An Agent-based Network Management System Using Active Information Resources

An expert network administrator is not always stationed as disasters happen. In that case, it is desirable that a novice administrator is capable of taking part in network recovery operations as well. In this paper, an agent-based network management system in emergency situations is presented. We use the Active Information Resource based Network Management System (AIR-NMS) to relieve the human administrator from parts of her management tasks and present an interface that remotely can control this management system. The effectiveness of the system is demonstrated by experiments using a prototype system. Key words: Active Information Resource (AIR), Network Management System, Knowledge-based Autonomous System, Multiagent System, Disaster Recovery. 1. I NTRODUCTION we have proposed an Active Information Resource (AIR) [4] Network systems have evolved fast and are now both sophisticated and complicated. Therefore, network administrators must have an advanced and broad knowledge in network management in order to operate and maintain their network. At the time of the Great East Japan Earthquake in 2011, network services like IP phone and e-mail were instantly discontinued and network administrators had to repair and restart their networks to get them up running again. However, expert administrators are not always stationed and large and complex networks are likely to have short-handed experts. Hence, it is desirable to make novice administrators also capable of taking part in network recovery operations. An interesting solution to this problem is to implement a network management system (NMS), where intelligent software agents [1] are applied. By automating some management tasks, NMSs can reduce the burden for network management. Most traditional NMSs [2,3] are able to gather network status information and detect faults automatically, but identifying the cause of a fault and recover it is one of the most difficult tasks for novice administrators, since they lack the expertise. In order to solve this problem of the traditional NMS, based NMS, called AIR-NMS [7]. The AIR-NMS consists of two types of AIRs, I -AIR and K AIR, where the former measures status information of various network equipment, and the latter controls network management heuristics of human administrators. In this paper, we introduce a study on a knowledge based support method for autonomous service operations in emergency situations. A mobile network module called ICT unit, which is placed at a suffering area in an emergency situation and provides network services for users in the area, is introduced in this study. Using the ICT units, the network services of the damaged network are able to recover rapidly. To maintain stable operation of ICT units, an intelligent management function of ICT units takes important role. We realize this function based on the AIR-NMS concept to reduce the burden for administrators and to enable even novice administrators to operate complex network services. In Section 2, the concept of the AIR-NMS is introduced. In addition, problems of applying the existing AIR-NMS to ICT units are described. In Section 3, the knowledge-based support scheme using an improved AIR-NMS is explained. The experiments using a prototype system are demonstrated in Section 4. Finally, the conclusion is presented in Section 5. Manuscript received: Sept. 09, 2013 / revised : Nov. 20, 2013 Corresponding Author: kino@riec.tohoku.ac.jp Tel: +81-22-217-5415, Fax: +81-22-217-5415 RIEC, Tohoku University. Japan.