Random Forest Dynamic Load Balancing Using Hybrid Genetic Algorithm
With ease of internet facilities number of jobs were handle by servers where jobs are of dynamic in nature. Hence dynamic load balancing of the work need to be required. Researcher has proposed number of techniques for this issue but jobs pattern identification for reducing the balancing time is highly required. Hence this paper has developed a model which can adopt dynamic situation by using genetic algorithm and learn the patterns of job requirement as well. For learning random forest learning technique was used which is a combination of job positional decision trees. While dynamic jobs sequences were managed by Teacher Leaning Particle Swarm optimization algorithm. So combination of bith these techniques were termed as RFDLB(Random Forest Dynamic Load Balancing). Experimental work was done on real job sequence dataset where values compared with existing model and results shows that proposed model work better by reducing the makespan by 2.821% while load balancing total completion time was also reduce by 59.31%.