Priority-Aware Bulk Data Transfer in Low-power IoT Networks

With the remarkable development of the Internet of Things (IoT), the computation demands from IoT networks are explosively increasing. Due to the lack of computing resources, edge computing has recently become a good choice for enhancing the IoT performance, where the IoT devices can offload their tasks to the edge server nodes. In this framework, task offloading directly impacts the latency of IoT tasks. Bulk data transfer is one of the most important modules in task offloading, of which the performance can be easily degraded by the unreliable wireless links of the IoT devices. However, the existing works either under-utilize the spectrum or cannot guarantee the multi-task priorities. To achieve a good trade-off between the transmission efficiency and multi-task priorities, in this paper, we propose a priorityguaranteed and rapid approach for bulk data transfer. By considering link qualities and priorities in the organization of the transfer buffer, we can 1) fully exploit the wireless spectrum and 2) strictly guarantee the multi-task priorities. We conduct simulation experiments and compared the performance with the state-of-the-art works. The results show that our work improves the transmission efficiency while guaranteeing the multi-task priorities.