• Dr.Prabodh Khampariya
• SNEHASIS DEY

Data traffic on mobile networks is rapidly expanding, putting operators under pressure to investigate various methods for capacity increase. As a result, the development and maintenance of contemporary 5G networks has become more difficult. Because of this, new methods to network design and administration are required that enable self-organization capabilities. We provide a new intelligent approach for large MIMO beam forming performance optimization in this work. Deep adversarial reinforcement learning is implemented in the proposed approach by combining three neural networks in a cooperative fashion. Neural networks trained to create realistic user mobility patterns are then employed by a second neural network to build antenna diagrams suitable for that user. Both of these networks get a proportional reward from a third neural network, which assesses the effectiveness of the created antenna design. The suggested technique has the benefit of being self-learning and not need extensive training datasets.

AI,ML,CAPACITY,ENERGY EFFICIENCY,NN

"Artificial Intelligence Driven Massive MIMO for Better Energy Efficiency in Wireless Communication Systems.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 8, page no.d184-d190, August-2022, Available :http://www.jetir.org/papers/JETIR2208322.pdf

"Artificial Intelligence Driven Massive MIMO for Better Energy Efficiency in Wireless Communication Systems.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 8, page no. ppd184-d190, August-2022, Available at : http://www.jetir.org/papers/JETIR2208322.pdf