Dynamic traffic steering based on fuzzy Q-Learning approach in a multi-RAT multi-layer wireless network

摘要: The infrastructure of current cellular networks must evolve to cope with the increasing demand for mobile-broadband services. Heterogeneous are an attractive solution operators expand network capacity, based on deploying different Radio Access Technologies, cell sizes and carrier frequencies in same environment. As a result, gain flexibility distribute traffic across (or layers) order make more efficient use resources enhance performance. In this work, dynamic steering technique multi-RAT multi-layer wireless is proposed. particular, fuzzy rule-based reinforcement learning algorithm modifies handover parameters according specific policy set by operator, which typically searches trade-off between key performance indicators. Results show that proposed optimization provides good support policies simply adjusting some weighting factors. addition, Q-Learning shown as effective adapt context variations, such those produced user spatial distribution.