Machine Learning for Wireless Networks - Recent Advances and Future Trends
1Alagappa University, Karaikudi, India
2Duy Tan University, Da Nang, Vietnam
3Sejong University, Seoul, Republic of Korea
Machine Learning for Wireless Networks - Recent Advances and Future Trends
Description
Our society is experiencing a digitisation revolution, with a drastic growth in Internet users and connected devices. Next-generation wireless networks should provide ultra-reliable, low-latency communication, and intelligently control Internet of Things (IoT) devices in real-time scenarios. Wireless network applications like real-time traffic data, sensor readings from driverless cars, or entertainment streaming recommendations generate extreme volumes of data that must be collected and processed in real-time. These communication requirements and core intelligence can only be achieved through the integration of machine learning techniques in wireless infrastructure and end-user devices.
In recent times, machine learning algorithms have gained significant interest in the area of wireless networking and communication. Machine learning driven algorithms and models can enable wireless network analysis and resource management and can be of advantage in handling the increasing volume of communication and computation for evolving networking applications. Nevertheless, the application of machine learning techniques for heterogeneous wireless networks is still under debate. More endeavours are needed to link the gap between machine learning and wireless networking research.
The aim of this Special Issue is to explore recent advancements in machine learning concepts to address practical challenges in wireless networks. This Special Issue will bring together researchers and academics to present new network modelling and architecture, networking applications, security and privacy, resource management, load balancing, and various challenges related to the design of future wireless networks with the help of machine learning.
Potential topics include but are not limited to the following:
- Machine learning based big-data analytic frameworks for networking data
- Machine learning algorithms for network scheduling and control
- Machine learning based energy-efficient networking techniques
- Machine learning based network resource allocation and optimisation in wireless networks
- New supervised machine learning methods for wireless networks
- New unsupervised machine learning methods for wireless networks
- Novel reinforcement learning methods for wireless networks
- New optimisation methods for machine learning for wireless networks
- Machine learning based innovative intelligent computing architecture/algorithms for wireless networks
- Machine learning based intelligent routing algorithms for traffic management in wireless networks
- Machine learning based resource allocation for shared/virtualised networks using machine learning
- Machine learning based quality of service (QoS) management in wireless networks
- Nature-inspired algorithms for wireless networks
- Machine learning based node localisation in wireless networks