Cooperative Micro Artificial Bee Colony Algorithm for Large Scale Global Optimization Problems

Abstract

Abstract. Large scale optimization problems or optimization problems involving high-dimensions often appear in real world application scenario. The mathematical representation of these problems appears similar to that of traditional low dimensional problems but they exhibit high interdependencies among the variables to be optimized. Hence normal evolutionary algorithms or swarm intelligence based methods cannot be directly operated on these problems to find global optimum. In these situations, cooperating approaches are proved to be very valuable, since they are based on though simple yet power strategy "divide and conquer". Though handy, computational burden of cooperative approach oriented methods will be high, as they involve optimization of various subcomponents for predefined number of steps. On other hand, recently evolved Micro Evolutionary Algorithms (micro-EAs) are shown to be very powerful strategies for solving optimization problems, as they involve very small population of just a few individuals. This advantage of micro-EA is accompanied by its tendency towards to get stuck in local optima. Hence this paper tries to combine the advantages of both cooperative strategies and also micro-EAs nature accompanied with a swarm intelligent Artificial Bee Colony (ABC) algorithm as main optimizer, to solve optimization problems of very high dimension. The proposed variant is termed as "Cooperative Micro-Artificial Bee Colony" (CMABC) algorithm. Computer simulations over benchmark suite considered and also extensive comparisons over cooperative variants of state-of-art Differential Evolution method show the superiority of proposed algorithm.

Support Vector Machines Trained with Evolutionary Algorithms Employing Kernel Adatron for Large Scale Classification of Protein Structures

“…The µ ABC algorithm was first introduced by Rajasekhar in 2012 29. This algorithm is a variant of the ABC algorithm with a small population (only 3 bees).…”

“…The EA algorithms combined with KA were chosen based on good results shown in other areas, their exploration and exploitation capabilities, and low computational complexity. 27–33…”

Micro-differential evolution: Diversity enhancement and a comparative study

“…Several other types of micro-population-based algorithms have been proposed in the literature. A cooperative micro-artificial bee colony (CMABC) approach for large-scale optimization is presented in [53]. This approach has combined the divide-and-conquer property of cooperative algorithms and low computational cost of micro-artificial bee colony (MABC) method.…”

“…Related Research Works Genetic Algorithm (GA) [5], [10], [21], [28]- [36] Particle Swarm Optimization (PSO) [6], [7], [40]- [52], [58] Differential Evolution (DE) [1], [3], [8], [9], [11]- [18], [60] Artificial Bee Colony (ABC) [53] Bacterial Foraging Optimization (BFO) [54] Artificial Immune System (AIS) [56] Elitistic Evolution (EEv) [57] has outperformed the standard bacterial foraging optimization algorithm (BFOA) with a larger population size [54]. For the environmental economic dispatch case study, a chaotic micro-bacterial foraging algorithm (CMBFA) with a time-varying chemotactic step size is proposed in [55].…”

A Switched Parameter Differential Evolution for Large Scale Global Optimization – Simpler May Be Better

“…Recently some promising Cooperative Co-evolutionary (CC) algorithms were proposed like the CC versions of the Particle Swarm Optimization (CCPSO and CCPSO2) [10] and CC with Differential Grouping [11]. Micro-EAs (see for example [12][13][14][15]) are instances of typical EAs characterized by small population size and often simple fitness functions. Different forms of Memetic Algorithms (MAs) [16][17][18][19] developed by combining an LS method with a global evolutionary optimizer have been frequently applied to solve large scale function optimization problems.…”