|BEE COLONY OPTIMIZATION|
BEE COLONY OPTIMIZATION (BCO) ALGORITHM
The Bee Colony Optimization (BCO) meta-heuristic belongs to the class of Nature-Inspired Algorithms. These algorithms are inspired by various biological and natural processes. Natural systems have become important sources of ideas and models for development of various artiﬁcial systems. The popularity of the Nature-Inspired Algorithms is mainly caused by the capability of biological systems to successfully adjust to continually varying environment. Neural networks, evolutionary computation, ant colony optimization, particle swarm optimization, artificial immune systems, and bacteria foraging algorithm are some of the algorithms and concepts that were inspired by nature.
Individuals in various biological systems are engaged in cooperation, collaboration, information exchange, and/or conflicts. In many cases, individuals, that are autonomous in their decision-making, work together with other individuals in order to achieve specific objective. Natural phenomena lecture us that simple individual organisms can create systems able to perform highly complex tasks by interacting with each other.
The BCO meta-heuristic has been proposed by Lučić and Teodorović (2001). The BCO is inspired by foraging behavior in honeybees. Lučić and Teodorović used the term “Bee System” in their first paper. The basic plan behind the BCO is to build the multi agent system (colony of artificial bees) able to efficiently solve hard combinatorial optimization problems. The artificial bee colony behaves partially similar, and partially in a different way from bee colonies in nature.
The BCO meta-heuristic has been recently used as a toll for solving large and complex real-world problems. It has been shown that the BCO poses an ability to find high quality solutions of difficult combinatorial problems within a reasonable amount of computer time. The BCO is a stochastic, random-search technique. This technique uses an analogy between the way in which bees in nature search for a food, and the way in which optimization algorithms search for a optimum of (given) combinatorial optimization problems. The basic idea behind the BCO is to build the multi agent system (colony of artificial bees) able to effectively solve difficult combinatorial optimization problems. Artificial bees investigate through the search space looking for the feasible solutions. In order to find better and better solutions, autonomous artificial bees collaborate and exchange information. Using collective knowledge and sharing information among themselves, artificial bees concentrate on more promising areas, and slowly abandon solutions from the less promising areas. Step by step, artificial bees collectively generate and/or improve their solutions. The BCO search is running in iterations until some predefined stopping criteria is satisfied.
The BCO works in a self-organized and decentralized way and therefore represents a good basis for parallelization. It also poses an ability to keep away from becoming trapped in local minima. BCO has proven to be very suitable method for solving non-standard combinatorial optimization problems, like the ones containing inaccurate data or involving optimization according to multiple criteria. Applications of the BCO algorithm in these problems were realized by hybridization with the appropriate techniques.
BCO Research Group