An Adaptive Offloading Mechanism for Mobile Cloud Computing: A Niching Genetic Algorithm Perspective

Mohammed S. Zalat

doi:10.1109/ACCESS.2022.3192391

An Adaptive Offloading Mechanism for Mobile Cloud Computing: A Niching Genetic Algorithm Perspective

2022-01-01

2

OA

AI

DOI：10.1109/ACCESS.2022.3192391

Original

Original request for help

Save

Abstract

En

The fast evolution of mobile applications demonstrates the growing need for more resources and processing power on mobile devices. Mobile Cloud Computing (MCC) combines cloud computing with mobile devices, enabling sophisticated and resource-intensive applications to operate on mobile devices regardless of their performance limits (e.g., battery life, memory utilization, and computation). Overcoming these constraints is accomplished using a well-known technique called computation offloading, which entails offloading heavy processing to resourceful servers and getting the results from these servers. Many studies have been done on mobile code offloading, with the goal of avoiding the stated limits and reducing execution time or battery consumption through single- or multiple-site offloading, so that people can use their phones and tablets more. However, the majority of existing techniques make offloading choices based on profile data, which implies a stable network environment and forces an object to be offloaded to the same site. As a consequence of these challenges, this research proposes a novel strategy for enhancing the multisite offloading mechanism by combining a Niching Genetic Algorithm (NGA) with a Markov Decision Process (MDP). MDP is used to determine the most optimal location for each application's modules to be executed. GA was used to determine the optimal transition probability for components operating on several sites. To aid in initial population selection, the proposed model employs a niche model in the form of a context-based clearing (CBC) technique to improve the variability of the genes inside the chromosome in order to minimize their association. The simulation results reveal that the proposed technique consumes little power and executes quickly while determining the optimal offloading decision with lower generation numbers.

Keywords:

Mobile handsets

Cloud computing

Task analysis

Servers

Genetic algorithms

Costs

Performance evaluation

Mobile cloud computing

offloading

niching genetic algorithm

Markov decision process

An Adaptive Offloading Mechanism for Mobile Cloud Computing: A Niching Genetic Algorithm Perspective

Abstract

Journal

Organization

Cited Papers