Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193459,
        author = {Mr. G. RAMASAMY and Dr. C. CHANDRASEKAR},
        title = {AI-Powered Deep Agentic Model for Resource Efficient Seamless Data Communication in 5G Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {387-410},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193459},
        abstract = {5G is an ultra-high-speed, low-latency, and reliable wireless communication systems. The rapid explosion of mobile devices in 5G network, integrated with the exponential growth of data traffic. As a result, it faces significant challenges in seamless connectivity while ensuring high-quality service delivery. The initiation of 5G technology demands major improvements in handover approach to ensure seamless connectivity and optimal performance in mobile networks.  In 5G mobile networks, frequent and unnecessary handovers have emerged as a significant challenge, particularly for mobile devices based on cellular data and exhibiting complex mobility patterns. To address this issue, a novel LAplace KErnelized Regressive Agentic AI (LAKER-AAI) model is developed by statistical distribution functions. By accurately modeling user mobility and network behavior, the proposed agentic AI model dynamically adjusts handover parameters to enhance the seamless data communication. This enhances the efficiency, increased connection speed, low latency, and throughput of handovers under varying network conditions. Agentic AI model called deep reinforcement learning model is employed for analyzing each device’s resources such as energy, bandwidth, memory, and spectrum. Next, identifies resource-efficient devices through the segmented regression model to enhance data delivery and minimize packet loss. Followed by, the connectivity metrics of the selected resource efficient devices is computed based on received signal strength and SINR and RSRP. Using this analysis, Laplace kernel is employed to identify better and poor connectivity of the devices.  Finally, Weighted Fair Queuing handover mechanism is employed for efficient handover to maintain seamless communication. Then Agentic AI model assigns the rewards for identifying the successful handover. Finally, resource-efficient seamless communication is achieved.   The performance of the proposed LAKER-AAI model is evaluated using various metrics, including energy efficiency, spectrum efficiency, handover success rate, data delivery rate, data loss, throughput, and handover latency. Quantitative results reveal that the LAKER-AAI model significantly enhances seamless communication in 5G networks, achieving higher throughput, lower latency, and packet loss compared to existing methods.},
        keywords = {5G network, Seamless communication, agentic AI, segmented regression model, Laplace kernel, Weighted Fair Queuing handover mechanism},
        month = {March},
        }