Frank Ayo Ibikunle
This research addresses key optimization challenges in next-generation wireless communication networks, such as 5G, 6G, and beyond, using artificial intelligence (AI) techniques. The main goal is to explore how AI methods can improve resource allocation, power control, interference management, traffic prediction, and mobility management in diverse and changing wireless environments. The study seeks to provide a clear understanding of how different AI approaches work and how they fit into developing network structures. The methodology includes a thorough review and analysis of AI techniques like supervised and unsupervised machine learning, deep learning, reinforcement learning, evolutionary algorithms, and hybrid models. This research examines these methods based on their principles, strengths, and real-world applications for optimizing wireless networks. It combines findings from various case studies and experimental results to show AI's role in improving network adaptability and efficiency. Key findings show that AI-driven optimization significantly surpasses traditional heuristic and static methods because it enables real-time, data-driven decision-making. This leads to better network throughput, lower latency, improved energy efficiency, and more effective interference management. AI techniques, especially reinforcement learning and deep learning, support adaptive resource management, predictive traffic handling, and smooth mobility in ultra-dense and multi-tier networks. The impact of this research shows how AI can transform wireless networks into intelligent, scalable, and sustainable systems that can support new applications like autonomous systems, smart cities, and immersive multimedia. The study concludes that ongoing progress in explainable AI, federated learning, and AI-native network design will be crucial for tackling issues related to scalability, privacy, and understanding, thus shaping the future of wireless communications.