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.
