czeslavo / gwo

Grey Wolf Optimizer (+ PSO for comparison) algorithm implementation in C++ with Python bindings

Grey Wolf Optimizer (GWO) C++ implementation with Python bindings

Structure

• optimization/ - implementation and python bindings
• benchmark/ - python code using the bindings, producing data for benchmarking
• parpers/ - original paper on GWO

Usage

You can go directly to benchmark directory and execute: make run

It will compile optimization.so shared library (with python bindings) and run python script, which imports the aforementioned library (module). Results of the execution will be present in data/ and bests/ directories.

gwo's Issues

float rand r1 and r2

Possible issue on gwo/optimization/grey_wolf_optimizer.cpp lines 97, 107, 117

I believe this

double r1 = get_random(0., 1.);
double r2 = get_random(0., 1.);

double A1 = 2. * a * r1 - a;
double C1 = calculate_c(calc_type_c, r1, iteration, max_number_of_iterations); 

should be

double r1 = get_random(0., 1.);
double r2 = get_random(0., 1.);

double A1 = 2. * a * r1 - a;
double C1 = calculate_c(calc_type_c, r2, iteration, max_number_of_iterations); 

I recommend an open-source C++ benchmarking framework for single-objective evolutionary optimization algorithms. You can find it at https://github.com/yangyongkang2000/SEvoBench.