A Novel Spectrum Sharing Scheme Using Dynamic Long Short-Term Memory With CP-OFDMA in 5G Networks

With the rapid increase in communication technologies, shortage of spectrum will be a major issue faced in the coming years. Cognitive radio is a promising solution to this problem and works on the principle of sharing between cellular subscribers and ad-hoc Device to Device (D2D) users. Existing 5G spectrum sharing techniques work as per a fixed rule and are pre-established. Also, recent game theoretic approaches for spectrum sharing uses unrealistic assumptions with less likely practical implications. Here, a novel spectrum sharing technique is proposed using 5G enabled bidirectional cognitive deep learning nodes (BCDLN) along with dynamic spectrum sharing long short-term memory (DSLSTM). A joint spectrum allocation and management is carried out with wireless cyclic prefix orthogonal frequency division multiple access (CP-OFDMA). The BCDLN self-learning nodes with decision making capability route information to several destinations at a constant spectrum sharing target, and cooperate via DSLSTM. BCDLN based on time balanced and unbalanced channel knowledge is also examined. With the proposed framework, expressions are derived for the spectrum allocated to multiple sources to obtain their spectrum targets as a variant of the participation node spectrum sharing ratio (PNSSR). The impression of noise when all nodes broadcast with equal spectrum allocation is also investigated.