Network management

About: Network management is a research topic. Over the lifetime, 17859 publications have been published within this topic receiving 234520 citations. The topic is also known as: computer network management & NM.

Machine Learning for Cognitive Network Management

Abstract: Over the last decade, a significant amount of effort has been invested on architecting agile and adaptive management solutions in support of autonomic, self-managing networks. Autonomic networking calls for automated decisions for management actions. This can be realized through a set of pre-defined network management policies engineered from human expert knowledge. However, engineering sufficiently accurate knowledge considering the high complexity of today's networking environment is a difficult task. This has been a particularly limiting factor in the practical deployment of autonomic systems. ML is a powerful technique for extracting knowledge from data. However, there has been little evidence of its application in realizing practical management solutions for autonomic networks. Recent advances in network softwarization and programmability through SDN and NFV, the proliferation of new sources of data, and the availability of lowcost and seemingly infinite storage and compute resource from the cloud are paving the way for the adoption of ML to realize cognitive network management in support of autonomic networking. This article is intended to stimulate thought and foster discussion on how to defeat the bottlenecks that are limiting the wide deployment of autonomic systems, and the role that ML can play in this regard.

The middlebox manifesto: enabling innovation in middlebox deployment

Abstract: Most network deployments respond to changing application, workload, and policy requirements via the deployment of specialized network appliances or "middleboxes". Despite the critical role that middleboxes play in introducing new network functionality, they have been surprisingly ignored in recent efforts for designing networks that are amenable to innovation. We make the case that enabling innovation in middleboxes is at least as important, if not more important, as that for traditional switches and routers. To this end, our vision is a world with software-centric middlebox implementations running on general-purpose hardware platforms that are managed via open and extensible management APIs. While these principles have been applied in other contexts, they introduce unique opportunities and challenges in the context of middleboxes that we highlight in this paper.

Radio Frequency Identification (RFID) Network System and Method

Abstract: A bidirectional radio frequency identification (RFID) network system and method are presented. The system allows users to configure, monitor, and manage different sensor devices by using a graphical user interface real-time. The reconfiguration is done through a network management computer at the top system level that receives user input, generates code images according to the user input, and appropriately routes the code images to sensor routers that directly control the sensors. If the system is multi-layered, some code images are also sent to the intermediate-level network management computers. The system allows users to not only monitor a business flow but react to problematic situations quickly by adjusting the workflow. The aspect-oriented nature of the system allows users to reconfigure the system based only the Functionality aspects without worrying about the Partitioning aspects (e.g., how the network and the sensors are physically connected).

Software defined mobile networks: concept, survey, and research directions

Abstract: This article provides a brief overview on the current development of software-defined mobile networks (SDMNs). Software defined networking is seen as a promising technology to manage the complexity in communication networks. The need for SDMN comes from the complexity of network management in 5G mobile networks and beyond, driven by increasing mobile traffic demand, heterogeneous wireless environments, and diverse service requirements. The need is strong to introduce new radio network architecture by taking advantage of software oriented design, the separation of the data and control planes, and network virtualization to manage complexity and offer flexibility in 5G networks. Clearly, software oriented design in mobile networks will be fundamentally different from SDN for the Internet, because mobile networks deal with the wireless access problem in complex radio environments, while the Internet mainly addresses the packet forwarding problem. Specific requirements in mobile networks shape the development of SDMN. In this article we present the needs and requirements of SDMN, with particular focus on the software-defined design for radio access networks. We analyze the fundamental problems in radio access networks that call for SDN design and present an SDMN concept. We give a brief overview on current solutions for SDMN and standardization activities. We argue that although SDN design is currently focusing on mobile core networks, extending SDN to radio access networks would naturally be the next step. We identify several research directions on SDN for radio access networks and expect more fundamental studies to release the full potential of software-defined 5G networks.