Task Scheduling Based on Priority and Resource Allocation in Multi-User Multi-Task Mobile Edge Computing System

Traditional cellular networks are unable to support the delay sensitive applications (e.g. vehicular networks, augmented reality). To cope with these challenges, mobile Edge Computing (MEC) has emerged as a new paradigm with computing capabilities in close proximity to the edge of wireless cellular network. In this paper, we study resource allocation for a multi-user multi-task (MUMT) MEC system based on orthogonal frequency-division multiple access (OFDMA). Each computation task is independent with different priorities. In this regard, we propose a priority based task scheduling policy and jointly optimize the computation and communication resource allocation, so as to maximize profit of mobile network operator (MNO) while satisfying the users quality of service (QoS), power consumption at user and base station (BS), and service rate allocation. Building on the proposed model, we develop an innovative framework to improve the MEC performance, by jointly optimizing the service rate, transmit power and subcarrier allocation under satisfying maximum power and service rate, and delay constraints. Our proposed algorithms are finally verified by numerical results which show that the proposed approach outperforms other benchmark schemes. For example, in the Priority queuing schemes, the performance can be improved compared to No-priority queuing.