Performance Evaluation of AI Based Load Balancing Algorithm (Reinforcement Learning) with other load balancing algorithms in a JPPF Grid: E.coli Genome Sequence Alignment Problem

Recent development of computational analysis in the field of genomics and proteomics has necessitated the use of high performance computing architectures such as grid, cluster and parallel computing. In this paper an attempt has been made to study the performance enhancement by optimization of various Load Balancing Algorithms (LBAs) and E.coli genome sequence alignment (using PAM 120 substitution matrix) was performed on the grid. We have achieved a performance gain of 11.72 times with just 8 processing nodes in comparison to serial execution time using artificial intelligence based LBA parameter optimization.