In recent years, flying ad hoc networks (FANETs) have witnessed a notable increase in its applications after the onset of the collaborations of the small unmanned aerial vehicles (UAVs). Because of its inherent characteristics, FANETs are used in diverse application ranging from the military to civil domain. Conversely, there are certain issues pertaining to the communication among the UAVs in view of the high mobility and limited battery resources available in the UAVs, resulting in their short lifetime. The paper is an attempt to address these issues plaguing to the short lifespan of the UAVs. In this paper, we propose a hybrid bio-inspired algorithm HGSOFA for optimizing cluster head (CH) selection in a FANETs. HGSOFA utilizes the hybrid implementation of glowworm swarm optimization (GSO) and firefly algorithm (FA). In this paper, we explain the step-by-step working of the HGSOFA and then performance is evaluated through rigorous simulations. Two separate network areas with varying node density is considered for conducting all the simulations. A robust experimental environment is developed using Taguchi and orthogonal methods. HGSOFA’s performance is tested against the conventional GSO and FA algorithms in respect of cluster building time, energy consumption and first node death. Comparable results have showcased the advantages of the HGSOFA as compared to other algorithms.

近年来，在小型无人飞行器（UAV）合作开始后，飞行自组织网络（FANET）的应用有了显着增长。由于其固有的特性，FANET被广泛用于从军事到民用领域的各种应用。相反，鉴于无人机中的高移动性和有限的可用电池资源，存在与无人机之间的通信有关的某些问题，从而导致其寿命短。本文试图解决困扰无人机使用寿命短的这些问题。在本文中，我们提出了一种混合生物启发算法HGSOFA，用于优化FANETs中簇头（CH）的选择。HGSOFA利用萤火虫群优化（GSO）和萤火虫算法（FA）的混合实现。在本文中，我们将说明HGSOFA的分步工作，然后通过严格的模拟评估性能。考虑使用两个具有不同节点密度的独立网络区域进行所有模拟。使用田口和正交方法开发了一个强大的实验环境。HGSOFA的性能已针对传统的GSO和FA算法在集群构建时间，能耗和第一节点死亡方面进行了测试。可比较的结果显示了HGSOFA与其他算法相比的优势。HGSOFA的性能已针对传统的GSO和FA算法在集群构建时间，能耗和第一节点死亡方面进行了测试。可比较的结果显示了HGSOFA与其他算法相比的优势。HGSOFA的性能已针对传统的GSO和FA算法在集群构建时间，能耗和第一节点死亡方面进行了测试。可比较的结果显示了HGSOFA与其他算法相比的优势。