QAAs: QoS provisioned artificial intelligence framework for AP selection in next-generation wireless networks
- PDF / 1,634,080 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 113 Downloads / 223 Views
QAAs: QoS provisioned artificial intelligence framework for AP selection in next-generation wireless networks Bhanu Priya1
· Jyoteesh Malhotra1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Emerging trend of ubiquitous data access is driving the demand for effective wireless communication connectivity. In essence to this, wireless local area network (WLAN) technology seems to be a reliable and cost effective access for the next-generation wireless ecosystem. But the pivotal challenge for WLAN in the next generation wireless networks is to cater the legions of heterogeneous services with characteristic sets of quality of service requirements. However, the strategies present in the existing literature are not accoutered for the application-agnostic association and are incompetent in handling the enormous WLAN state space. Realising the pitfalls of the existing strategies, a novel software-defined networking enabled artificial intelligence framework has been proposed. The proposed framework implements a novel invalid action reduction scheme and double deep reinforcement learning to guarantee the flow based association in a multi-service WLAN environment. Moreover, it allows the multi-parametric optimisation of the association decision and faster convergence to the stable solution. The analytical results validated through the extensive simulations revealed that the proposed scheme achieves high performance gain in terms of convergence, stability and network utility as compared to the other solutions in the literature. Keywords Artificial intelligence · Double deep reinforcement learning · Software-defined networking · Next-generation wireless networks · Access point selection
1 Introduction Wireless communication networks have witnessed rapid growth in mobile data traffic as well as a surging increase in user demands. In accordance with Cisco visual networking index report [1], by 2022 the monthly IP traffic will reach 50 GB per capita and about 96% of the mobile traffic will be consumed in the indoors. This drastic growth in the demand has urged 5G to adopt a mature and reliable wireless access solution. In spite of the maturity of 3G and 4G communication networks, WLAN is a promising solution as it allows ubiquitous coverage and reliable communication access. Moreover, in order to add more capacity in a flexible way, operators are interested in offloading data to WLAN from cellular network [2]. Therefore, WLAN will play a significant role in the nextgeneration wireless ecosystem [3] where small nodes such as pico and femto cells will be integrated to improve the user quality of experience.
B 1
Bhanu Priya [email protected] ECE Department, GNDU RC, Jalandhar, India
WLAN is considered as a preferred access in the campuses, the majority of in-buildings and public places to achieve seamless connectivity. The traffic inside these networks is represented by multifarious QoS demands. In order to satisfy this drastic growth in the heterogeneous demands, the finite WLAN spectrum needs
Data Loading...
