Modified-LSTM and feed forward neural network enabled resource allocation for 6G wireless networks

Abstract

The 6G wireless networks utilize terahertz (THz) frequency and intended to tremendously dynamic and diverse applications with deep learning enabled network, harvested significant attention and able to solve complex problems. Efficient resource allocation is a key requirement of next generation wireless networks. This research focuses on the resource allocation optimization challenge which includes storage, computing power, bandwidth and memory in the milieu of 6G wireless networks with device-to-device (D2D) communication enabled. The proposed model uses modified long short-term memory (mLSTM) and feed forward neural network to allocate resources to various tasks as per requirement such as information access, audio/video streaming, information access and productivity activity applications. The proposed work focuses on network parameters like channel noise, signal to noise ratio (SNR), distance from base station and includes D2D communication decisions to improve network performance. This research gives a novelty learning based solution for resource allocation for 6G wireless networks which contributes to the enhancement of next generation wireless communication networks. The lowest computing power utilized is 1%, Bandwidth utilized is 3% of total bandwidth and 2% storage.