ENHANCING QUALITY OF SERVICE IN IOT ROUTING USING THE CONVOLUTIONAL LION ROUTING OPTIMIZATION (CLRO) ALGORITHM

Abstract

The Internet of Things (IoT) is growing at a rapid pace, which has increased the need for effective routing protocols to guarantee excellent Quality of Service (QoS) in network communication. In order to optimize routing in cluster-based IoT networks, this study proposes the Convolutional Lion Routing Optimization (CLRO) method, a novel approach that combines the Lion Optimization method (LOA) with Convolutional Neural Networks (CNN). In order to minimize End-to-End Delay, optimize Packet Delivery Ratio (PDR), decrease Routing Overhead, boost Throughput, and preserve Energy Consumption, the CLRO algorithm was created. The FireFly (FF) and Artificial Bee Colony (ABC) algorithms are two well-known optimization algorithms that are used to compare the performance of the CLRO method. According to simulation studies, the CLRO algorithm greatly improves QoS metrics, which makes it a viable option for effective IoT routing.