Parallel Fuzzy Logic Controller Implementation Using MPICH2

Abstract

In this work FLC program is implemented using C++ codes. Two implementations are presented one with the rules stored inside the program, the other with rules in a rulebase file. The execution times of these two implementations, along with MATLAB FLC implementation, are compared using different simulated FLCs. Furthermore, to reduce the rulebase searching time, a parallel FLC is implemented using C++ and MPI (Message Passing Interface). The MPICH2 package is used to run the parallel FLC. A cluster of four computers is used as the parallel environment. The execution time of this FLC program is evaluated using servomotor, Anti Skid System, and other simulated applications. The speedup and efficiency are studied using different number of computers. The results show that decomposing the rulebase searching operation to more than a computer reduce the execution time significantly.