Takayuki Kushida

Sensor-Cloud Infrastructure - Physical Sensor Management with Virtualized Sensors on Cloud Computing

Increasing numbers of physical sensors are used for various purposes. Those physical sensors are usually used by their own applications. Because each application manages both of physical sensors and their sensor data exclusively, other applications cannot use the physical sensors in the different party easily. We propose a new infrastructure called Sensor-Cloud infrastructure which can manage physical sensors on IT infrastructure. The Sensor-Cloud Infrastructure virtualizes a physical sensor as a virtual sensor on the cloud computing. Dynamic grouped virtual sensors on cloud computing can be automatic provisioned when the users need them. The approach to enable the sensor management capability on cloud computing. Since the resource and capability of physical sensor devices is limited, the cloud computing on the IT infrastructure can be behalf of the sensor management such as availability and performance of physical sensors. This paper describes the design of Sensor-Cloud Infrastructure, the system architecture and the implementation.

A New Model of Accelerating Service Innovation with Sensor-Cloud Infrastructure

Cloud computing service is a model of a shared network-delivered service in which users focus only provided services and need not worry about the implementation of the services. The service model and life cycle become changing by cloud computing service. The paper proposes a new type of approach to accelerate the service innovation with Sensor-Cloud Infrastructure which provides IT resources and sensors as cloud computing service. Service provider prepares service templates. Service requesters can get service instances quickly when they require. Service requesters can use service instances themselves or extend service instances for creating new services. This paper describes a service model with the Sensor-Cloud Infrastructure, accounting, service life cycle and service innovation with use case scenarios.

Multi Cloud Management for unified cloud services across cloud sites

Recently, there is appearing a multi Infrastructure as a Service (IaaS) cloud site environment. It makes server users/administrators annoying because each cloud site is managed separately by each cloud owner and they have to make use of cloud sites individually. In this paper, we propose the Multi Cloud Management Platform that locates between cloud users and cloud sites and provides unified cloud services. It can decrease workloads of server users/administrators under a multi IaaS cloud site by a service catalog federation, a collaborative management, and an application virtual server migration services. We implement a prototype system, and show our approach is feasible.

Global digital museum: multimedia information access and creation on the Internet

Multimedia information access on the Internet creates a new paradigm for museum information and education service that complements conventional school programs. We designed and developed the Global Digital Museum to permit easy access to the cultural heritage stored in museums around the world. The system provides a single virtual museum, enabling global search and edit of museum contents on the Internet. We applied the Global Digital Museum model to K-12 museum education by using real museum multimedia data. Technical issues addressed include: 1) unified and global access to heterogeneous and distributed multimedia contents of museums; and 2) interactive editing of the contents on the World-Wide Web. We describe the concept of Global Digital Museum, the system and network architecture, the data model for museum infomlation, and implementation of a prototype system on the Internet.

Research note: An empirical study of the characteristics of Internet traffic

Traffic engineering for packet-switched networks is important in terms of both network managements and future network managements and future network planning. A common methodology for traffic measurement should be established to facilitate understanding of the characteristics of individual networks. This paper describes the design and development of a system for measuring Internet traffic and the characteristics of this traffic. Results obtained with the system for the backbone traffic are given several parameters such as the number of packets, the volume of data transmitted, the connection time, the starting time, the connection interval and the number of retransmitted packets. Since it is proved that the above results are obtained from the backbone traffic, the proposed approach can be applied to the Internet in general.

Total Energy Management System for Cloud Computing

Reducing the energy used in Cloud Computing is an important issue a sustainable society. There are many existing approaches for reducing energy use in data centers, but new approaches are needed in case of energy management of Cloud Computing. Cloud Computing involves decentralized data centers, so new flexible way for collecting energy consumption data becomes quite important. Many current approaches focus on reducing energy consumption by air handling equipment, however energy from IT resources also need to be optimized for a total energy management of Cloud Computing. For advanced energy management for Cloud Computing, we developed a Cloud energy management system with sensor management functions, with an optimized VM allocation tool to minimize energy consumption at multiple data centers. Our evaluations showed more than a 30% energy savings for the servers in our experimental environment. Our system can be extended to optimize energy usage from various perspectives, such as for minimizing electricity bills or carbon emissions.

The traffic measurement and the empirical studies for the Internet

The traffic engineering for a packet switched network such as the Internet is important for the network management and the future network plan. The investigation method for the traffic measurement should be build to understand the characteristics of the network. This paper describes the measurement system for the Internet traffic and shows some aspects of the Internet with the system. The results show some aspects of TCP sessions such as the number of packets, amount for transmission, connection time, the starting time, connection interval and retransmission of packets. The self-similar test for the traffic of the TCP and UDP were also done with the variance time plot and they were self-similar traffic.

Empirical study of inter-arrival packet times and packet losses

A packet switched network such as the Internet provides only the best-effort service for users. Recent studies of the characteristics of packet arrival on a packet switched network have shown a self-similar property with long-range dependence, and also show a heavy-tailed distribution. This paper investigates end-to-end performance of the Internet empirically. It focuses on the inter-arrival process of packets and the property of packet loss between end-to-end hosts. We show that both the inter-arrival process and loss events are self-similar with a long-range dependence property. The inter-arrival process of packets has a heavy-tailed distribution which sums up the difference of all queues in intermediate routers.

Study on an inter-organization activity based on the Internet traffic

A traffic analysis on the Internet has an advantage for obtaining the characteristics of transferred packets. There were many studies to understand the characteristics of the Internet traffic with mathematical statistical approach. The approach of this study is different front previous studies. It focuses on studying the traffic analysis with the framework of knowledge extraction. The measurement results of traffic capturing on the backbone network is applied to the inter-organization activity on the Internet. It shows that the proposed framework can be useful for the experiment results.

Industry Cloud - Effective Adoption of Cloud Computing for Industry Solutions

Many enterprises in industries start using Cloud Computing for their IT infrastructure services. This adoption of Cloud Computing is a part of the enterprise transformation which is the migration from a legacy IT environment to Cloud Computing. On the other hand, one of major targets is an industry solution which provides a critical business service to their end customers. This paper proposes Industry Cloud which is the enhanced design of Cloud Computing for industry solutions. It efficiently supports industry solutions for enterprise business requirements. The paper describes Industry Cloud with a requirement analysis of industry solutions, those adopted functions, and three use case scenarios in the electronics and retail industry. The contribution of the paper is the analysis of industry wide requirements, the definition of Industry Cloud with a common function among industry solutions and the usage with use case scenarios.