Authors: Mahfuzulhoq Chowdhury
Addresses: Computer Science and Engineering Department, Chittagong University of Engineering and Technology, Chittagong-4349, Bangladesh
Abstract: Wearable devices are very popular nowadays due to their computing and communication abilities. Limited computation, battery, and storage capabilities hinder the growth of emerging latency-sensitive wearable device-based applications. At present, the existing works on wearable computing suffered from higher latency, energy, and user payment due to lack of wearable device users mobility prediction, budget-aware offloading, deadline, resources availability, cooperation, and energy cost awareness. This paper proposes a prediction and budget-aware task offloading for wearable computing by investigating the wearable device users' payment, mobility, cloud, and network resource availability, and task requirements. The effectiveness of the proposed prediction and budget-aware offloading scheme for wearable computing is evaluated by comparing its results with the baseline greedy and independent resource selection scheme. The experimental results demonstrate that our proposed scheme provides a significant performance gain than the compared schemes in terms of makespan delay, user payment, utility, energy cost, and service provider profit.
Keywords: wearable devices; wearable computing; task offloading scheme; user payment and budget; service provider profit.
International Journal of Sensor Networks, 2021 Vol.36 No.4, pp.204 - 215
Received: 03 Oct 2020
Accepted: 07 Jan 2021
Published online: 21 Aug 2021 *