Quality of service criteria in real time video streaming applications

This study looks into how difficult it is to stream videos over Mobile Ad-hoc Networks (MANETs). Because it is dynamic and decentralized, it has problems like packet loss, high latency, and lower throughput. This paper is proposing a Feed Forward Neural Network (FFNN) approach to enhance the throughput, packets delivery rate, and the end to end delay and packet loss reduction in MANETs. The methodology involves three scenarios simulating varying node densities (100, 200, and 300). video packets are sent from a base station to host nodes. Because MANETs are always changing, the proposed Feed Forward Neural Network (FFNN) model is designed to optimize real-time video packet exchange in a way that adapts to the network. results demonstrate that the proposed approach is outperformed over the base line technology. These achievements show that the model is good at solving problems that come up with video streaming over MANETs. It offers a strong way to improve performance in changing and limited network settings. The following tables and discussions show numerical results that support the success of the proposed method even more.