This paper presents a distributed power control scheme for next-generation multiservices CDMA systems. CDMA has inherent capability to control the quality-of-service (QoS) requirements by assigning different power levels to each traffic type. Toward this, optimum power control schemes have been investigated. The main drawback of the previously proposed algorithms is that they would require all users' transmission state necessiating a complicated control process or peak-rate badnwidth allocation. To overcome this, we exploit the Markovian property to obtain the statistics of the traffic. The statistical formulation is presented for allocating power distributedly so as to keep the "collision" probability below a predefined probability. Numerical examples show that the distributed power control scheme allows better utilization of wireless resources through statistical multiplexing than peak-rate bandwidth assignment, and it does not require a complicated control process while keeping total transmitted power at slightly greater than optimum power control.

As use of the Internet continues to spread rapidly, Traffic Engineering (TE) is needed to optimize IP network resource utilization. In particular, load balancing with TE can prevent traffic concentration on a single path between ingress and egress routers. To apply TE, we have constructed an MPLS (Multi-Protocol Label Switching) network with TE capability in the JGN (Japan Gigabit Network), and evaluated dynamic load balancing behavior in it from the viewpoint of control stability. We confirmed that with this method, setting appropriate control parameter values enables traffic to be equally distributed over two or more routes in an actual large-scale network. In addition, we verified the method's effectiveness by using a digital cinema application as input traffic.

Fairness as defined in wireline network cannot be achieved in wireless packet networks due to the bursty and location-dependent channel errors of wireless link. Channel-state dependent scheduling and compensation mechanism for errored flows are generally employed to improve the fairness in wireless packet scheduling algorithms. Most of the wireless scheduling algorithms, however, have two common significant problems. One problem is that they operate incorrectly unless all flows have the same packet size. This is due to the incorrect lead-and-lag model and the swapping-based rough compensation mechanism of the algorithms. The other problem is the degradation of error-free flow during compensation. The root of the degradation is that the bandwidth for compensation cannot be reserved since it is very difficult to predict. In this paper, we introduce WGPS (Wireless General Processor Sharing) to define fairness in wireless networks and present PWGPS as a packetized algorithm of WGPS. In our method, lead and lag of all flows are defined in terms of virtual time which is flexible enough to deal with packet size differences. Further, compensation is done by increasing the service share of the errored flow to a predetermined amount Δ. This enables the maximum bandwidth for compensation can be estimated and thus reserved. Our method can be proved to achieve improved fairness as compared with the previous scheduling algorithms.

In the future network, optical technology will play a stronger role not only for transmission but also for switching. Optical burst switching (OBS) emerged as a promising switching paradigm. It brings together the complementary strengths of optics and electronics. This paper presents the design and implementation of an overlay mode burst-switched photonic network testbed, including its architecture, protocols, algorithms and experiments. We propose a flexible "transceiver + forwarding" OBS node architecture to perform both electronic burst assembly/disassembly and optical burst forwarding. It has been designed to provide class of service (CoS), wavelength selection for local bursts, and transparency to cut-through bursts. The functional modules of OBS control plane and its key design issues are presented, including signaling, routing, and a novel scheduling mechanism with combined contention resolution in space and wavelength domains. Finally, we report the experimental results on functional verification, performance analysis and service demonstration.

Decentralized and unstructured peer-to-peer (P2P) networks such as Gnutella are attractive for large-scale information retrieval and search systems because of their scalability, fault-tolerance, and self-organizing nature. Because of this decentralized architecture, however, traditional P2P keyword search systems are difficult to globally share useful semantic knowledge among nodes. As a result, traditional P2P keyword search systems cannot support semantic search (support only naive text-match search). In this paper, we describe a design of the semantic P2P keyword search system. We exploit the semantics of correlation among keywords rather than synonym. The key mechanism is query expansion, where a received query is expanded based on keyword relationships. Keyword relationships are improved through search and retrieval processes and each relationship is shared among nodes holding similar data items. This semantic P2P search system has two main advantages. First, expanding search results through query expansion increases the possibility of locating desired data items which would not be found by traditional P2P search systems due to the keywords' textual mismatch. Second, keyword relationships originally introduced for query expansion, can be used for result ranking. Our main challenges are 1) managing keyword relationships in a fully decentralized manner and 2) maintaining the quality of search results, while suppressing result implosion. We also describe the prototype implementation and evaluation of the semantic P2P search system.

DANSE (Dynamically Adaptive Networking Service Environment) is a new architecture for adaptive network service systems. In this paper, a framework for context-aware service construction based on DANSE architecture is presented. In DANSE, any hardware, software, information, and services that are available on a network are treated as network resources. DANSE coordinates the construction of an end user's service based on the user's requests and situation or context (i.e., user's location, schedule, co-workers, etc.). To provide users with satisfactory services, it monitors user context continuously and searches for network resources that are convenient for a target user. Moreover, it detects changes in user context and invokes service construction if needed. If the desired service is not available, alternative services are automatically constructed. With those capabilities, DANSE enables ubiquitous provision of services any time, anywhere.

