TY - GEN
T1 - 5G D2D Transmission Mode Selection Performance Cluster Limits Evaluation of Distributed AI and ML Techniques
AU - Ioannou, Iacovos
AU - Christophorou, Christophoros
AU - Vassiliou, Vasos
AU - Pitsillides, Andreas
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/17
Y1 - 2021/7/17
N2 - 5G D2D Communication promises improvements in energy and spectral efficiency, overall system capacity, and higher data rates. However, to achieve optimum results, it is essential to select wisely the Transmission mode of the D2D Device to form clusters in the most advantageous positions in terms of Sum Rate and Power Consumption. Towards this end, this paper investigates the use of Distributed Artificial Intelligence (DAI) and innovative D2D, Machine Learning (ML) approaches (i.e., DAIS, FuzzyART, DBSCAN and MEC) to achieve satisfactory results in terms of Spectral Efficiency (SE), Power Consumption (PC) and execution time, with the creation of clusters and back-hauling links in D2D network under existing Base Station. Additionally, this paper focuses on a small number of Devices (i.e., <=200), targeting the identification of the limits of each approach in terms of the low number of devices. More specifically, we investigate when an operator must consider implementing a D2D network (that requires extra complexity), therefore when the cluster members are sufficient enough to achieve better results than the classic mobile network. So, this research identifies where it is beneficial to form a cluster, investigate the critical point that gains increases rapidly and in the end, examine the applicability of 5G requirements. Additionally, prior work presented a Distributed Artificial Intelligence (DAI) Solution/Framework in D2D, and a DAIS Transmission Mode Selection (TMS) plan was proposed. In this paper, DAIS is further examined, improved in terms of thresholds evaluation (i.e., Weighted Data Rate (WDR), Battery Power Level (BPL)), evaluated, and compared with other approaches (AI/ML). The results obtained demonstrate the exceptional performance of DAIS and FuzzyART, compared to all other related approaches in terms of SE, PC, execution time and cluster formation. Also, results show that the investigated AI/ML approaches are also beneficial for Transmission Mode Selection (TMS) in 5G D2D communication, even with fewer devices (i.e., >=5 for clustering, >=50 for backhauling) as lower limits.
AB - 5G D2D Communication promises improvements in energy and spectral efficiency, overall system capacity, and higher data rates. However, to achieve optimum results, it is essential to select wisely the Transmission mode of the D2D Device to form clusters in the most advantageous positions in terms of Sum Rate and Power Consumption. Towards this end, this paper investigates the use of Distributed Artificial Intelligence (DAI) and innovative D2D, Machine Learning (ML) approaches (i.e., DAIS, FuzzyART, DBSCAN and MEC) to achieve satisfactory results in terms of Spectral Efficiency (SE), Power Consumption (PC) and execution time, with the creation of clusters and back-hauling links in D2D network under existing Base Station. Additionally, this paper focuses on a small number of Devices (i.e., <=200), targeting the identification of the limits of each approach in terms of the low number of devices. More specifically, we investigate when an operator must consider implementing a D2D network (that requires extra complexity), therefore when the cluster members are sufficient enough to achieve better results than the classic mobile network. So, this research identifies where it is beneficial to form a cluster, investigate the critical point that gains increases rapidly and in the end, examine the applicability of 5G requirements. Additionally, prior work presented a Distributed Artificial Intelligence (DAI) Solution/Framework in D2D, and a DAIS Transmission Mode Selection (TMS) plan was proposed. In this paper, DAIS is further examined, improved in terms of thresholds evaluation (i.e., Weighted Data Rate (WDR), Battery Power Level (BPL)), evaluated, and compared with other approaches (AI/ML). The results obtained demonstrate the exceptional performance of DAIS and FuzzyART, compared to all other related approaches in terms of SE, PC, execution time and cluster formation. Also, results show that the investigated AI/ML approaches are also beneficial for Transmission Mode Selection (TMS) in 5G D2D communication, even with fewer devices (i.e., >=5 for clustering, >=50 for backhauling) as lower limits.
KW - 5G
KW - Clustering
KW - D2D
KW - Distributed Artificial Intelligence
KW - Transmission Mode selection
KW - Unsupervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85115691772&partnerID=8YFLogxK
U2 - 10.1109/COMNETSAT53002.2021.9530792
DO - 10.1109/COMNETSAT53002.2021.9530792
M3 - Conference contribution
AN - SCOPUS:85115691772
T3 - 10th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2021 - Proceedings
SP - 70
EP - 80
BT - 10th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2021
Y2 - 17 July 2021 through 18 July 2021
ER -