An Optimized Neural Network-Based Resource Allocation for 5G Wireless Communication Systems

Fifth-generation (5G) wireless communication technology plays a vital role in different applications and services. However, they face a challenge in resource coverage mobility and resource management. Thus, a novel hybrid Strawberry-based Deep Belief Neural Approach (SbDBNA) was developed to allocate and share the resources optimally to the Machine Type Communication (MTC) users. Initially, the desired number of nodes is created in the NS2 environment. The user state is analyzed as sleep or active to minimize resource wastage. Moreover, the users’ requirement is determined to estimate the priority of each user. Then, the resources are allocated and shared with all the users based on priority and requirement. The incorporation of strawberry fitness in the presented model improves the Quality of Service (QoS) and reduces the time complexity. The proposed work is implemented in NS2 software, and the results are estimated in terms of throughput, delay, and data aggregation rate. Moreover, the robustness of the presented model is validated with a comparative analysis.