Abstract
Shuffled Frog-Leaping Algorithm (SFLA) is a memetic meta-heuristic approach for solving complex optimization problems. Like other evolutionary algorithms, it may also suffer from the problem of slow convergence. To elevate the convergence property of the algorithm, locally informed search strategy is incorporated with SFLA. To improve the intensification and diversification capabilities of SFLA, locally informed search strategy is embedded by calculating the mean of local best and one randomly selected neighbour solution of memeplex while updating the position of worst solution in local best updating phase. Similarly, mean of global best and a randomly selected neighbour solution is used to improve the position of worst solution while updating the position of worst solution in global best updating phase. The proposed algorithm is named as Locally Informed Shuffled Frog-Leaping Algorithm (LISFLA). The modified algorithm LISFLA is analysed over 15 distinct benchmark test problems and compared with conventional SFLA, its recent variant, namely Binomial Crossover Embedded Shuffled Frog-Leaping Algorithm (BC-SFLA) and three other nature inspired algorithms, namely Gravitational Search Algorithm (GSA), Differential Evolution (DE) and Biogeography-Based Optimization Algorithm (BBO). The results manifest that LISFLA is an antagonist variant of SFLA.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call