Hideki Okita

Distributed Cache System for Large-Scale Networks

Network traffic has been rapidly increasing in proportion along with the spread of broadband access networks. The traffic of the core network is predicted to exceed its transmission capability in the near future. Therefore, we propose a centrally controlled cache system with distributed cache storage in the access network. In this system, a cache control server manages a list of all contents cached by multiple cache servers. It can provide content requested by a user if it is cached in any of the cache servers in the access network. Additionally, it can reduce network traffic between the core network and the access network if the requested contents are cached in the cache server of the access network. We examine issues for the implementation of our system, and describe a prototype system. As a result of evaluation of the system, we have made it clear that our system architecture is suitable for an access network that accommodates one million users

Per-Subscriber On-Demand QoS Assurance in Distributed Web Cache System

A large number of subscribers and massive amount of Web content have caused an increase in the access network load of network service providers. To address this problem, various systems, such as a Web cache system, have been developed to enhance WWW service. In this article, we propose a per-subscriber QoS-assurance web cache system that is based on an added QoS assurance function to a distributed Web cache system (DCCS). The proposed system executes QoS configurations selectively for the flows of premium subscribers who have contracted for QoS assurance services. The proposed system selects premium subscribers by cooperating with the AAA function of the access network. The number of QoS flow entries is suppressed by means of dynamic selection of target routers in the QoS configuration. Also, the system controls increases in system load by selecting targets of QoS configuration in accordance with content size. By this means, we can construct a QoS-assurance Web cache system applicable for large scale access networks with a large number of subscribers. In this article, we evaluated scalability of the proposed system from two points of view, the number of QoS flow entries registered on each router and the control load of the QoS configuration device. We determined that the proposed system has sufficient scalability for access networks with the capacity for one million subscribers including 10% premium subscribers

Proposal and Evaluation of Data-Model Translation for Server-Virtualization Environment to Improve Virtual-Network Configuration Management

To reduce the operational load of virtual-network operation in data centers that contain server virtualization platforms and network switches provided by multiple vendors, it would become the challenge to ease management of configurations which are different among server-virtualization environments. This paper proposes a new data-model translation method to unify data-model among multiple configurations of server-virtualization platforms. As the result of evaluation with 24 virtual machines, data-model translation overhead was less than 10% of the time to acquire virtual-machine configuration, and the network management system took 80.5 s to generate configuration information for the overall system. These results indicate that the proposed method is effective to improve the efficiency of configuration management of virtual networks.

A practical approach for network fault detection

Todays fault detection in commercial networks is still done in an inefficient way with alarms and threshold violations that treat measured indexes separately. To provide a practical network fault detection approach for the actual network operation, we investigate many actual network fault occurrences, and discover that many network faults can be characterized by unbalanced variation among measured network indexes that occur prior to or during an network fault occurrence. According to this general model of network fault, we propose a practical method for network fault detection that automatically extracts the unbalanced variation among measured indexes without the necessity of recognizing the physical meaning of them. Our evaluation shows that the proposed approach is applicable for the majority of measured indexes in the commercial networks, is efficient and scalable in performance, and with acceptable detection accuracy.

Proposal of virtual network configuration acquisition function for data center operations and management system

Virtualization technologies have been widely deployed in data centers to improve the system utilization. However, they cause increased workload for operators to clarify the structure of virtual networks in data centers. To reduce the operation time, this paper provides the virtual-network management system which automates the integration of the configurations of the virtual networks. The proposed system collects the configurations from server virtualization platforms and VLAN-supported switches, and integrates these configurations according to the newly developed XML-based management information model for virtual-network configurations. The preliminary evaluations show that the proposed system helps to reduce the time to collect and update the configurations by about 40 percent. This result implies that the proposed system is effective for improving the configuration management process for virtual networks in data centers.