We have designed a scalable and expressive naming system called SENS, capable of retrieving information of computing and content resources distributed widely across the Internet through exact queries and multi-attribute range queries over resource names. Our system utilizes a descriptive naming scheme to name resources and a multi-dimensional resource ID space for message routing through an overlay network of name servers (NSs). The resource ID space is constructed on the overlay network based on CAN routing algorithm. Our novel mapping scheme between resource names and resource IDs preserves resource ID locality while still achieving good load balancing regarding resource information distribution. We also propose a multicast routing algorithm to deliver resource information and a broadcast routing algorithm to route query messages to corresponding NSs with small cost of message transmission. Our simulation results show that our system can achieve good routing performance and load balancing.

Application-level multicast (ALM) is a novel technology for multipoint applications, such as large scale file distribution, video and audio streaming, and video conferencing. Although many ALM mechanisms or algorithms have been proposed, all the multicast functions have been independently developed and integrated into individual applications. In such a situation, the development of ALM applications includes a lot of redundancy. Our goal is to improve the efficiency of developing ALM applications by reducing the development redundancy and to provide application developers with a middleware on which various ALM applications can be efficiently developed with minimum efforts. To this end, we develop a functional unit oriented ALM middleware, namely RelayCast. RelayCast provides a minimum but fundamental set of functionality as a functional unit, and constructs the basis on which additional and specific functions (i.e. codec, video capture, etc.) for each application are implemented. Some functional units contain several components with different algorithms, and RelayCast meets the requirements of various applications by choosing the appropriate component. In this paper, we propose RelayCast architecture, and present the implementation and experiments of a prototype.

Burst switched WDM optical networks are coming up as suitable network architectures for future Optical Internet backbones. However, the lack of optical processing capabilities results in increased burst blocking probability, which in turn lead to very limited network performance. Efficient contention resolution algorithm is therefore necessary. In this paper, we propose a distributed wavelength assignment algorithm named Priority-based Wavelength Assignment (PWA) for such networks. Each node selectively assigns wavelengths based on the wavelength priority information "learned" from its wavelength utilization history in a distributed manner. As the learning process progresses, nodes in the same part of the network tend to assign different wavelengths to avoid contentions. Simulation results show that the PWA can effectively reduce the blocking probability and increase the performance of burst optical networks compared to previous algorithms such as random assignment.

With the proliferation of various types of computing and networking resources in ubiquitous computing environments, an architecture allowing mobile users to flexibly access these resources is desirable. We have focused our attention on the access link resources of devices surrounding users. Our framework named Personal Mesh allows personal devices to seamlessly access the Internet via appropriate access links available in a personal area network. The Personal Mesh deals with two technical issues: access link selection management and a PAN mobility support mechanism. In this paper, we describe the design and implementation of Personal Mesh and show the effectiveness of our system by experiment.

Layered multicast approach enables IP multicast to adapt to heterogeneous networks. In layered multicast, each layer of a session is sent to separate multicast groups. These layers will be transmitted on the same route, or on different routes. However, traditional congestion control schemes of layered multicast do not consider the case when layers of a session are transmitted on different routes. In this paper, at first we show that in sparse-mode routing protocols like PIM-SM and CBT, layers of a session can be mapped to different Rendezvous Points or cores due to the bootstrap mechanism. It means that layers of a session can be transmitted on different routes. We then show that traditional congestion control schemes of layered multicast do not work properly in sparse-mode routing regions. At last we introduce Rendezvous Point based Layered Multicast (RPLM), a novel congestion control scheme suitable for sparse-mode routing regions, and show that RPLM works efficiently in regions using sparse mode routing protocols. RPLM uses per-RP packet loss rate instead of the overall one to detect congestion on each route, and can react to congestion quickly by dropping the highest layer on the congested route. In addition, RPLM simultaneously drops all the layers those are useless in quality's improvement to prevent bandwidth waste.

In this paper, we introduce a concept of minimum bandwidth guaranteed service model for mobile multimedia. In this service model, service is defined in the context of the guaranteed minimum bandwidth and the residual service share. Each flow under this service model is guaranteed with its minimum bandwidth and provided with more in proportion to the residual service share if there is leftover bandwidth. The guaranteed minimum bandwidth assures a flow to keep minimum tolerable quality regardless of the network load, while the leftover bandwidth enhances the quality of service according to the application's adaptivity and the user's interest. We show that the minimum bandwidth guaranteed service model could be implemented by a two-folded wireless packet scheduler consisting of a guaranteed scheduler and a sharing scheduler. Wireless channel condition of each flow is considered in scheduling so that wireless resource can be distributed only to the flows of good channel state, improving total wireless link utilization. We evaluate the service model and the scheduling method by simulation and implementation.