Abstract—In 5G network, resource allocation for the cell edge users is the major challenge. To address this challenge, we present GFDM (Generalized Frequency Division Multiplexing) for the physical layer of 5G wireless networks is a non orthogonal waveform with circularly pulse shaped mechanism. This mechanism is also used for resource allocation. In this paper, to allocate the weights on the filter bank of GFDM for cell edge users, an optimized Deep Neural Network (DNN) is presented in this paper. To enhance the performance of the DNN, weight parameters of it are optimized using Rain Optimization Algorithm (ROA). Using this proposed ROA based DNN, weight resources are allocated to the cell edge users optimally. Simulation results shows that the performance of the proposed resource allocation outperforms the conventional resource allocation in terms of normalized cell throughput.
 

Index Terms—GFDM, Resource allocation, optimization, deep neural network, rain optimization algorithm and cell throughput

Cite: Anitha S. Sastry and Akhila S., "A Novel Approach to the Resource Allocation for the Cell Edge Users in 5G," Journal of Communications vol. 17, no. 1, pp. 39-48, January 2022. Doi: 10.12720/jcm.17.1.39-48