5th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications

Research Article

Learning from experts in cognitive radio networks: The docitive paradigm

Download160 downloads
  • @INPROCEEDINGS{10.4108/ICST.CROWNCOM2010.9173,
        author={Ana Galindo-Serrano and Lorenza Giupponi and Pol Blasco and Mischa Dohler},
        title={Learning from experts in cognitive radio networks: The docitive paradigm},
        proceedings={5th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications},
        publisher={IEEE},
        proceedings_a={CROWNCOM},
        year={2010},
        month={9},
        keywords={Cognitive radio  aggregated interference  decentralized Q-learning  docitive learning  multiagent system},
        doi={10.4108/ICST.CROWNCOM2010.9173}
    }
    
  • Ana Galindo-Serrano
    Lorenza Giupponi
    Pol Blasco
    Mischa Dohler
    Year: 2010
    Learning from experts in cognitive radio networks: The docitive paradigm
    CROWNCOM
    IEEE
    DOI: 10.4108/ICST.CROWNCOM2010.9173
Ana Galindo-Serrano1,*, Lorenza Giupponi1, Pol Blasco1, Mischa Dohler1
  • 1: Centre Tecnològic de Telecomunicacions de Catalunya (CTTC), Parc Mediterrani de la Tecnologia, Av. Carl Friedrich Gauss 7, Barcelona, Spain
*Contact email: ana.maria.galindo@cttc.es

Abstract

In this paper we introduce the novel paradigm of docition for cognitive radio (CR) networks. We consider that the CRs are intelligent radios implementing a learning process through which they interact with the surrounding environment to make self-adaptive decisions. However, in distributed settings the learning may be complex and slow, due to interactive decision making processes, which results in a non-stationary environment. The docitive paradigm proposes a timely solution based on knowledge sharing, which allows CRs to develop new capacities for selecting actions. We demonstrate that this improves the CRs' learning ability and accuracy, and gives them strategies for action selection in unvisited states. We evaluate the docitive paradigm in the context of a secondary system modeled as a multi-agent system, where the agents are IEEE 802.22 CR base stations, implementing a real-time multi-agent reinforcement learning technique known as decentralized Q-learning. Our goal is to solve the aggregated interference problem generated by multiple CR systems at the receivers of a primary system. We propose three different docitive algorithms and we show their superiority to the well know paradigm of independent learning in terms of speed of convergence and precision.