Michihiro Aoki

PopCache: Cache more or less based on content popularity for information-centric networking

Due to a mismatch between downloading and caching content, the network may not gain significant benefit from the sophisticated in-network caching of information-centric networking (ICN) architectures by using a basic caching mechanism. This paper aims to seek an effective caching decision policy to improve the content dissemination in ICN. We propose PopCache-a caching decision policy with respect to the content popularity-that allows an individual ICN router to cache content more or less in accordance with the popularity characteristic of the content. We propose an analytical model to evaluate the performance of different caching decision policies in terms of the server-hit rate and expected round-trip time. The analysis confirmed by simulation results shows that PopCache yields the lowest expected round-trip time compared with three benchmark caching decision policies, i.e., the always, fixed probability and path-capacity-based probability, and PopCache provides the server-hit rate comparable to the lowest ones.

Impact of Tohoku earthquake on R&E network in Japan

The Internet is one of the important infrastructures in our daily life, and its highly distributed and autonomous natures have been said to be robust against failures. This paper reports an impact of an unexpectedly large earthquake (M9.0) hit to the northern part of Japan at 14:46:18 on 11th March (UTC+9), 2011(the East Japan Earthquake) [2] on a nation-wide research and education network (SINET4 [10, 12, 13]) in Japan. We show that the network managed to run even after the earthquake thanks to two different levels of redundancies, though some physical links were damaged; consequently, the impact on the routing (both BGP and OSPF) was insignificant. At the epicenter area, some network nodes (i.e., universities) were disconnected from the network by the blackout upto 70 hours. In the view of long-term traffic trend, it took 5--6 weeks for recovery of the traffic volume there. On the other hand, in the backbone network, the rapid decrease (40--50%) in the traffic volume only lasted for a few hours due to the blackout near the epicenter, and the impact of the traffic decrease in the epicenter area on the backbone traffic is estimated to 15--25%. Furthermore, we confirmed the increases of the traffic generated by users who rushed to access to the network for obtaining up-to-date information and videostreams.

ATCA-Based Open-Architecture Router Prototype

We have developed an open-architecture router (OAR) prototype using industrial standard hardware, software components, and interfaces. The prototype is built with Advanced Telecom Computing Architecture (ATCA)-compliant hardware. Carrier-grade Linux (CGL) is used as the operating system. A new OAR configuration method is described where industrial standard hardware and software interfaces are used. Basic forwarding functions with routing protocol processing are demonstrated for the first time.

Functionally distributed transport networking on Next-Generation Network

Traffic in IP networks has increased and services have diversified over the last few years. IP networks need to have scalability and high-quality data transmissions and they must be able to incorporate new functions. For good processing performance and ease of adding functions to the transport stratum on a next-generation network (NGN), we have proposed a functionally distributed transport networking architecture that separates the control-plane processing part (control element, CE) from the forwarding plane processing part (forwarding element, FE) of the router. In this architecture, the CE is mounted on a general-purpose server platform, and one path-control process in the CE consolidates and processes the path computations and the path settings for two or more routers. The functions and performance of the CE are easily upgraded. Moreover, a particular CE computes the path for an entire network by using the single network-integration path-control method that treats each sub-network as one router. This leads to efficient operation of a large-scale network. In this paper, we argue that the issues of our architecture could be bottleneck factors for the path computational performance in a large-scale network and we predict the influence of these factors by using a simulation environment.

A multi-layer disjoint path selection algorithm for highly reliable carrier services

In this paper, we consider a mechanism for providing path protection in multi-region networks. Here a region includes an interior gateway protocol (IGP) area, an autonomous systems (AS) and a layer network. Many path protection schemes have been proposed, but most of them have been focused on a protection mechanism within a region network. We thus propose a mechanism for providing inter-region protection, which is used for highly reliable carrier services. We also point out inter-region protection schemes are remarkably effective in improving end-to-end reliability. The key to our proposal lies in a multilayer disjoint routing algorithm, called MLD, that enables us to find multi-layer protection paths. We investigated the performance of our scheme through extensive simulations, and the simulation results show that our approach is sure to find a set of failure-independent paths while achieving better utilization of network resources.

