An Energy-Efficient Bio-Inspired Mobility-Aware Cluster p-WOA Algorithm for Intelligent Whale Optimization and Fuzzy-Logic-Based Zonal Clustering Algorithm in FANET

Abstract

Listen

Translate article

The newest research topic is flight ad hoc network (FANET). The primary obstacles faced by unmanned aerial vehicles (UAVs) are their limited flight duration and inefficient routes resulting from their great mobility and low battery power. Compared to MANETs or VANETs, FANETS routing is thought to be more difficult because of these topological restrictions. Artificial intelligence (AI)-based clustering techniques can be applied to resolve intricate routing issues in situations when both static and dynamic routing are ineffective. To overcome these path difficulties, clustering techniques based on evolutionary algorithms, including intelligent, probabilistic, bio-inspired whale optimization algorithms (p-WOAs), we suggest fuzzy-logic-based zonal clustering-based routing algorithms in this study to be used in FANET to build clusters. In addition to requiring fewer cluster heads (CHs) for routing, p-WOA offers good coverage and low energy consumption. The stochastic whale optimization technique, which draws inspiration from nature, is utilized in this paper to build networks and deploy nodes. The next step is to choose cluster heads using a region clustering technique based on fuzzy logic. By selecting the right cluster head, you can decrease routing traffic and increase cluster longevity. Routing overhead is also decreased. The data are then sent to the best path using a reference point group mobility model. The proposed p-WOA was used to test fuzzy integral and fuzzy logic ant optimization, fuzzy integral and neural network interference system, fuzzy integral and whale optimization algorithm (ANFIS-WOA), and fuzzy integral and FL-ALO. An array of indicators, such as cluster count, longevity, cluster configuration time, cluster head consistency, and energy usage, are employed to assess the effectiveness of the suggested methodology. The suggested algorithm works better than the most advanced techniques available today, as demonstrated by the experimental findings presented in this paper.