Adaptive fuzzy flow rate control considering multifractal traffic modeling and 5G communications

Area of Science:

• Telecommunications Engineering
• Network Flow Control
• Fuzzy Logic Systems

Background:

• 5G networks require advanced flow control to manage traffic efficiently.
• Predictive models are crucial for optimizing performance in dynamic network environments.
• Existing control schemes may not adequately address delay minimization and Quality of Service (QoS) guarantees.

Purpose of the Study:

• To propose a predictive Generalized Orthonormal Basis Functions-Fuzzy (GOBF-Fuzzy) flow control scheme for 5G downlinks.
• To optimize traffic source rates for minimizing data delay and ensuring minimum user traffic rates.
• To enhance system downlink performance and guarantee QoS parameters.

Main Methods:

• Derivation of an optimal control rate expression for traffic sources.
• Application of an adaptive GOBF-Fuzzy model to predict queueing behavior.
• Multifractal modeling to obtain orthonormal basis functions for traffic flows.
• Integration of these functions into a fuzzy model trained with the Least Mean Square (LMS) adaptive algorithm.
• Simulations using a Filtered Orthogonal Frequency Division Multiplexing (F-OFDM) based 5G Downlink.

Main Results:

• The proposed adaptive GOBF-Fuzzy control scheme effectively predicts queueing behavior in 5G systems.
• Simulations demonstrate significant enhancement in 5G downlink performance.
• The algorithm successfully guarantees essential Quality of Service (QoS) parameters.

Conclusions:

• The adaptive GOBF-Fuzzy flow control scheme is efficient for 5G downlinks.
• The proposed method improves system performance by minimizing data delay and ensuring QoS.
• This approach offers a robust solution for traffic management in next-generation wireless networks.