Coordinate-based efficient indexing mechanism for intelligent IoT systems in heterogeneous edge computing

Powered by edge servers (also called as edge nodes) which are close to the data source, distributed edge AI processes the huge amounts of data generated by Internet of Things (IoT) devices, extracting value for users. In edge computing, massive data are stored in several distributed edge nodes with heterogeneous capabilities. Intelligent applications running on one edge node may need data from other edge nodes. An efficient data indexing mechanism can rapidly locate the edge node where the data is kept, supporting latency-sensitive intelligent applications. The existing indexing methods in edge computing assume that all edge nodes are the same in capability and the number of edge nodes is constant. This paper proposes CREIM, a coordinate-based efficient indexing mechanism for intelligent IoT systems in heterogeneous edge computing. CREIM achieves fair load balancing on edge nodes with heterogeneous capabilities. The indexing mechanism deals well with the horizontal scaling of edge nodes. Besides, CREIM addresses a fast lookup with one overlay hop, providing low latency data retrieval for edge intelligent applications. In the experiments, CREIM is applied in a realistic network simulated by the mininet and the routing forwarding is supported by the P4 switch. The experiments are constructed by combining real location datasets of Shanghai Telecoms base stations with the real-collected requests of end-devices. The experimental results demonstrate that CREIM achieves a near-optimal latency of index-lookup, adapts the heterogeneous capabilities among edge nodes and reduces the cost of increasing/decreasing edge nodes by 56.36% compared with the state-of-the-art method.