MR-Edge: a MapReduce-based Protocol for IoT Edge Computing with Resource Constraints
Qian Wang, Brian Lee, Niall Murray, Yuansong Qiao · 2019
Edge computing is proposed to remedy the Cloud-only processing architecture for Internet of Things (IoT) because of the massive amounts of IoT data. The challenge is how to deploy and execute data processing tasks on heterogeneous IoT edge network. As MapReduce is a well-known model in Cloud computing for distributed processing of big data, this paper aims to devise a MapReduce-based protocol to achieve IoT edge computing. Our design is built upon the novel Information Centric Networking (ICN), which supports function naming and forwarding so as to facilitate task distribution among edge devices. To guarantee the correctness of task execution, a tree topology is formed in our approach to establish the logical connection between different types of edge devices, namely processing-capable nodes and forward-only ones. Moreover, the proposed protocol includes a task maintenance scheme that enables the coexistence of multiple IoT computation jobs. A testbed is implemented on ndnSIM to verify the feasibility of our design. The results show our approach could significantly decrease the network traffic compared with centralized data processing.