Some of the functionalities will not work if javascript off. Please enable Javascript for it.
Official Website of Rajiv Gandhi Institute of Petroleum Technology, Jais, Amethi, India. / 5G-IoT

5G Communication and IoT

Deep Learning and or/ AI has been recognized as a state-of-the-art and path breaking technology for achieving significant data rate enhancement in communication systems. In hybrid RF/VLC, data rate maximization is subject to constraints on bandwidth, power and the user association. The joint optimization problem of bandwidth, power and user association to maximize the data rate is non-concave and obtaining an optimal solution is difficult with conventional optimization algorithms. The 5G communication and IoT Group in the Department is actively involved in developing Deep Q Network based solutions to address these issues. The application of DQN learning based algorithm is carried out by finding an optimal policy with the help of an action-value function. As the data sets for the considered system are large, a multi-layered neural network is used for approximating the action-value function estimator. In only RF systems, the group is involved in the application of Deep Learning and AI system in cognitive radio communication security.



Deep Learning/AI in Hybrid RF/VLC based 5G Communication


Deep Learning/AI in RF based 5G Communication


Cognitive Radio (CR) technology is established as an efficient mechanism to combat spectrum scarcity in 5G Communications. Cooperative spectrum sensing (CSS) further enhances its efficiency. However, primary user emulation attack (PUEA) can affect the key purpose of CSS, by changing its fundamental model. This necessitates optimization of the CSS system facing a PUEA. The department is involved in performing such optimization with the help of Deep Q- Network (DQN) learning. the application of DQN learning is carried out by finding an optimal policy with the help of an action-value function. The optimal policy gives the optimal decision threshold and the optimal sensing time. As the data sets for the considered system are large, a multi-layered network is used for approximating the action-value function estimator.