Editorial: Intelligent and Holistic Solutions for Next Generation Wireless Networks
- PDF / 264,920 Bytes
- 3 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 169 Views
Editorial: Intelligent and Holistic Solutions for Next Generation Wireless Networks Shuai Han 1 & Jalel Ben-Othman 2 & Shiwen Mao 3 & Ruoyu Su 4
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Editorial: Following the great success of 2G and 3G mobile networks and the fast growth of 4G, the next generation mobile networks or the 5th generation wireless systems has been proposed aiming to provide unprecedented networking capability to mobile users. How the next generation communication should and will be? How to effectively apply and benefit from the technologies and make them intelligently interoperate together? With developments in artificial intelligence, machine learning has boosted the sustained growth of the next generation communication networks in different perspectives. Inspired by the fundamental framework of machine learning, many researchers derive holistic approaches to achieve near or optimal solutions for next generation communication systems, which brings new opportunities for encoding and decoding, clustering, localization, mobile crowdsensing, edge computing, and security both in academia and industry. This special issue endeavors to provide researchers with a variety of intelligent and holistic solutions by conventional
* Shuai Han [email protected] Jalel Ben-Othman [email protected] Shiwen Mao [email protected] Ruoyu Su [email protected] 1
Harbin Institute of Technology, 92 Xidazhi St, Nangang, Harbin, Heilongjiang, China
2
University of Paris 13, 99 Avenue Jean Baptiste Clément, 93430 Villetaneuse, France
3
Auburn University, Auburn, AL 36849, USA
4
Nanjing University of Posts and Telecommunications, 9 Wenyuan Rd, Qixia District, Nanjing 210049, Jiangsu, China
optimization method, supervised/unsupervised learning, deep learning, and reinforcement learning in different aspects of next generation wireless networks. The first article titled “Performance Analysis of an Energy-Efficient Clustering Algorithm for Coordination Networks” improves the mechanism of Coordinated Multi-Point (CoMP) for cellular telecommunication networks in terms of energy consumption caused by extra signal processing and backhaul traffic. An energyefficient algorithm of dynamic clustering is proposed to minimize the overall network energy consumption. The second article titled “Deep Reinforcement Learning Aided Cell Outage Compensation Framework in 5G Cloud Radio Access Networks”, authored by Peng Yu, maximizes the energy efficiency of Cloud Radio Access Networks (C-RAN) by deep reinforcement learning. As a typical framework of deep learning, deep Q network (DQN) is adopted to achieve optimal mechanism of antenna downtilt and power allocation to compensate users. As a significant application of mobile networks, the third paper titled “A Multi-sensor School Violence Detecting Method Based on Improved Relief-F and D-S Algorithms” proposed a school violence detecting method based on improved Relief-F and Dempster-Shafe (DS) algorithms. The improved Relief-F algorithm is utilized to sele
Data Loading...
