基于人工蜂群算法求解FEVM问题

Solving FEVM Problem Based on Artificial Bee Colony Algorithm

日益复杂的计算问题促使各种受启于生物的优化算法不断的研究、发展,人工蜂群(Artificial Bee Colony, ABC)算法正是其中之一,主要在于它鲁棒性强,控制参数少,易于实现。本文着重针对不易求解的不确定规划领域中的模糊期望值模型(fuzzy expected value model, FEVM)问题,提出了模糊模拟技术与ABC算法相结合求解FEVM模型问题的混合求解算法。在该智能算法中,选用模糊模拟技术来计算模糊期望值函数,人工蜂群算法担任在搜索空间中的搜索策略,并给出了详细的求解FEVM模型问题的步骤。其克服了经典的基于遗传算法的混合算法的耗时、计算复杂、易陷入局部最优等不足,最后通过典型的数值实验验证了该算法的可行有效性,具有一定的实用价值。

The increasingly complex computing problems promote the continuous research and development of various optimization algorithms inspired by biology lately, artificial bee colony(ABC) algorithm is one of them, due to its strong robustness, less control parameters and easy implement. This paper focuses on the problem of fuzzy expected value model(FEVM) in the field of uncertain programming, a hybrid algorithm of fuzzy simulation and ABC algorithm is proposed to solve model problems. In the intelligence algorithm, fuzzy simulation is used to calculate fuzzy expected value function, ABC algorithm is taken as the search strategy in search space, and the detail steps are designed for fuzzy expected value model problem. It conquers many disadvantages such as taking a long time, computing complexity, resapsing into local extremum in the hybrid intelligence algorithm based on Genetic Algorithm, finally, the feasibility and effectiveness of the algorithm are verified by typical numerical experiments, it has some practical value for FEVM problems.