An Adaptive Solution for Congestion Control in CoAP-based Group Communications

Abstract

Abstract-The use of lightweight devices and constrained resources like Wireless Sensors Network (WSN) makes patterns traffic in the Internet of Things (IoT) different from the ones in conventional networks. One of the most emerging messaging protocols used to address the needs of these lightweight IoT nodes is Constrained Application Protocol (CoAP). CoAP presents a lot of advantages compared to other IoT application layer protocols; it ensures group communication via multicast communications between a server and multiple clients. Nevertheless, it doesn't support a group communication from a client to multiple servers; it relies on multiple unicasts to do so. Regarding the fact that these constrained devices communicate via a large amount of messages and notifications, network congestion occurs. This paper proposes an adaptive congestion control algorithm designed for group communications using unicast between a client and multiple servers. Simulated results show that the proposed mechanism can appropriately achieve higher performances in terms of response time and packet loss.

Congestion Control in CoAP Observe Group Communication

“…Generally, there are two communication patterns, both CoAP-based and Observing Resource (Obs), which are considered as one-to-one communication [9]. Since a variety of application domains require data from IoT devices, data communication between a sender and a receiver is essential, contributing to the emergence of group communication [10,11,12,13]. At the same time, congestion control for group communication has also been developed as a crucial communication platform for networks with a large number of sensor nodes [14,15,16,17,18].…”

An approximation delay between consecutive requests for congestion control in unicast CoAP-based group communication

“…A paper by Quakasse et al [9] proposes a way to solve network congestion in CoAP by improving the delay and adapt the behavior of the solution to network conditions. The paper also suggests the use of delays between unicast requests depending on the link delay and the estimated group size.…”