mdss-bit.rar_源码

@ DPSO is based on the PSO version by Yuhui SHI. @ Please see the OLD_README before reading this file!!! /==================== Other Information =============================/ Dissipative PSO V1.1 Xiao-Feng Xie, Dec 15, 2001 (last modified) URL: http://www.adaptivebox.net/research/ Difference: add two chaos parameters: Cv, Cl @ Ref: X. F. Xie, W. J. Zhang, Z. L. Yang. A dissipative particle swarm optimization. Congress on Evolutionary Computation (CEC), Hawaii, USA, 2002: 1456-1461 @@Notes: IF Cv=Cl=0, then DPSO==PSO /========================= Usage ============================ To make all the programs you should type -> make all To run it, under command prompt, type in -> dpso *.run @ The *.run file specifies all information required to run the program. There are (you may see the C Program for dedails): /*------Algorithm setting parameters: Total evaluation time = m*(T+1)------------*/ NUMBER_OF_AGENTS: m MAXITER: T weight_up weight_low Cv Cl MAXV /*------Output setting parameters------------*/ run_no Output step of generation results_file_prefix /*------problem setting parameters------------*/ fun_type: 0-Shaffer f6, 1-Sphere, 2-Rosenbrock, 3-generalized Rastrigrin, 4-generalized Griewank DIMENSION MAXX /========================= Examples ============================ * examples in the directory "testfile", All are under m=20, and Dim=10 SF1: SPSO, Inertia weight(0.9 to 0.4) Griewank_LPSO_SF1.RUN Rastrigrin_LPSO_SF1.RUN SF3: DPSO, Inertia weight(0.4), cv=0, cl=0.001 Griewank_DPSO_DP3.RUN Rastrigrin_DPSO_DP3.RUN /========================= Output Information ============================ The output file name will be given in runtime. Each row represents the information of a run. hence the total row number is equal to the parameter "run_no" if it was not interrupted. Each column represents the gbest value at a certain generation number, which the interval is equatio to the parameter "Output step of generation".