KINDAI UNIVERSITY


*A space between the first name and last name, please enter

MIZUTANI Kimihiro

Profile

FacultyDepartment of Informatics
PositionLecturer
DegreePh.D in Engineering
Commentator Guidehttps://www.kindai.ac.jp/meikan/2330-mizutani-kimihiro.html
URL
Mail
Last Updated :2020/04/04

Education and Career

Education

  •   2005 04  - 2008 03 , Doshisha University, Department of Engineering
  •   2008 04  - 2010 03 , Nara Institute of Science and Technology, Graduate school of Information Science
  •   2014 10  - 2015 09 , Nara Institute of Science and Technology, Graduate school of Information Science

Academic & Professional Experience

  •   2019 04 ,  - 現在, Faculty of Science and Engineering, Department of Informatics, Kindai University
  •   2018 04 ,  - 2019 03 , Assistant Manager, NTT West
  •   2010 04 ,  - 2018 03 , Researcher, Network Innovation Labs, NTT
  •   2008 09 ,  - 2009 03 , Information-technology Promotion Agency,Japan

Research Activities

Research Areas

  • Informatics, Information networks

Research Interests

  • IoT, Distributed Networking, Artificial Intelligence, Overlay Network

Published Papers

  • Reducing Dense Virtual Networks for Fast Embedding, Toru MANO, Takeru INOUE, Kimihiro MIZUTANI, Osamu AKASHI, IEICE Transactions on Communications, IEICE Transactions on Communications, 103(4), - - -, Apr. 2020 , Refereed
  • Increasing Capacity of the Clos Structure for Optical Switching Networks, Toru Mano, Takeru Inoue, Kimihiro Mizutani, Osamu Akashi, Proc. of IEEE Global Communications Conference (GLOBECOM), Proc. of IEEE Global Communications Conference (GLOBECOM), Dec. 2019 , Refereed
  • Measuring Lost Packets with Minimum Counters in Traffic Matrix Estimation., Kohei Watabe, Toru Mano, Takeru Inoue, Kimihiro Mizutani, Osamu Akashi, Kenji Nakagawa, IEICE Transactions, IEICE Transactions, 102-B(1), 76 - 87, 2019 , Refereed
  • On Intelligent Traffic Control For Large Scale Heterogeneous Networks: A Value Matrix Based Deep Learning Approach, Zubair Fadlullah, Fengxiao Tang, Bomin Mao, Nei Kato, Osamu Akashi, Takeru Inoue, Kimihiro Mizutani, IEEE Communications Letters, IEEE Communications Letters, 22(12), 2479 - 2482, Dec. 2018 , Refereed
  • Action Determination Learning Scheme for Driving Support Considering Signal and Traffic Conditions, 水谷后宏, 吉田学, 秦崇洋, 社家一平, 計測自動制御学会論文集, 計測自動制御学会論文集, 54(11), 793‐801(J‐STAGE), 2018
  • Toward Preventive Network Service Management by Neural Networks., Taichi Kawabata, Takashi Kurimoto, Kimihiro Mizutani, 2018 IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2018, Washington, DC, USA, June 25-27, 2018, 2018 IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2018, Washington, DC, USA, June 25-27, 2018, 125 - 126, 2018 , Refereed
  • A Novel Non-Supervised Deep-Learning-Based Network Traffic Control Method for Software Defined Wireless Networks., Bomin Mao, Fengxiao Tang, Zubair, Md. Fadlullah, Nei Kato, Osamu Akashi, Takeru Inoue, Kimihiro Mizutani, IEEE Wireless Commun., IEEE Wireless Commun., 25(4), 74 - 81, 2018 , Refereed
  • On Removing Routing Protocol from Future Wireless Networks: A Real-time Deep Learning Approach for Intelligent Traffic Control., Fengxiao Tang, Bomin Mao, Zubair, Md. Fadlullah, Nei Kato, Osamu Akashi, Takeru Inoue, Kimihiro Mizutani, IEEE Wireless Commun., IEEE Wireless Commun., 25(1), 154 - 160, 2018 , Refereed
  • Fast packet classification algorithm for network-wide forwarding behaviors., Takeru Inoue, Toru Mano, Kimihiro Mizutani, Shin-ichi Minato, Osamu Akashi, Computer Communications, Computer Communications, 116, 101 - 117, 2018 , Refereed
