Empirical Analysis of Hybrid Artificial Intelligent Techniques for Resource Aware D2D Communication in 5g/6g Networks

Wireless Communication with high data rate applications attains greater
significance recent years. The better quality of services in wireless network
directs to massive energy utilization in wireless network. To attain better
efficiency for resource distribution in cellular organization, a device-to-device
(D2D) communication is considered as a vital factor. Several research
technologies have been intended in conventional work to give the better D2D
connection but, achieving maximum throughput is a still difficult issue. In
addition, D2D communication expresses few confronts i.e. Energy usage and
data delivery rate. Resource efficient device selection is the major area of center
in D2D communication. Though, latency and loss rate involved during the
communication was failed to be minimized. In order to overcome the above
limitation, three proposed techniques are implemented in this research work as
follows.
Initially, a Bio-inspired Conic Optimized and Distributed Latency Q Learning
(BCO-DLQL) is intended with the goal of attaining effective D2D
communication in 5G. At the starting, a Bio-inspired Conic Particle Swarm
Optimization (BCPSO) concept is implemented in this work with the aim of
providing the computationally effective solutions for better energy usage in 5G.
Subsequently, the Distributed Latency Managed Q Learning (DLMQL) concept
is implemented with the objective of decreasing the latency is observed during
the D2D communication and thereby obtaining better connectivity in network.
Then, nearby device and communication range for the consequent continuous
flow of information is also analyzed in order to diminish information loss.