研究発表

—This paper proposes a source-based high-speed wavelength-path protection scheme configuring a tree-shaped backup path in WDM networks. In the proposed scheme, a failure-detecting node on a primary path starts protection by sending a failure notification to a source node of the primary path through the tree-shaped backup path. Intermediate nodes on the backup path and the source node which receive the failure notification switch to the backup path autonomously. Therefore, the proposed scheme provides high-speed protection. The simulation results revealed that the proposed scheme reduces the failure-recovery time compared with the conventional protection schemes.

次世代メトロ/アクセス統合網であるエラスティックλアグリゲーション網(EλAN)が提案されている. 本稿では, 有線光網であるEλANにおける大規模災害時の救済を実現する光アドホックネットワーク実現手法を提案する.

次世代メトロ/アクセス統合網であるエラスティックλアグリゲーション網(EλAN)が提案されている. 本論文では, 有線光網であるEλANにおける大規模災害時の救済を実現する光アドホックネットワークを実現するためのキー装置となるリモートONUの構成手法を提案する.

本論文では頻繁な経路変更に対応するために，光回線直結を用いるデータセンターアーキテクチャを対象に，10−9s 単位での切り替えが可能なPLZT Plomb Lanthanum Zirconate Titanate) 光スイッチを導入した光回線交換データセンターアーキテクチャを提案した．また，PLZT 光スイッチを用いた光回線交換通信を行うために，TDM(Time Division Multiplexing) 型光回線多重による帯域割り当てを提案した．計算機シミュレーションを用いて評価した結果，提案手法は従来手法のアーキテクチャと比較して光回線利用効率を 向上させ，消費電力を最大で45%削減することを示した．

WebRTC に P2P で取引されるデータに対する課金機能をそれぞれ追加拡張して課金情報の管理可能なプラットフォームを提案する.提案したプラット フォームを用いて実際にデータ取引および課金を行い,レイテンシーと課金の整合性について結果を示す

本論文では家庭用太陽光発電所の発電出力予測手法とサービ スを提案する.小型太陽光パネルを用いた実験環境での予測値と発電の実測値の比較や,機械学習の成熟度について の結果を示す

CCN) において, コンテンツの配置場所はユーザからのコンテンツアクセス速度に大きく影響する. また, コンテンツ同士の関連性を利用して構成されるリンクドコンテンツの最適配置を実現することで, さらなるアクセス速度の向上が見込める. しかし, 複数コンテンツの最適配置問題はNP完全とされており, 計算時間が膨大になるという問題点がある. 脳や生体の制御に用いられているゆらぎ制御は, 複雑な問題に対して効率よく解を発見可能であることが知られている. 本論文では, ゆらぎ制御がリンクドコンテンツ配置問題に適応可能かどうかを検討した結果を報告する.

NICT委託研究エラスティック光アグリゲーションネットワークの研究開発における慶應義塾大学の取り組み紹介

The recent development of network technologies that offer centralized control of explicit routes opens the door to the online optimization of explicit routing. For this kind of Traffic Engineering optimization, raising the calculation speeds by using multi-core processors with effective parallel algorithms is a key goal. This paper proposes an effective parallel algorithm for General purpose Programming on Graphic Processing Unit (GPGPU); its massively parallel style promises strong acceleration of calculation speed. The proposed algorithm parallelizes not only the search method of the Genetic Algorithm, but also its fitness functions, which calculate the network congestion ratio, so as to fully utilize the power of modern GPGPUs. Concurrently, each execution is designed for thread-block execution on the GPU with consideration of thread occupancy, local resources, and SIMT execution to maximize GPU performance. Evaluations show that the proposed algorithm offers, on average, a nine fold speedup compared to the conventional CPU approach.

Elastic Optical Networks (EONs) enable optical circuits to be assigned distinct numbers of spectrum slices. Individual circuits can then be assigned an optimal number of slices to best match their target transmission rates. A well-known drawback of EONs is spectrum fragmentation and its resulting uneven blocking probability, which circuit requests experience when the available spectrum slices in the fiber are insufficient or not contiguous. Capturing this spectrum fragmentation problem analytically is a challenging problem. Not surprisingly, most of the existing studies at this time mainly use simulationbased techniques to quantify blocking probability in EONs. In this paper, the authors present a Markov Chain (MC) model that attempts to characterize the fragmentation problem in a simplified scenario, i.e., only two types of circuit services are allowed over a single fiber link. Despite its limited scope, this initial analytical effort is able to accurately capture the nonmonotonic behavior of the blocking probability in EONs for the first time.

This paper proposes a new two-wavelength design for large-enterprise access links. The goal of this design is to lower power consumption and equipment costs without having a significant impact on performance. In our design, one wavelength is used as part of a lower-rate static circuit for general-purpose IP traffic, while the second wavelength is dynamically configured into a high-rate circuit for large dataset transfers whenever needed. A few provider-router ports are shared among a larger number of customers given that large dataset transfers are relatively infrequent. This leads to potential start-time delays, but results in significant power and cost savings. Using analytical models, we provide a quantitative power-and-cost comparison of our dynamic solution with the static always-on high-rate single-circuit solution used currently. The number of shared provider-router ports is kept large enough based on the number of customers to ensure that the probability of start-time delay exceeding a threshold is less than 1%.

我々は, TE (Traffic Engineering)によりトラヒックを集約しネットワーク機器のポート単位での電源on/offによる省電力化を目指すMiDORi(Multi-(layer, path, and resources) Dynamically Optimized Routing)ネットワークに対して, Energy Efficient Ethernet (EEE)の省電力技術の仕組みの一つであるLPI (Low Power Idle)技術を適用することでより一層の省電力化を可能とする「LPI電力特性を考慮したパス再割り当て手法」を提案している. 提案手法は, パス経路変更を行うことにより, リンク使用率の高いリンクと低いリンクに二極化させ, 消費電力を削減するものである. 本論文では, 日本の現状に即したモデルであるJapan Photonic Networks (JPN)に対して, LPI電力特性を考慮したパス再割り当てアルゴリズムを適用した場合の提案手法の特性評価結果を報告する.

On most campus networks, outdated computational resources are not used. This paper proposes a Hadoop-based resource allocation scheme for leveraging these outdated resources. The proposed scheme splits a computational job into tasks using appropriate splitting ratios based on computer processing performance and network resource availability. We compare our resource allocation scheme with a conventional scheme, which divides a job equally without consideration of computer processing performance and network resource availability. Both experiments and simulations are used to compare our proposed scheme and the conventional scheme. Simulation results show that the proposed scheme outperforms the conventional scheme in terms of job execution time.

In Smart Grid, renewable energy such as photovoltaic power and wind power has been rapidly introducing. Then, the power grid has been shifting from the tree 1:N structure with centralized power plants to the N:M structure with various kind of power resources. In this case, to realize matching control among N supply resources including unstable renewable energy and M consumers, the scalable real time matching method is necessary. In this paper, we propose a novel scalable real time matching algorithm to reduce the transmission loss by distributed P2P communication that is the P2P Interactive Agent eXtensions (PIAX) platform. Then, we show that the proposed method utilizing PIAX enables the real time matching and can reduce the transmission loss similar as centralized control method.