The growing popularity of small cost-effective satellites (SmallSats, CubeSats, etc.) creates the potential for a variety of new science applications involving multiple nodes functioning together to achieve a task, such as swarms and constellations. As this technology develops and is deployed for missions in Low Earth Orbit and beyond, the use of delay tolerant networking (DTN) techniques may improve communication capabilities within the network. In this paper, a network hierarchy is developed from heterogeneous networks of SmallSats, surface vehicles, relay satellites and ground stations which form an integrated network. There is a trade-off between complexity, flexibility, and scalability of user defined schedules versus autonomous routing as the number of nodes in the network increases. To address these issues, this work proposes a machine learning classifier based on DTN routing metrics. A framework is developed which will allow for the use of several categories of machine learning algorithms (decision tree, random forest, and deep learning) to be applied to a dataset of historical network statistics, which allows for the evaluation of algorithm complexity versus performance to be explored. We develop the emulation of a hierarchical network, consisting of tens of nodes which form a cognitive network architecture. CORE (Common Open Research Emulator) is used to emulate the network using bundle protocol and DTN IP neighbor discovery.
Evaluation of Classifier Complexity for Delay Tolerant Network Routing
2019-06-01
1576603 byte
Conference paper
Electronic Resource
English
A comparative study on delay-tolerant network routing protocols
Emerald Group Publishing | 2020
|Connection Time for Routing Decisions in Vehicular Delay Tolerant Network
British Library Conference Proceedings | 2019
|Multi-domain routing in Delay Tolerant Networks
IEEE | 2024
|A Delay-Tolerant Network Routing Based on Probability of Relay and Social Network Analysis
British Library Online Contents | 2016
|