  • 送信レート制御を行うネットワークにおけるパーフェクトサンプリング, 永田尚志, 井上武, 間野暢, 水谷后宏, 明石修, 電子情報通信学会論文誌 B(Web), 電子情報通信学会論文誌 B(Web), J100-B(12), 1068‐1072 (WEB ONLY), Dec. 2017
  • A Tensor Based Deep Learning Technique for Intelligent Packet Routing., Bomin Mao, Zubair, Md. Fadlullah, Fengxiao Tang, Nei Kato, Osamu Akashi, Takeru Inoue, Kimihiro Mizutani, 2017 IEEE Global Communications Conference, GLOBECOM 2017, Singapore, December 4-8, 2017, 2017 IEEE Global Communications Conference, GLOBECOM 2017, Singapore, December 4-8, 2017, 1 - 6, 2017 , Refereed
  • Towards a Low-Delay Edge Cloud Computing through a Combined Communication and Computation Approach., Tiago Gama Rodrigues, Katsuya Suto, Hiroki Nishiyama, Nei Kato, Kimihiro Mizutani, Takeru Inoue, Osamu Akashi, IEEE 84th Vehicular Technology Conference, VTC Fall 2016, Montreal, QC, Canada, September 18-21, 2016, IEEE 84th Vehicular Technology Conference, VTC Fall 2016, Montreal, QC, Canada, September 18-21, 2016, 1 - 5, 2016 , Refereed
  • Reducing dense virtual networks for fast embedding., Toru Mano, Takeru Inoue, Kimihiro Mizutani, Osamu Akashi, 35th Annual IEEE International Conference on Computer Communications, INFOCOM 2016, San Francisco, CA, USA, April 10-14, 2016, 35th Annual IEEE International Conference on Computer Communications, INFOCOM 2016, San Francisco, CA, USA, April 10-14, 2016, 1 - 9, 2016 , Refereed
  • An efficient framework for data-plane verification with geometric windowing queries., Takeru Inoue,Richard Chen,Toru Mano, Kimihiro Mizutani, Hisashi Nagata, Osamu Akashi, 24th IEEE International Conference on Network Protocols, ICNP 2016, Singapore, November 8-11, 2016, 24th IEEE International Conference on Network Protocols, ICNP 2016, Singapore, November 8-11, 2016, 1 - 10, 2016 , Refereed
  • A Geometric Windowing Algorithm in Network Data-Plane Verification., Richard Chen, Toru Mano, Takeru Inoue, Kimihiro Mizutani, Hisashi Nagata, Osamu Akashi, 36th IEEE International Conference on Distributed Computing Systems, ICDCS 2016, Nara, Japan, June 27-30, 2016, 36th IEEE International Conference on Distributed Computing Systems, ICDCS 2016, Nara, Japan, June 27-30, 2016, 743 - 744, 2016 , Refereed
  • A mobility-based mode selection technique for fair spatial dissemination of data in multi-channel device-to-device communication., Hideki Kuribayashi, Katsuya Suto,Array, Kimihiro Mizutani, Takeru Inoue, Osamu Akashi, 2016 IEEE International Conference on Communications, ICC 2016, Kuala Lumpur, Malaysia, May 22-27, 2016, 2016 IEEE International Conference on Communications, ICC 2016, Kuala Lumpur, Malaysia, May 22-27, 2016, 1 - 6, 2016 , Refereed
  • Efficient Virtual Network Optimization Across Multiple Domains Without Revealing Private Information., Array,Takeru Inoue, Dai Ikarashi, Koki Hamada, Kimihiro Mizutani, Osamu Akashi, IEEE Trans. Network and Service Management, IEEE Trans. Network and Service Management, 13(3), 477 - 488, 2016 , Refereed
  • Living Will for Resilient Structured Overlay Networks., Kimihiro Mizutani, Takeru Inoue, Toru Mano, Osamu Akashi, Satoshi Matsuura, Kazutoshi Fujikawa, IEICE Transactions, IEICE Transactions, 99-B(4), 830 - 840, 2016 , Refereed
  • Stable Load Balancing with Overlapping ID-space Management in Range-based Structured Overlay Networks, MIZUTANI Kimihiro, INOUE Takeru, MANO Toru, AKASHI Osamu, MATSUURA Satoshi, FUJIKAWA Kazutoshi, Computer Software, Computer Software, 32(3), 3_101 - 3_110, 2015 , Refereed
