Predicted Contention Resolution in 802.11ax Based on Reinforcement Learning
Main Article Content
Abstract
in this paper, we exploits the spatial reuse SR mechanism of IEEE 802.11ax by integrating the color scheme to predict, adapts the OBSS/PD threshold, and adjusts the transmission power level. With the rapid development of modern technology, networks of communication have turned into a complex and colossal system. The new network technology, such as WIFI 6, is committed to providing more great performance and improvements where the density and complexity of the network will more increase and new requirements and problems will appear. In this solution, we propose a prediction reinforcement-learning model in network traffic based on the dynamic exponential smoothing model and optimises the smoothing coefficient of the model through the hyperbolic cosine. Moreover, our solutions based on the network traffic prediction improve the many parameters such as throughput and de delay. The simulation results show that the advantage of prediction model with optimised hyperbolic cosine has a high accuracy and stability in dense scenario
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
