AI and Edge Computing-Driven Technologies for Knowledge Defined Networking
1Tsinghua University, Beijing, China
2Southern University of Science and Technology, Shenzhen, China
3Northeastern University, Shenyang, China
4University of Hertfordshire, Hatfield, UK
AI and Edge Computing-Driven Technologies for Knowledge Defined Networking
Description
Software Defined Networking (SDN) and Network Function Virtualization (NFV) are the two main driving forces transforming network architecture from rigid and ossified to flexible and programmable. With the now-widespread use of Artificial Intelligence (AI) and edge computing, the new concept of Knowledge Defined Networking (KDN) has emerged, which has the potential to address new challenges in the current programmable networks by providing mobile edge computing and edge caching capabilities together with AI to the proximity of end users. In AI and edge computing integrated networks, edge resources are managed by AI systems to offer powerful computational processing and massive data acquisition locally at edge networks. AI helps to obtain efficient resource scheduling strategies in a complex environment with heterogeneous resources and a massive number of devices, while meeting the ultra-low latency and ultra-high reliability requirements of novel applications, e.g. self-driving cars, remote operation, intelligent transport systems, Industry 4.0, smart energy, e-health, and AR/VR services. By integrating AI functions and edge computing technologies into KDN, the network system becomes evolvable by forming a closed network loop that consists of data collection, learning, deciding, and forwarding, which will finally have full insight into the operating environment and can adapt resource allocation or orchestration in a dynamic manner.
Despite the benefits introduced by AI and edge computing-driven KDN, many challenges are still faced in this new paradigm. For example, the integrated architectures and frameworks are not clearly identified. In addition, the related concepts and protocols are not well defined. To sum up, AI and edge computing-driven KDN is still in its infancy, and only limited research efforts have been made to apply AI and edge computing in KDN.
The aim of this Special Issue is to promote integration among the technologies of AI and edge computing to speed up the development of KDN on the basis of SDN and NFV. The Special Issue will also present and highlight the advances and latest implementations and applications in the field of KDN such that the theoretical and practical frontiers can be moved forward for a deeper understanding from both the academic and industrial viewpoints. Original research and review articles are welcome.
Potential topics include but are not limited to the following:
- The architectures of AI, edge computing, and some new emerging techniques
- New concepts, theories, and protocols the AI and edge computing enabled KDN
- AI and edge computing enabled KDN in AR/VR, smart cities, IoT, and satellite communications
- Edge computing for distributed AI-based applications
- AI for task scheduling or/and resource allocation in edge computing
- Network traffic prediction and control in AI-based KDN
- AI-based data analysis in KDN
- Edge computing-based smart resources management in KDN
- Energy-efficient knowledge management in KDN
- Advanced techniques or networking paradigms for KDN
- Security and privacy in KDN