Multivariate regressive deep stochastic artificial learning for energy and cost efficient 6G communication

Abstract

In recent years, with the development of 6G networks in mobile computing, the energy consumption of data centers has increased significantly. Therefore, energy saving in data centers has become an important research direction for sustainable computing. High-energy consumption is not only detrimental to the environment but also raises the operating costs. In order to improve the energy and cost aware communication, a new technique called Multivariate Regressive Deep Stochastic Artificial Structure Learning (MRDSASL) is introduced in the 6G network. The input layer of deep stochastic artificial Structure Learning receives the several nodes and it transferred into the next layer called hidden layer where the node energy levels are estimated. Followed by, the received signal strength of the nodes is evaluated in the next consecutive hidden layer. Then the spectrum utilization is also measured in the third hidden layer. At last hidden layer, the multivariate regression function is employed to analyze the estimated node status with the threshold. Finally, the soft step activation function finds the efficient nodes through the regression analysis. Based on the deep analysis, the 6G architecture is designed with the efficient nodes. By selecting the node with higher energy, signal strength and spectrum utilization, data communication performance can be improved with minimum cost in 6G network. The simulation assessment of proposal technique and other related works are carried out in terms of metrics namely energy consumption, cost and packet delivery ratio. The simulation result illustrates that the MRDSASL technique improves the packet delivery ratio 12 %, minimizes the energy consumption by 12 %, and reduces the delay 12 % as compared to state-of-the-art works. The assessment and conferred results reveal the improvement of proposed technique in the 6G network.