Applying fuzzy logic and genetic algorithms to enhance the efficacy of the PID controller in buffer overflow elimination for better channel response timeliness over the Internet

Abstract

SUMMARYIn this paper two novel intelligent buffer overflow controllers: the fuzzy logic controller (FLC) and the genetic algorithm controller (GAC) are proposed. In the FLC the extant algorithmic PID controller (PIDC) model, which combines the proportional (P), derivative (D) and integral (I) control elements, is augmented with fuzzy logic for higher control precision. The fuzzy logic divides the PIDC control domain into finer control regions. Every region is then defined either by a fuzzy rule or a 'don't care' state. The GAC combines the PIDC model with the genetic algorithm, which manipulates the parametric values of the PIDC as genes in a chromosome. The FLC and GAC operations are based on the objective function {0, } 2 . The principle is that the controller should adaptively maintain the safety margin around the chosen reference point (represent by the '0' of {0, } 2 ) at runtime. The preliminary experimental results for the FLC and GAC prototypes indicate that they are both more effective and precise than the PIDC. After repeated timing analyses with the Intel's VTune Performer Analyzer, it was confirmed that the FLC can better support realtime computing than the GAC because of its shorter execution time and faster convergence without any buffer overflow.

Simulation Model of Enhancing Performance of TCP/AQM Networks by Using Matlab

“…Genetic algorithms (GA) are evolutionary algorithms that can be used to improve the performance of TCP networks or other systems [19][20][21]. They are considered an improvement technique to raise the level of efficiency of network systems for this type of work [22][23][24].…”

“…The work depended on FSMC and GAs to control an AQM network to improve computer network performance by providing effective queue management [27]. Some studies have been conducted that simulated the adoption of non-linear systems, which is important in order to improve work performance by using traditional and expert control methods, which enables the researchers to control system behavior and obtain a balance with the changes in the operation of the system [24].…”