Improving Architectural Reusability for Resource Allocation Framework in Futuristic Cloud Computing Using Decision Tree Based Multi-objective Automated Approach

Godhrawala, Husain; Sridaran, R.

doi:10.1007/978-3-031-23092-9_32

Cited by 7 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike previous methods, our approach uses neural networks to choose jobs for scheduling using genetic algorithms. It dynamically modifies resource allocation parameters for optimal utilization, adapting flexibly to changing cloud computing environments [11]. Additional research is required to ensure that jobs are allocated to cloud resources in an efficient manner, ultimately improving the quality of service criteria and respecting service levels [12].…”

Section: Introductionmentioning

confidence: 99%

Revolutionizing Cloud-Based Task Scheduling: A Novel Hybrid Algorithm for Optimal Resource Allocation and Efficiency in Contemporary Networked Systems

Mittal,

Kumar,

Sharma

2024

IJCDS

View full text Add to dashboard Cite

The need for cloud computing has increased in the age of contemporary networked systems, driving the pursuit of optimal resource allocation and data processing. It is imperative in essential fields where security, such as transportation systems, depends on computing performance. Even after much research has been done on managing resources in cloud computing, finding algorithms that maximize job completion, minimize costs, and maximize resource consumption has remained a top priority. However, existing techniques have shown limitations, which calls for new ways. Our work shows the novel hybrid approach that has the potential to change the game completely. The Neural Network Task Classification (N2TC) is the result of merging neural networks with genetic algorithms. This ground-breaking method skillfully applies the Genetic Algorithm Task Assignment (GATA) for resource allocation while utilizing neural networks for task categorization. Notably, our algorithm carefully considers execution time, response time, costs, and system efficiency to promote fairness, a defense against resource scarcity. Our method achieves a remarkable 13.3% cost reduction, a stunning 12.1% increase in response time, and a 3.2% increase in execution time. These strong indicators act as a wake-up call, announcing our hybrid algorithm's power and revolutionary potential in transforming the paradigms around cloud-based task scheduling. This work represents a turning point in cloud computing, demonstrating an innovative combination of algorithms that not only overcomes current constraints but also ushers in a new era of efficacy and efficiency with far-reaching implications outside the domain of transportation systems.

show abstract

Section: Introductionmentioning

confidence: 99%