Performance Evaluation of VDSL Network with Fuzzy Control Policing Mechanisms

Fuzzy control is based on fuzzy logic, which provides a most efficient way to handle inexact information as a basis of reasoning. With fuzzy logic it is possible to convert knowledge, which is expressed in an uncertain form, to an exact and precise output for uncertain systems. In fuzzy control, the controller can be simply represented by if-then-else rules. The interpretation of the controller is fuzzy but the controller will process an input-data then produce an exact output-data in a deterministic way. However, traditional policing mechanisms have proved to be inefficient in coping with the conflicting requirements of ideal policing mechanisms, that is, low dropping frames and high conforming frames due to the adjustment of unpredictable input data rates. This will lead us to explore alternative solutions based on artificial intelligence techniques, specifically, in the field of fuzzy systems. In this paper, we propose a fuzzy logic to control policing mechanisms that aim at detecting violations of negotiated parameters such as input data rates, token rates and etc. We evaluate and compare the performance of the three fuzzy logic control policing mechanisms, namely: Fuzzy Leaky Bucket (FLB), Fuzzy Jumping Window (FJW) and Fuzzy Triggered Jumping Window (FTJW) with conventional policing mechanisms, namely: Leaky Bucket(LB), Jumping Window(JW) and Triggered Jumping Window (TJW). Simulation results show that on VDSL frames, the fuzzy logic control scheme help improve performance of our fuzzy control policing mechanisms much better than conventional policing ones while various types of burst/silence traffic are employed