A large-scale data collection scheme for distributed Topic-Based Pub/Sub

Abstract

In this paper, we propose a scalable data collection scheme for distributed Topic-Based Pub/Sub (TBPS) messaging that can prevent overloads in network processes in the large-scale IoT applications. Our proposal scheme employs “Collective Store and Forwarding,” which stores and merges multiple small size messages into one large message along a multi-hop tree structure on the structured overlay for TBPS, taking into account the delivery time constraints. This makes it possible to reduce the overhead of network process even when a large number of sensor data is published asynchronously. We also propose a tree construction method for adjusting maximum network process load on nodes called the “Adaptive Data Collection Tree.” Simulation results show that compared to existing schemes, our proposal schemes can reduce a network occupation time by 90% to collect data from 10,000 publishers.