Abstract
Nowadays, broadband applications that use the licensed spectrum of the cellular network are growing fast. For this reason, Long-Term Evolution-Unlicensed (LTE-U) technology is expected to offload its traffic to the unlicensed spectrum. However, LTE-U transmissions have to coexist with the existing WiFi networks. Most existing coexistence schemes consider coordinated LTE-U and WiFi networks where there is a central coordinator that communicates traffic demand of the co-located networks. However, such a method of WiFi traffic estimation raises the complexity, traffic overhead, and reaction time of the coexistence schemes. In this article, we propose Experience Replay (ER) and Reward selective Experience Replay (RER) based Q-learning techniques as a solution for the coexistence of uncoordinated LTE-U and WiFi networks. In the proposed schemes, the LTE-U deploys a WiFi saturation sensing model to estimate the traffic demand of co-located WiFi networks. We also made a performance comparison between the proposed schemes and other rule-based and Q-learning based coexistence schemes implemented in non-coordinated LTE-U and WiFi networks. The simulation results show that the RER Q-learning scheme converges faster than the ER Q-learning scheme. The RER Q-learning scheme also gives 19.1% and 5.2% enhancement in aggregated throughput and 16.4% and 10.9% enhancement in fairness performance as compared to the rule-based and Q-learning coexistence schemes, respectively.
Highlights
The modern industry has expanded the deployment of wireless networks in search of effective networking solutions that can improve network performance
The most significant issue is establishing a harmonious coexistence with the WiFi networks that already exist on the unlicensed spectrum
Many coexistence strategies have been proposed to ensure that WiFi and Long Term Evolution (LTE) networks coexist together
Summary
The modern industry has expanded the deployment of wireless networks in search of effective networking solutions that can improve network performance. The paper proposes coexistence schemes for uncoordinated LTE-U and WiFi networks which do not require a signaling protocol to exchange traffic status between the technologies. Propose coexistence scheme that use ER based Q-learning and RER based Q-learning solutions for uncoordinated LTE-U and WiFi networks. In the proposed coexistence scheme, the LTE-U eNB uses a WiFi saturation sensing model to estimate the WiFi traffic load and selects an optimal configuration according to the WiFi saturation status. The proposed scheme requires modifications on the LTE-U eNB side only and this makes it compatible with commercial off-the-shelf WiFi devices This enhances the deployment of real-time coexistence decisions as there is no delay introduced due to traffic load status exchange between the technologies.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have