Volume 41, Number 5, Octobre 2023
|887 - 894
|11 December 2023
Fairness guarantee algorithm of high-density WLAN based on neural network and genetic algorithm
School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, China
In order to meet the growing requirements of users for wireless services in various scenarios, highly densely deployed wireless local area network(WLAN) will be developed. However, due to the limited frequency resources, there must be a large number of wireless access points(APs) in the same channel. But APs which are located in the same channel will interfere with each other, resulting in a decline in the fairness of throughput in the network. And it can not provide users with good quality of service. In order to improve the fairness of throughput and experience of users, it is necessary to formulate the reasonable network parameter adjusting methods. A method based on neural network and genetic algorithm is proposed. The neural network is used to build the relationship between the parameters of WLAN and the fairness of throughput. The trained model is used as the fitness evaluation function of the genetic algorithm. And the genetic algorithm is used to solve the optimization parameter combination configuration to improve the fairness of throughput in WLAN. Simulation results show that the present algorithm can improve the fairness of throughput in the whole network.
为了满足用户在各类场景下对无线业务日益增长的要求, 高密集部署的无线局域网(wireless local area network, WLAN)是未来发展的趋势。但由于频率资源有限, 相同信道必然存在多个WLAN无线接入点(access point, AP), 然而处于同一信道的AP会互相干扰, 造成网络中小区间吞吐量的公平性下降, 无法为用户提供良好的服务质量。为了提高网络公平性, 改善用户体验, 需要制定合理的网络参数调优方法, 给出了一种基于神经网络和遗传算法对WLAN参数优化的方法。采用神经网络构建网络参数与网络吞吐量公平性之间的映射, 将训练完成的模型作为遗传算法的适应度评估函数, 通过遗传算法求解优化参数组合配置来改善WLAN吞吐量公平性问题。仿真结果表明所提出算法能够使得高密集WLAN吞吐量公平性得到提升。
Key words: wireless local area network(WLAN) / fairness / neural network / genetic algorithm
关键字 : 无线局域网 / 公平性 / 神经网络 / 遗传算法
© 2023 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.