Prerequisite – Genetic Algorithm
SSGA stands for Steady-State Genetic Algorithm. It is steady-state meaning that there are no generations. It differs from the Simple Genetic Algorithm, as in that tournament selection does not replace the selected individuals in the population, and instead of adding the children of the selected parents into the next generation, the two best individuals out of the two parents and two children are added back into the population so that the population size remains constant.
- Generate initial population of size N.
- Evaluate each solutions’ fitness/goodness.
- Select 2 solutions as parents without repetition.
- Do Crossover, Mutation and Inversion and create 2 offsprings.
- If offspring is duplicated, then go to step 3.
- If Not, then evaluate the fitness of offspring.
- If offspring are better than the worst solutions then replace the worst individuals with the offspring such that population size remains constant.
- Check for convergence criteria.
- If convergence criteria are met, then terminate the program else continue with step 3.
- Small Generation Gap.
- Only 2 offspring produced in one generation.
- Generally used for smaller population size N.
- Less computationally expensive compared to Simple GA.
- Population size N remains constant throughout.
- To optimize a wide range of different fit functions which is not solvable using normal hard computing-based algorithms.
- Distributed computer network topologies.
- Learning fuzzy rule base using genetic algorithms.
- In training neural networks using SSGA instead of normal Backprop algorithms and many more.