    Summary:Structured overlay networks that support range queries cannot hash data IDs for load balancing, in order to preserve the total order on the IDs. Since data and queries are not equally distributed on the ID-space without hashing in range-based overlay networks, uneven loads are imposed on the overlay nodes. Existing load balancing techniques for range-based overlay networks distribute the loads by using data reallocation or node migration, which makes the networks very unstable due to heavy data reallocation or frequent churn.<BR>This paper proposes a novel scheme that distributes, fairly, the loads without node migration and with little data reallocation, by sharing some ID-space regions between neighboring nodes. Our &ldquo;overlapping&rdquo; ID-space management scheme derives the optimal overlap based on kernel density estimations; the query loads based on the statistical theory are used to calculate the best overlap regions. This calculation is executed in a distributed manner with no central coordinator. We conduct thorough computer simulations, and show that our scheme alleviates the worst node load by 20&ndash;90 % against existing techniques without node migration and with least data reallocation.
  • Testaments for resilient structured overlay networks., Kimihiro Mizutani, Takeru Inoue, Toru Mano, Osamu Akashi, Satoshi Matsuura, Kazutoshi Fujikawa, 21st Asia-Pacific Conference on Communications, APCC 2015, Kyoto, Japan, October 14-16, 2015, 21st Asia-Pacific Conference on Communications, APCC 2015, Kyoto, Japan, October 14-16, 2015, 514 - 518, 2015 , Refereed
  • Virtual Network Embedding across Multiple Domains with Secure Multi-Party Computation., Toru Mano, Takeru Inoue, Kimihiro Mizutani, Osamu Akashi, IEICE Transactions, IEICE Transactions, 98-B(3), 437 - 448, 2015 , Refereed
  • Efficient virtual network optimization across multiple domains without revealing private information., Toru Mano, Takeru Inoue, Dai Ikarashi, Koki Hamada, Kimihiro Mizutani, Osamu Akashi, 23rd International Conference on Computer Communication and Networks, ICCCN 2014, Shanghai, China, August 4-7, 2014, 23rd International Conference on Computer Communication and Networks, ICCCN 2014, Shanghai, China, August 4-7, 2014, 1 - 8, 2014 , Refereed
  • TCP Available Bandwidth Estimation Function with Socket API, KUGIMOTO Takeshi, MIYAKE Shigeki, MIZUTANI Kimihiro, Computer Software, Computer Software, 31(3), 3_246 - 3_258, 2014
    Summary:Recently, a lot of streaming services making use of TCP (Transmission Control Protocol) are developed. To keep the QoS in the streaming services highly, it is important to estimate available bandwidth of TCP stream precisely in a short period of time. We propose the real time available bandwidth estimating method. Our proposed method has the two advantages for the conventional bandwidth estimating methods. (1) Our proposed method does not generate the test traffic for the estimation and (2) considers the network conditions such as the jitter and latency. Therefore, our proposed method realizes the real time bandwidth estimation with lower network load and higher precision. Application software can easily use the results obtained by the function through socket API (Application Programming Interface). We implement the method for the TCP protocol stacks and compare the precision with the conventional bandwidth estimation tools. From the experimental results, our method outperforms the tools in the presicion.
  • On the fast-convergence of delay-based load balancing over multipaths for dynamic traffic environments., Meng Li,Array, Nei Kato, Kimihiro Mizutani, Osamu Akashi, Atsushi Takahara, International Conference on Wireless Communications and Signal Processing, WCSP 2013, Hangzhou, China, October 24-26, 2013, International Conference on Wireless Communications and Signal Processing, WCSP 2013, Hangzhou, China, October 24-26, 2013, 1 - 6, 2013 , Refereed
