A Neuro-Fuzzy Hybrid Framework for Augmenting Resources of Mobile Device

Abstract

Due to the drastic exploitation of mobile devices and mobile apps in the day-to-day activities of people, the enhancement in hardware and software tools for mobile devices is also rising rapidly to cater to the requirements of mobile users. However, the progress of resource-intensive mobile applications is still inhibited by the limited battery power, restricted memory, and scarce resources of mobile devices. By employing mobile cloud computing, mobile edge computing, and fog computing, many researchers are providing their frameworks and offloading algorithms to augment the resources of mobile devices. In the existing solutions, offloading resource-intensive tasks is adopted only for specific scenarios and also not supporting the flexible exploitation of IoT-based smart mobile applications. So, a novel neuro-fuzzy modeling framework is proposed to augment the inadequate resources of a mobile device by offloading the resource-intensive tasks to external entities, and also a Bat optimization algorithm is exploited to schedule as many tasks as possible to the augmentation entities thereby improving the total execution time of all tasks and minimizing the resource exploitation of the mobile device. In this research work, external augmentation entities like distant cloud, edge cloud, and microcontroller devices are providing Resource augmentation as a Service (RaaS) to mobile devices. An IoT-based smart transport mobile app is implemented based on the proposed framework which depicts a significant reduction in execution time, energy consumption, bandwidth utilization, and average delay. Performance analysis depicts that the neuro-fuzzy hybrid model with Bat optimization provides a significant improvement compared with proximate computing and web service frameworks on the Quality of Service (QoS) parameters namely energy consumption, execution time, bandwidth utilization, and latency. Thus, the proposed framework exhibits a feasible solution of RaaS to resource-constrained mobile devices by exploiting edge computing.