Edge controller-based deep learning framework for data-driven view in 5G cellular network

The emergence of the 5G portable network has brought plenty of advantages. Notwithstanding, it provoked new difficulties in the 5G organisation's online protection guard framework, resource management, energy, and reserve, along these lines making the current methodologies out of date to handle the new difficulties. This paper brings an effective edge-based DL model for a 5G cellular network. It gives insights about cloud controller managing RAN for transferring data from user devices to the core network, for example, network strength, security capacities, and network versatility. The proposed engineering comprises four unique layers recognised as network orchestration layer, RAN controllers layer, distributed units layer, and service layer. It uses a DCNN-based model and also further converges with feed-forward organisations to learn the effect of organisation designs and other outside factors. To enhance the safety features of the proposed model, we have used AES methods besides DCNN on the edge. Experimental studies state that while evaluating our DL incorporated model with other techniques, the proposed model outperforms under measures like accuracy, memory utilisation, sensitivity, etc.