Heuristic-Learning-Based Network Architecture for Device-to-Device User Access Control

D2D networks have been employed in various mobile applications. Due to the limited wireless resource, a network cannot meet the data transmission requirements of all the users, especially in a data-intensive application. In such a scenario, a few users must temporarily disconnect from a network to guarantee the normal operation of the network. In a D2D network, the user access control strategy depends on the authenticity of CSI, since a user can be allocated more wireless resource and be allowed to stay in the network with a higher probability if the user has a higher CSI value. In this article, we investigate a heuristic learning method in which each user's CSI needs to be verified, and the users advocating a larger CSI are detected to be frauds. The results indicate that a dramatic increase of network performance can be captured by the proposed algorithm.

[1]  Olav Tirkkonen,et al.  Resource Sharing Optimization for Device-to-Device Communication Underlaying Cellular Networks , 2011, IEEE Transactions on Wireless Communications.

[2]  Jason Cong,et al.  Minimizing Computation in Convolutional Neural Networks , 2014, ICANN.

[3]  Tunchan Cura,et al.  A particle swarm optimization approach to clustering , 2012, Expert Syst. Appl..

[4]  B. Kulkarni,et al.  An ant colony approach for clustering , 2004 .

[5]  Adel Nadjaran Toosi,et al.  Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applications , 2012, Artificial Intelligence Review.

[6]  Kaushik Roy,et al.  The k-Nearest Neighbor Algorithm Using MapReduce Paradigm , 2014, 2014 5th International Conference on Intelligent Systems, Modelling and Simulation.

[7]  Qing He,et al.  Parallel K-Means Clustering Based on MapReduce , 2009, CloudCom.

[8]  Sueng Jae Bae,et al.  Dynamic power control mechanism for interference coordination of device-to-device communication in cellular networks , 2011, 2011 Third International Conference on Ubiquitous and Future Networks (ICUFN).

[9]  Yonggang Wen,et al.  A Survey on Consensus Mechanisms and Mining Strategy Management in Blockchain Networks , 2018, IEEE Access.

[10]  Thomas Hofmann,et al.  Map-Reduce for Machine Learning on Multicore , 2007 .

[11]  Di Lin,et al.  Blockchain Consensus Based User Access Strategies in D2D Networks for Data-Intensive Applications , 2018, IEEE Access.

[12]  Hyung-Jin Choi,et al.  A practical channel estimation and feedback method for device-to-device communication in 3GPP LTE system , 2014, ICUIMC '14.

[13]  Jeffrey G. Andrews,et al.  Power Control for D2D Underlaid Cellular Networks: Modeling, Algorithms, and Analysis , 2013, IEEE Journal on Selected Areas in Communications.

[14]  Asrar U. H. Sheikh,et al.  Low-Complexity Particle Swarm Optimization for Time-Critical Applications , 2014, ArXiv.