  • Secure resource provisioning across multiple domains., Toru Mano, Kimihiro Mizutani, Osamu Akashi, 2013 IFIP/IEEE International Symposium on Integrated Network Management (IM 2013), Ghent, Belgium, May 27-31, 2013, 2013 IFIP/IEEE International Symposium on Integrated Network Management (IM 2013), Ghent, Belgium, May 27-31, 2013, 1129 - 1134, 2013 , Refereed
  • MARIF: Multiple Queries Look-up Architecture Using Range Information FeedBack in a DHT Network, Kimihiro Mizutani, Toru Mano, Osamu Akashi, Kensuke Fukuda, IEICE Transaction on Communications, IEICE Transaction on Communications, E96B(7), 1680 - 1690, 2013 , Refereed
  • A Design of Scalable Computing Platform for Continuous Data, MIZUTANI Kimihiro, MANO Toru, AKASHI Osamu, FUKUDA Kensuke, Computer Software, Computer Software, 30(2), 2_101 - 2_118, 2013
    Summary:Recently, many researchers focus on the studies of management and analysis for continuous data such as time series and geographical location data. To manage the large continuous data, the structured overlay network technologies are proposed. In addition, to analyze the large continuous data, MapReduce platforms are proposed. However, it is difficult to analyze the continuous data by MapReduce platforms on overlay. Because general overlay uses hash functions and these hash functions do not preserve the continuousness. In addition, general MapReduce platform generates a lot of communications and synchronous operations in continuous data processing. To handle these problems, we propose the scalable computing platform for continuous data.<BR>Our platform achieves the asynchronous computing and high parallel performance for continuous data analysis. In concrete terms, our platform builds the balanced tree based on SkipList for all nodes. This architecture enables each node to manage its children nodes' states, analysis results, and synchronous operations. In addition, our platform can balance load by gathering all nodes' load information. Therefore, our platform realizes high performance MapReduce computing for continuous data.
  • Streaming server management scheme for reducing power consumption., Kimihiro Mizutani, Toru Mano, Osamu Akashi, Tetsuo Kawano, Hiroshi Shimizu, 2012 IEEE Global Communications Conference, GLOBECOM 2012, Anaheim, CA, USA, December 3-7, 2012, 2012 IEEE Global Communications Conference, GLOBECOM 2012, Anaheim, CA, USA, December 3-7, 2012, 3548 - 3553, 2012 , Refereed
  • Efficient query bundling mechanism in a DHT network., Kimihiro Mizutani, Toru Mano, Osamu Akashi, Kensuke Fukuda, 2012 IEEE Global Communications Conference, GLOBECOM 2012, Anaheim, CA, USA, December 3-7, 2012, 2012 IEEE Global Communications Conference, GLOBECOM 2012, Anaheim, CA, USA, December 3-7, 2012, 2695 - 2700, 2012 , Refereed
  • A Dynamic Flow Control Mechanism Based on a Hierarchical Feedback Model for Data Center Networks, Kimihiro Mizutani, Osamu Akashi, Atsushi Terauchi, Mitsuru Maruyama, IEEE Network Operations and Management, IEEE Network Operations and Management, 599 - 602, 2012 , Refereed
  • Dynamic Session Management Based on Reinforcement Learning in Virtual Server Environment, Kimihiro Mizutani, Izumi Koyanagi, Takuji Tachibana, IAENG ICCSA, IAENG ICCSA, 905 - 910, Mar. 2010 , Refereed
  • An Implementation and Its Evaluation of a Framework for Managing States of Nodes among Structured Overlay Networks, Kimihiro Mizutani, Satoshi Matsuura, Shinichi Doi, Kazutoshi Fujikawa, Hideki Sunahara, IEEE ICNS, IEEE ICNS, 282 - 287, Mar. 2010 , Refereed

