Femtocell Systems With Self Organization Capabilities
In this paper, the authors present a self-organization technique to manage interference in femtocell networks. They model femtocells as a multiagent system implementing a form of Reinforcement Learning (RL) known as Q-Learning (QL) to solve the aggregated interference problem originated due to the macro-femtocell systems coexistence. They discuss this approach and propose a modification in order to solve some of the potential implementation limits of the QL algorithm. In order to achieve a more accurate environment representation and therefore a more appropriate femtocell system behavior, they combine Fuzzy logic with QL, in the form of Fuzzy Q-Learning (FQL), which allows agents to represent continuously the state and action spaces.