作者: Pablo Munoz , Raquel Barco , Jose Maria Ruiz-Aviles , Isabel de la Bandera , Alejandro Aguilar
关键词: Engineering 、 Fuzzy logic 、 Performance indicator 、 Fuzzy control system 、 Fuzzy rule 、 Reinforcement learning 、 Real-time computing 、 Femtocell 、 Distributed computing 、 Broadband networks 、 Load balancing (computing)
摘要: Mobile-broadband traffic has experienced a large increase over the past few years. Femtocells are envisioned to cope with such demand of capacity in indoor environments. Since those small cells low-cost nodes, thorough deployment is not typically performed, particularly enterprise scenarios. As result, matching between and network resources rarely optimal. In this paper, several load balancing techniques based on self-tuning femtocell parameters designed solve localized congestion problems. particular, these implemented by fuzzy logic controllers (FLC) rule-based reinforcement learning systems (FRLSs). Performance assessment carried out dynamic system-level simulator. Results show that combination FLC FRLS produces an performance significantly higher than if alone. Both response time final value indicators improved.