Published Paper Details:

Directional wireless communication systems require efficient power control and accurate alignment to ensure reliable connectivity and optimal energy usage. Conventional optimization-based methods struggle in highly dynamic environments with mobility and channel uncertainty. This paper presents an Artificial Intelligence (AI)-driven framework for adaptive power control and alignment detection. Reinforcement learning is employed to dynamically regulate transmission power, while deep learning models are used to detect alignment states directly from received signal features. Simulation results demonstrate im proved energy efficiency, higher throughput, and robust alignment performance compared to traditional techniques, highlighting the effectiveness of AI-based solutions in next-generation wireless networks Reinforcement learning is utilized to continuously learn optimal transmis sion power policies based on real-time channel conditions and interference levels, enabling improved energy efficiency without relying on explicit channel models. In parallel, deep learning models are employed to identify alignment states directly from received signal fea tures such as signal strength, phase variations, and mobility patterns, thereby reducing beam training overhead and alignment latency. The joint optimization of power control and alignment detection allows the system to adapt more effectively to dynamic wireless envi ronments. Simulation-based evaluations demonstrate that the proposed AI-driven approach achieves higher throughput, lower power consumption, and improved alignment robustness when compared to traditional methods. The results highlight the potential of AI algorithms as a key enabler for next-generation wireless networks, including millimeter-wave and mas sive MIMOsystems, where adaptability and efficiency are critical performance requirements.