Research Article
TCP Cubic Implementation in the OMNeT++ INET Framework for SIoT Simulation Scenarios
@INPROCEEDINGS{10.1007/978-3-031-54521-4_2, author={Ioannis Angelis and Athanasios Tsipis and Eleni Christopoulou and Konstantinos Oikonomou}, title={TCP Cubic Implementation in the OMNeT++ INET Framework for SIoT Simulation Scenarios}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part I}, proceedings_a={COLLABORATECOM}, year={2024}, month={2}, keywords={INET Framework Network Simulation OMNeT++ SIoT Satellite Communication TCP Cubic}, doi={10.1007/978-3-031-54521-4_2} }- Ioannis Angelis
Athanasios Tsipis
Eleni Christopoulou
Konstantinos Oikonomou
Year: 2024
TCP Cubic Implementation in the OMNeT++ INET Framework for SIoT Simulation Scenarios
COLLABORATECOM
Springer
DOI: 10.1007/978-3-031-54521-4_2
Abstract
TCP is a well-known protocol for reliable data transfer. Although TCP was originally designed for networks with low Round Trip Time (RTT) and low error rates over the communication channel, in modern networks these characteristics vary drastically, e.g., Long Fat Networks are usually attributed a high Bandwidth Delay Product. When considering satellite communications, which are also characterized by high error rates but are considered a driving force for future networks, such as the Satellite Internet of Things (SIoT), it becomes clear that there exists an ever-growing need to revisit TCP protocol variants and develop new tools to simulate their behavior and optimize their performance. In this paper, a TCP Cubic implementation for the OMNeT++ INET Framework is presented and made publicly available to the research community. Simulation experiments validate its expected behavior in accordance with the theoretical analysis. A performance comparison against the popular TCP NewReno is also performed to evaluate TCP Cubic’s applicability to satellite environments. The obtained results testify to the latter’s superiority in efficiently allocating the bandwidth among the different information flows with vast gains to the overall system throughput, thus, rendering it the better candidate for future SIoT environments.