On incentive-based inter-domain caching for content delivery in future internet architectures

Leveraging in-network caching of proposed future network architectures such as content-centric networking (CCN) encourages users and ISPs to enjoy performance improvements of networks. However, we raise an argument against a rule of thumb stating that more content storage is better since business relationships in inter-domain networks are based on profit negotiations rather than an efficiently deployed network architecture. The objective of this paper is to identify the optimal cache allowance for a caching mechanism in CCN in inter-domain networks. We propose an incentive model for ISPs and analyze their maximum profits by studying the effects of cache allowance in their routers. The results confirmed from our analysis indicate that the minimum expected round-trip time can be achieved by deploying the maximum cache allowance in all routers. In contrast, the maximum cache allowance in the router connected to clients and the minimum cache allowance in the gateway router of an ISP that connects to the clients provides the maximum profit to that ISP. On the other hand, the maximum cache allowance in the gateway router of an ISP that is connected to clients and the minimum cache allowance in the router close to the server provides the highest profit to an ISP connected to the server.

Using Ferry Access Points to Improve the Performance of Message Ferrying in Delay-Tolerant Networks

Delay-Tolerant Networks (DTNs) are sparse, wireless networks where disconnections are common due to host mobility and low node density. The Message Ferrying (MF) scheme is a mobilityassisted paradigm to improve connectivity in DTN-like networks. A ferry or message ferry is a special node in the network which has a per-determined route in the deployed area and relays messages between mobile hosts (MHs) which are intermittently connected. Increased contact opportunities among mobile hosts and the ferry improve the performance of the network, both in terms of message delivery ratio and average end-end delay. However, due to the inherent mobility of mobile hosts and pre-determined periodicity of the message ferry, mobile hosts may often ’miss’ contact opportunities with a ferry. In this paper, we propose the combination of stationary ferry access points (FAPs) with MF routing to increase contact opportunities between mobile hosts and the MF and consequently improve the performance of the DTN. We also propose several placement models for deploying FAPs on MF routes. We evaluate the performance of the FAP placement models through comprehensive simulation. Our findings show that FAPs do improve the performance of MF-assisted DTNs and symmetric placement of FAPs outperforms other placement strategies. Keywords—Service infrastructure, delay-tolerant network, message ferry routing, placement models.

Verification of path computational performance in functionally distributed transport networking on next-generation network

Traffic in IP networks has increased and services have diversified over the last few years. IP networks need to have scalability and high-quality data transmissions and they must be able to incorporate new functions. For good processing performance and ease of adding functions to the transport stratum on a next-generation network (NGN), we have proposed a functionally distributed transport networking architecture that separates the control-plane processing part (control element, CE) from the forwarding plane processing part (forwarding element, FE) of the router. In this architecture, the CE is mounted on a general-purpose server platform, and one path-control process in the CE consolidates and processes the path computations and the path settings for two or more routers. The functions and performance of the CE are easily upgraded. Moreover, a particular CE computes the path for an entire network by using the single network-integration path-control method that treats each sub-network as one router. This leads to efficient operation of a large-scale network. In this paper, we argue that the issues of our architecture could be bottleneck factors for the path computational performance in a large-scale network and we predict the influence of these factors by using a simulation environment.

Forwarding model of backplane Ethernet for open architecture router

Diversified IP services have recently required flexible and scalable edge routers to support advanced service functions such as IPsec VPN and application layer firewalls. However, those functions cannot be integrated into existing routers easily, and this prevents required routers from becoming available. A common forwarding model of backplane Ethernet for a router supporting separate control, line, and service cards is proposed in this paper. This model enables an open architecture router that has multivendor control, line, and service cards, where packets are forwarded among them based on a common method of backplane routing. It supports inline, host, and tap service cards. We propose an efficient forwarding decision-making algorithm in terms of the required speed and efficiency of table lookup and demonstrate that the method requires half the table lookup processing resources compared with those of a naive method

Expansion of bandwidth-on-demand capabilities in Japanese academic backbone network

This paper describes the progress made in improving the bandwidth-on-demand (BoD) capabilities of the Japanese academic backbone network called SINET3. Since the start of layer-1 BoD services in 2008, we have expanded the service provision area nationwide, introduced functions to improve the usability in response to user requests, and flexibly managed the network resources by taking into account a hybrid accommodation of the layer-1 and layer2/3 services. We are also approaching layer-2 BoD services for applications requiring a relatively small amount of bandwidth. The current status for layer-1 BoD services and the near-future plan for layer-2 BoD services including the initial implementation image are described.