Decentralised approaches for network management
ACM SIGCOMM Computer Communication Review
Models and support mechanisms for distributed management
Proceedings of the fourth international symposium on Integrated network management IV
Evaluating Management Decisions via Delegation
Proceedings of the IFIP TC6/WG6.6 Third International Symposium on Integrated Network Management with participation of the IEEE Communications Society CNOM and with support from the Institute for Educational Services
Active networks: Applications, security, safety, and architectures
IEEE Communications Surveys & Tutorials
Mobile agents for network management
IEEE Communications Surveys & Tutorials
Delegated agents for network management
IEEE Communications Magazine
Active networks for efficient distributed network management
IEEE Communications Magazine
| Hi-index | 0.00 |
As a solution to the lack of scalability of the centralized management paradigm, the distributed management paradigm has been introduced. In the paradigm, on the basis of active nodes in active networks, management scripts are downloaded to and executed on managed systems. The paradigm, however, contains a serious and unsolved issue that ill-balanced of system load over a network is caused by unexpected amount of the management scripts added on the systems' own tasks. Therefore, considering network resource utilization, how to distribute and place the management scripts in an appropriate manner is a significant issue to be studied in order to hold the balance of the management tasks in the overall network. For a solution to the issue, we propose a new dynamic load-balancing algorithm for distributed management in active networks. The decision on which systems to execute the management scripts is dynamically made on the basis of the deviation from the average CPU utilization of all the systems and the bandwidth needed for executing all the management scripts. We theoretically show how to find optimal values for a tolerable deviation and a maximum tolerable bandwidth for the better load-balancing. We evaluate the proposed algorithm by applying it to an operational LAN. The results show that the proposed algorithm performs so well with a trivial overhead that it can hold the balance among management tasks in an overall network. The proposed algorithm could be one of the essential techniques enabling the distributed management paradigm more promising.