Summarization in Semantic Based Service Discovery in Dynamic IoT-Edge Networks

TL;DR

This paper introduces a decentralized, ontology-based semantic routing protocol for IoT networks that reduces memory and network traffic by summarizing capabilities, enabling efficient device discovery and composition.

Contribution

It presents a novel ontology-based summarization and coding scheme for semantic routing in IoT, supporting adaptive compression and bounded routing table sizes.

Findings

Significantly reduces routing table size and network traffic.

Supports efficient IoT capability lookup in resource-constrained devices.

Outperforms existing semantic routing algorithms in experiments.

Abstract

In the last decade, many semantic-based routing protocols had been designed for peer-to-peer systems. However, they are not suitable for IoT systems, mainly due to their high demands in memory and computing power which are not available in many IoT devices. In this paper, we develop a semantic-based routing protocol for dynamic IoT systems to facilitate dynamic IoT capability discovery and composition. Our protocol is a fully decentralized routing protocol. To reduce the space requirement for routing, each node maintains a summarized routing table. We design an ontology-based summarization algorithm to smartly group similar capabilities in the routing tables and support adaptive routing table compression. We also design an ontology coding scheme to code keywords used in the routing tables and query messages. To complete the summarization scheme, we consider the metrics for choosing the summarization candidates in an overflowing routing table. Some of these metrics are novel and are difficult to measure, such as coverage and stability. Our solutions significantly reduce the routing table size, ensuring that the routing table size can be bounded by the available memory of the IoT devices, while supporting efficient IoT capability lookup. Experimental results show that our approach can yield significantly lower network traffic and memory requirement for IoT capability lookup when compared with existing semantic-based routing algorithms including a centralized solution, a DHT-based approach, a controlled flooding scheme, and a cache-based solution.