|講 題||Network Big Data Analysis for Autonomic Future Internet|
|講 者||Professor Geyong Min, University of Exeter, U.K.|
|日 期||2017/10/26||長 度||00:37:38||人 氣||41 次|
|Autonomic Future Internet (AFI) coupled with the emerging SDN/NFV technologies is regarded as a promising and viable solution for addressing many grand challenges faced by 5G, such as explosive growth of network data traffic, massive increase in the number of interconnected devices, and continuous emergence of new services and applications. The ambition of AFI is to exploit an autonomic, intelligent and self-managing Future Internet with consequent improvement in network efficiency and performance, increased profitability, and reduced OPEX and CAPEX. Two key features of AFI are self-management and cognitive learning; the former is essential for complexity reduction and fast adaptation to changing situations and the latter can increase the intelligence through flexible knowledge utilization.|
In this talk, we will present state-of-the-art network architecture for AFI that is seamlessly integrated with SDN and NFV. The core Knowledge Plane within this unified architecture is responsible for real-time network big data analysis and knowledge discovery in order to maintain high-level behaviors of how the network should be configured, managed, and optimized. To establish a powerful, flexible and scalable Knowledge Plane in AFI, we will present the innovative big data processing technologies and cost-effective platform developed in our research group, including the unified representation of heterogeneous network big data and real-time incremental data analysis tools for extracting valuable insights to support better decision making for network design, resource management and optimization. This talk offers the theoretical underpinning for efficient processing of big data, and also opens up a new horizon of research and development by exploiting the key intelligence and insights hidden in rich network big data for design and improvement of Future Internet.