Resource allocation is the optimal distribution in a limited number of resources available for certain activities. The allocation of the resources for a large number of activities requires exponentially multiplying a computation cost. Therefore, the resource allocation problem is known as NP-Hard problem in the literature. In this study, a multi-objective binary artificial bee colony algorithm has been proposed for solving the multi-objective resource allocation problems. The proposed algorithm has benefited from the robust structure and easy implementation properties of the artificial bee colony algorithm. The contribution is to introduce the multi-objective version of the artificial bee colony algorithm with advanced local search and binary format using transfer functions. The multi-objective binary artificial bee colony algorithm has been improved as two versions using sigmoid and hyperbolic tangent transfer functions to be able to search in the binary search space. With the proposed algorithms, the multi-objective resource allocation problems in the literature are solved, and the algorithms are compared with other algorithms that develop for the same problems. The results obtained show that the proposed algorithms give effective results on the problem. Especially, in large-scale problems, higher accuracy values are reached with a smaller number of evaluations.

资源分配是在某些活动可用的有限数量的资源中的最佳分配。为大量活动分配资源需要成倍地增加计算成本。因此，资源分配问题在文献中被称为NP-Hard问题。为了解决多目标资源分配问题，提出了一种多目标二进制人工蜂群算法。所提出的算法得益于人工蜂群算法的鲁棒结构和易于实现的特性。所做的贡献是引入了具有先进的局部搜索和使用传递函数的二进制格式的人工蜂群算法的多目标版本。多目标二进制人工蜂群算法已改进为使用S型和双曲正切传递函数的两个版本，以便能够在二进制搜索空间中进行搜索。通过提出的算法，解决了文献中的多目标资源分配问题，并将该算法与针对相同问题而开发的其他算法进行了比较。获得的结果表明，所提出的算法在该问题上给出了有效的结果。特别是在大规模问题中，通过较少的评估就可以达到更高的精度值。并将这些算法与针对相同问题开发的其他算法进行比较。获得的结果表明，所提出的算法在该问题上给出了有效的结果。特别是在大规模问题中，通过较少的评估就可以达到更高的精度值。并将这些算法与针对相同问题开发的其他算法进行比较。获得的结果表明，所提出的算法在该问题上给出了有效的结果。特别是在大规模问题中，通过较少的评估就可以达到更高的精度值。