analyses in terms of scheduling priority and achieving a marginal increase in CCR value outperforming the conventional mechanisms
Summary
Computational requirements today have increased the issues in parallel processing and traditional sequential processing [1,2]. The tasks are scheduled in the number of available processors, minimizing the duration of the scheduling length. This proposed work considers dual purpose for scheduling application is to enable efficient execution of applications on scattered heterogeneous systems. This minimizes the duration and reliability of available processors by taking failure rates and processor speed into account. A high failure rate frequency is predicted depending on reliability, when a processor completes the execution of application task as soon as possible. Conventional scheduling mechanisms depend on existing heuristic approach to assign priority for each and every task in an ordered list of scheduled tasks. When the processing capability of processes is fair, the homogeneous multiprocessor systems are considered over heterogeneous systems
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
