Optimized task scheduling for cost-latency trade-off in mobile fog computing using fuzzy analytical hierarchy process

Mobile Fog Computing (MFC) paradigm can be integrated as a unit called as Multi-Access Edge Computing (MFC) in a fifth-generation (5G) network. There are extensive researches coercing to the MFC. Task scheduling is an important issue in the area of MFC to solve computing capacities such as limited CPU power, storage capacity, memory constraints, and limited battery life in Mobile Devices (MDs). The multi-criteria decision making problem in fog nodes has not been widely studied. According to the variety and difficulty of criteria, the scheduling in the fog node has become a challenge. The previous works in the tasks scheduling context considered a few criteria of dynamic scheduling without covering other enough criteria. Besides, in MFC, the tasks come with different priorities. We present a scheduling algorithm based on the Priority Queue, Fuzzy and Analytical Hierarchy Process namely PQFAHP in our paper. We use PQFAHP to combine several priorities and prioritize multi-criteria. In our paper, dynamic scheduling includes the completion time, energy consumption, RAM, and deadline criteria. Our experimental results show that the proposed algorithm can consider multi criteria for scheduling Our proposed work is one of the multi-criteria algorithms that performs optimal results than several benchmark algorithms in terms of waiting time, delay, service level, mean response time, and the number of scheduled tasks on the MFC side. This paper has considerable contributions related to the scheduling of fog computing. For instance, it could decrease 14.2%, 49%, and 26% in average waiting time, delay, and energy consumption respectively, and increase 10.8% in service level.

Automated summary

This paper proposes a scheduling algorithm based on Priority Queue, Fuzzy and Analytical Hierarchy Process for multi-criteria task scheduling in mobile fog computing. Experimental results show that the proposed algorithm achieves better results in multiple criteria.