The Internet of Things (IoT) brings new applications and challenges related to cloud computing. The service distribution challenge is becoming more evident and a need for better service options is emerging. The focus of the work is to optimize issues related to the allocation of resources in Edge Computing, improving the quality of service (QoS) with new methodologies. An algorithm based on a bio-inspired model was developed. This algorithm is based on the behavior of gray wolves and it is called Algorithm for 5G Resource Management Optmization in Edge Computing (GROMEC). The algorithm uses the meta-heuristic technique applied to Edge Computing, to result in a better allocation resources through user equipment (UE). The resources considered for allocation in that work are processing, memory, time and storage. Two genetic algorithms were used to define the fitness of an Edge in relation to the resource. Two other algorithms that use traditional techniques in the literature, the Best-First and AHP methods, were considered in the evaluation and comparison with the GROMEC. In the function used to calculate fitness during the simulation made with the GROMEC, the proposed algorithm had a lower number of denied services, presented a low number of blocks and was able to meet the largest number of UEs allocating on average up to 50% more in relation to the Best and 5.25% in relation to Nancy.

中文翻译：

---

边缘计算中5G资源管理优化算法

物联网 (IoT) 带来了与云计算相关的新应用和挑战。服务分发的挑战变得越来越明显，对更好的服务选项的需求正在出现。这项工作的重点是优化与边缘计算中资源分配相关的问题，使用新方法提高服务质量 (QoS)。开发了一种基于仿生模型的算法。该算法基于灰狼的行为，称为边缘计算中的 5G 资源管理优化算法 (GROMEC)。该算法使用应用于边缘计算的元启发式技术，通过用户设备（UE）获得更好的资源分配。在该工作中考虑分配的资源是处理、内存、时间和存储。使用两种遗传算法来定义与资源相关的边的适应度。在与 GROMEC 进行评估和比较时，考虑了使用文献中传统技术的另外两种算法，即最佳优先和 AHP 方法。在使用 GROMEC 进行的模拟过程中用于计算适应度的函数中，所提出的算法具有较低的拒绝服务数量，呈现的块数量较少，并且能够满足最大数量的 UE 平均分配高达 50%与 Best 相关，5.25% 与 Nancy 相关。