Name
Title | ||
|---|---|---|
Transfer Learning: A Paradigm for Dynamic Spectrum and Topology Management in Flexible Architectures |
Abstract | ||
|---|---|---|
In this paper, we introduce a novel paradigm of transfer learning for spectrum and topology management in a rapidly deployable opportunistic network for the post disaster and temporary event scenarios. The network architecture is designed to be rapidly changing between different disaster phases, and highly flexible during the temporary event period. Transfer learning is developed to learn the dynamic radio environment from network topologies. This also allows previously learnt information in earlier phases of a deployment to be efficiently used to influence the learning process in later phases of a deployment. A Transfer Learning strategy is designed to change the knowledge base from the most recent phase via multi-agent coordination. We evaluate transfer learning paradigm in a small cell Terrestrial eNB architecture, integrated with Q-Learning and Linear Reinforcement Learning. It is demonstrated that transfer learning significantly improves the initial performance, the convergence speed and the steady state QoS, by exchanging topology information for resource prioritization. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/VTCFall.2013.6692444 | VTC Fall |
Keywords | Field | DocType |
q-learning,reinforcement learning,resource prioritization,opportunistic network,quality of service,disasters,multiagent coordination,network topology,telecommunication network topology,steady state qos,multi-agent systems,radio spectrum management,transfer learning,spectrum management,disaster,cell terrestrial enb architecture,dynamic radio environment,topology information,topology management,dynamic spectrum,network architecture,flexible architectures,multi agent systems | Logical topology,Computer science,Transfer of learning,Computer network,Quality of service,Network architecture,Multi-agent system,Network topology,Knowledge base,Distributed computing,Reinforcement learning | Conference |
ISSN | Citations | PageRank |
1090-3038 | 5 | 0.50 |
References | Authors | |
4 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qiyang Zhao | 1 | 50 | 6.99 |
| Tao Jiang | 2 | 57 | 5.24 |
| Nils Morozs | 3 | 55 | 7.98 |
| David Grace | 4 | 281 | 35.65 |
| Tim Clarke | 5 | 102 | 20.02 |