The existing literature on device-to-device(D2D)architecture suffers from a dearth of analysis under imperfect channel conditions.There is a need for rigorous analyses on the policy improvement and evaluation of netwo...The existing literature on device-to-device(D2D)architecture suffers from a dearth of analysis under imperfect channel conditions.There is a need for rigorous analyses on the policy improvement and evaluation of network performance.Accordingly,a two-stage transmit power control approach(named QSPCA)is proposed:First,a reinforcement Q-learning based power control technique and;second,a supervised learning based support vector machine(SVM)model.This model replaces the unified communication model of the conventional D2D setup with a distributed one,thereby requiring lower resources,such as D2D throughput,transmit power,and signal-to-interference-plus-noise ratio as compared to existing algorithms.Results confirm that the QSPCA technique is better than existing models by at least 15.31%and 19.5%in terms of throughput as compared to SVM and Q-learning techniques,respectively.The customizability of the QSPCA technique opens up multiple avenues and industrial communication technologies in 5G networks,such as factory automation.展开更多
Network densification is envisioned as one of the key enabling technologies in the next generation and beyond wireless networks to satisfy the demand of high coverage and capacity whilst deliver an ultra-reliable low ...Network densification is envisioned as one of the key enabling technologies in the next generation and beyond wireless networks to satisfy the demand of high coverage and capacity whilst deliver an ultra-reliable low latency communication services especially to the users on the move.One of the fundamental tasks in wireless networks is user association.In the case of ultra-dense vehicular networks,due to the dense deployment and small coverage of the eNodeBs,there may be more than one eNodeB that may simultaneously satisfy the conventional maximum radio signal strength user association criteria.In addition to this,the spatial-temporal vehicle distribution in dynamic environments contribute significantly towards the rapidly changing radio environment that substantially impacts the user association,therefore,the network performance and user experience.This paper addresses the problem of user association in dynamic environments by proposing intelligent user association approach,variable-reward,quality-aware Q-learning(VR-QAQL)that has an ability to strike a balance between the number of handovers per transmission and system performance whilst a guaranteed network quality of service is delivered.The VR-QAQL technique integrates the control-theoretic concepts and the reinforcement learning approach in an LTE uplink,using the framework of an urban vehicular environment.The algorithm is assessed using large-scale simulation on a highway scenario at different vehicle speeds in an urban setting.The results demonstrate that the proposed VR-QAQL algorithm outperforms all the other investigated approaches across all mobility levels.展开更多
文摘The existing literature on device-to-device(D2D)architecture suffers from a dearth of analysis under imperfect channel conditions.There is a need for rigorous analyses on the policy improvement and evaluation of network performance.Accordingly,a two-stage transmit power control approach(named QSPCA)is proposed:First,a reinforcement Q-learning based power control technique and;second,a supervised learning based support vector machine(SVM)model.This model replaces the unified communication model of the conventional D2D setup with a distributed one,thereby requiring lower resources,such as D2D throughput,transmit power,and signal-to-interference-plus-noise ratio as compared to existing algorithms.Results confirm that the QSPCA technique is better than existing models by at least 15.31%and 19.5%in terms of throughput as compared to SVM and Q-learning techniques,respectively.The customizability of the QSPCA technique opens up multiple avenues and industrial communication technologies in 5G networks,such as factory automation.
文摘Network densification is envisioned as one of the key enabling technologies in the next generation and beyond wireless networks to satisfy the demand of high coverage and capacity whilst deliver an ultra-reliable low latency communication services especially to the users on the move.One of the fundamental tasks in wireless networks is user association.In the case of ultra-dense vehicular networks,due to the dense deployment and small coverage of the eNodeBs,there may be more than one eNodeB that may simultaneously satisfy the conventional maximum radio signal strength user association criteria.In addition to this,the spatial-temporal vehicle distribution in dynamic environments contribute significantly towards the rapidly changing radio environment that substantially impacts the user association,therefore,the network performance and user experience.This paper addresses the problem of user association in dynamic environments by proposing intelligent user association approach,variable-reward,quality-aware Q-learning(VR-QAQL)that has an ability to strike a balance between the number of handovers per transmission and system performance whilst a guaranteed network quality of service is delivered.The VR-QAQL technique integrates the control-theoretic concepts and the reinforcement learning approach in an LTE uplink,using the framework of an urban vehicular environment.The algorithm is assessed using large-scale simulation on a highway scenario at different vehicle speeds in an urban setting.The results demonstrate that the proposed VR-QAQL algorithm outperforms all the other investigated approaches across all mobility levels.
