AI-Assisted Complex Wireless Network
Evaluation Using Dynamic Ranking Scheme
Yuan Gao
1,2,3 , Jiang Cao
1(&)
, Weigui Zhou
2 , Chao Qing
2 , Hong Ao
2 ,
Su Hu
3 , Junsong Yin
1 , ShuangShuang Wang
1 , Xiangyang Li
1 ,
and Haosen Yu
4
1 Academy of Military Science of the PLA, Beijing 100142, China
caojiang60@foxmail.com
2 Xichang Satellite Launch Center, Sichuan 615000, China
3 University of Electronic Science and Technology of China, Sichuan
611731, China
4 International College, Chongqing University of Posts
& Telecommunications, Chongqing 400065, China
Abstract. In recent development of communication systems, increasing
amount of mobile terminals and multimedia content will require more and more
resources to satisfy the need of users. However, there is rare study about the
evaluation of large-scale complex network, from which the shortage of the
network could be discovered. In this paper, we discuss the AI-based network
evaluation method, we propose a novel discovery and ranking system using
deep learning to collect and evaluate the network influence factor, and then, the
key factors will be discovered to detect the advantages and shortages of network
elements, deployments and scale. The AI-based detection and evaluation system
is running along with the LTE-A system-level simulation platform, the accuracy
and the effectiveness are evaluated, system shortages are successfully discovered
within 100 trainings.
Keywords: AI Á Complex Á Wireless network Á Dynamic ranking
1 Introduction
The breakthrough of fifth-generation wireless communication system has brought
significant improvement in our daily life [1–3]. More and more types of terminals are
connected to Internet providing varieties of information. One significant different
compared to previous wireless communication system is the complexity, caused by the
advanced signal processing or information fusion methods, and the huge number of
network elements and data [4, 5], where existing methods could not tackle the enormous scale of the evaluation.
Performance evaluation of complex network is still a hard topic in both academic
and industry. Existing evaluations are mainly focused on some dedicated points, for
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 546–553, 2020.
https://doi.org/10.1007/978-981-15-0187-6_65
Evaluation Using Dynamic Ranking Scheme
Yuan Gao
1,2,3 , Jiang Cao
1(&)
, Weigui Zhou
2 , Chao Qing
2 , Hong Ao
2 ,
Su Hu
3 , Junsong Yin
1 , ShuangShuang Wang
1 , Xiangyang Li
1 ,
and Haosen Yu
4
1 Academy of Military Science of the PLA, Beijing 100142, China
caojiang60@foxmail.com
2 Xichang Satellite Launch Center, Sichuan 615000, China
3 University of Electronic Science and Technology of China, Sichuan
611731, China
4 International College, Chongqing University of Posts
& Telecommunications, Chongqing 400065, China
Abstract. In recent development of communication systems, increasing
amount of mobile terminals and multimedia content will require more and more
resources to satisfy the need of users. However, there is rare study about the
evaluation of large-scale complex network, from which the shortage of the
network could be discovered. In this paper, we discuss the AI-based network
evaluation method, we propose a novel discovery and ranking system using
deep learning to collect and evaluate the network influence factor, and then, the
key factors will be discovered to detect the advantages and shortages of network
elements, deployments and scale. The AI-based detection and evaluation system
is running along with the LTE-A system-level simulation platform, the accuracy
and the effectiveness are evaluated, system shortages are successfully discovered
within 100 trainings.
Keywords: AI Á Complex Á Wireless network Á Dynamic ranking
1 Introduction
The breakthrough of fifth-generation wireless communication system has brought
significant improvement in our daily life [1–3]. More and more types of terminals are
connected to Internet providing varieties of information. One significant different
compared to previous wireless communication system is the complexity, caused by the
advanced signal processing or information fusion methods, and the huge number of
network elements and data [4, 5], where existing methods could not tackle the enormous scale of the evaluation.
Performance evaluation of complex network is still a hard topic in both academic
and industry. Existing evaluations are mainly focused on some dedicated points, for
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 546–553, 2020.
https://doi.org/10.1007/978-981-15-0187-6_65