AI-Enhanced Routing Protocols for Efficient Data Transmission in Wireless Networks

The increasing demand for efficient data transmission in wireless networks, such as mobile ad-hoc networks (MANETs) and vehicular ad-hoc networks (VANETs), presents significant challenges in maintaining reliable communication and minimizing energy consumption. Traditional routing protocols often fail to adapt dynamically to varying network conditions, leading to suboptimal performance and increased latency. To address these limitations, this study introduces an AI-enhanced Position Assisted Routing Protocol (PARP) designed for efficient data transmission in wireless networks. The proposed protocol leverages machine learning algorithms, specifically deep reinforcement learning (DRL), to optimize routing decisions based on real-time network conditions and node positions. The PARP integrates position-based information with AI-driven prediction models to proactively determine the optimal routing paths, thus reducing packet loss and improving transmission efficiency. Extensive simulations were conducted using the NS-3 simulator to evaluate the performance of the AI-enhanced PARP against existing protocols such as AODV and DSR. The results demonstrate a significant improvement in key performance metrics: packet delivery ratio increased by 23%, average end-to-end delay reduced by 35%, and network throughput improved by 28% compared to conventional protocols. Additionally, the proposed protocol achieved a 15% reduction in energy consumption, highlighting its suitability for energy-constrained wireless networks. These findings indicate that the AI-enhanced PARP can dynamically adapt to network changes, providing a robust and efficient solution for data transmission in various wireless network scenarios. Future research will focus on incorporating additional environmental factors, such as interference and mobility patterns, to further enhance the protocol’s adaptability and performance.