A self-adaptive routing paradigm for wireless mesh networks based on reinforcement learning
| Autor: | Marco Conti, Maddalena Nurchis, Raffaele Bruno, Luciano Lenzini |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2011 |
| Předmět: |
Static routing
Zone Routing Protocol Dynamic Source Routing business.industry Computer science Distributed computing Enhanced Interior Gateway Routing Protocol Policy-based routing Wireless Routing Protocol Link-state routing protocol Multipath routing Opportunistic routing performance evaluation reinforcement learning business Computer network |
| Zdroj: | 14th International Symposium on Modeling Analysis and Simulation of Wireless and Mobile Systems (MSWiM 2011), pp. 197–204, Miami, Florida, USA, October 31-November 4, 2011 info:cnr-pdr/source/autori:Nurchis M. [1], Bruno R. [1], Conti M. [1], Lenzini L. [2]/congresso_nome:14th International Symposium on Modeling Analysis and Simulation of Wireless and Mobile Systems (MSWiM 2011)/congresso_luogo:Miami, Florida, USA/congresso_data:October 31-November 4, 2011/anno:2011/pagina_da:197/pagina_a:204/intervallo_pagine:197–204 MSWiM |
| DOI: | 10.1145/2068897.2068932 |
| Popis: | Classical routing protocols for WMNs are typically designed to achieve specific target objectives (e.g., maximum throughput), and they offer very limited flexibility. As a consequence, more intelligent and adaptive mesh networking solutions are needed to obtain high performance in diverse network conditions. To this end, we propose a reinforcement learning-based routing framework that allows each mesh device to dynamically select at run time a routing protocol from a pre-defined set of routing options, which provides the best performance. The most salient advantages of our solution are: i) it can maximize routing performance considering different optimization goals, ii) it relies on a compact representation of the network state and it does not need any model of its evolution, and iii) it efficiently applies Q-learning methods to guarantee convergence of the routing decision process. Through extensive ns-2 simulations we show the superior performance of the proposed routing approach in comparison with two alternative routing schemes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|