Misc

  • Increasing Capacity of the Clos Structure for Efficient Nonblocking Networks, Toru Mano, Takeru Inoue, Kimihiro Mizutani, Osamu Akashi, 118, 466, 25, 30,   2019 03 , https://www.ieice.org/ken/paper/20190304j1l6/
  • トマトの生育情報を用いた収穫日予測手法の検討, 水谷后宏, 東田光裕, 増田貴大, 岡本朋子, 電子情報通信学会大会講演論文集(CD-ROM), 2018, ROMBUNNO.B‐18‐22,   2018 08 28 , http://jglobal.jst.go.jp/public/201802255789925299
  • 深層強化学習を用いた一般道における自動車の速度調整システム, 水谷后宏, 吉田学, 秦崇弘, 社家一平, 電子情報通信学会大会講演論文集(CD-ROM), 2018, ROMBUNNO.A‐14‐14,   2018 03 06 , http://jglobal.jst.go.jp/public/201802251739539321
  • Network Reduction Method that Minimizes Total Capacity Change for Virtual Network Embedding Acceleration, Toru Mano, Takeru Inoue, Kimihiro Mizutani, Shin-ichi Minato, Osamu Akashi, 117, 129, 13, 18,   2017 07 , http://www.ieice.org/ken/paper/20170719Dbvz/
  • ネットワーク故障におけるパスの統合・分割による故障単位の推定, 堤陽祐, 渡部康平, 井上武, 水谷后宏, 間野暢, 明石修, 中川健治, 電子情報通信学会大会講演論文集(CD-ROM), 2017, ROMBUNNO.B‐7‐62,   2017 03 07 , http://jglobal.jst.go.jp/public/201702251701646242
  • On Efficient Framework for Data-plane Verification with Geometric Windowing Queries, Takeru Inoue, Toru Mano, Kimihiro Mizutani, Hisashi Nagata, Osamu Akashi, IEICE Technical Report, 116, 251, 25, 30,   2016 10 , http://ci.nii.ac.jp/naid/40020991526
  • パーフェクトシミュレーション高速化のための遷移先割り当てに関する一検討, 永田尚志, 井上武, 水谷后宏, 間野暢, 明石修, 電子情報通信学会大会講演論文集(CD-ROM), 2016, ROMBUNNO.B‐7‐23,   2016 09 06 , http://jglobal.jst.go.jp/public/201602285804484395
  • An Analysis Method of Network Troubles with Path Identificationz, 渡部 康平, 井上 武, 水谷 后宏, 間野 暢, 明石 修, 中川 健治, 電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 115, 484, 135, 140,   2016 03 03 , http://ci.nii.ac.jp/naid/40020791215
  • Interactive Analysis of Large-scale Networks based on Integration of Multiple-layer Information, 明石 修, 水谷 后宏, 間野 暢, 井上 武, 福田 健介, 漆谷 重雄, 電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 115, 481, 215, 220,   2016 03 03 , http://ci.nii.ac.jp/naid/40020791228
  • Interactive Analysis of Large-scale Networks based on Integration of Multiple-layer Information, 明石 修, 水谷 后宏, 間野 暢, 井上 武, 福田 健介, 漆谷 重雄, 電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 115, 482, 215, 220,   2016 03 03 , http://ci.nii.ac.jp/naid/40020791971
  • Distributed Time Series Data Management and Analysis, Kimihiro Mizutani, Takeru Inoue, Toru Mano, Hisashi Nagata, Osamu Akashi, NTT Technical Review, 16, 3, 1, 6,   2016 03 , https://www.ntt-review.jp/archive/ntttechnical.php?contents=ntr201603fa5.html
  • Interactive Analysis of Large-scale Networks based on Integration of Multiple-layer Information, 明石修, 水谷后宏, 間野暢, 井上武, 福田健介, 漆谷重雄, 情報処理学会研究報告(Web), 2016, IOT-32, 2016-IOT-32(35) (WEB ONLY),   2016 02 25 , http://jglobal.jst.go.jp/public/201602200004054411
  • An Analysis Method of Network Troubles with Path Identification, 渡部康平, 井上武, 水谷后宏, 間野暢, 明石修, 中川健治, 電子情報通信学会技術研究報告, 115, 484(IN2015 108-153), 135‐140,   2016 02 25 , http://jglobal.jst.go.jp/public/201602203327666643
  • Debuggable reinforcement learning for server resource management, 水谷后宏, 井上武, 間野暢, 明石修, 電子情報通信学会技術研究報告, 115, 409(ICM2015 26-40), 31‐36,   2016 01 14 , http://jglobal.jst.go.jp/public/201602208344568216
  • 新世代ネットワークと革新的サービス 時系列データの分散管理・解析技術, 水谷后宏, 井上武, 間野暢, 永田尚志, 明石修, NTT技術ジャーナル, 28, 1, 30, 34,   2016 01 01 , http://jglobal.jst.go.jp/public/201602212686619405
  • Efficient Network Policy Checking with Multi-dimensional Graph Traversal Algorithm, Chen Richard, Takeru Inoue, Toru Mano, Kimihiro Mizutani, Hisashi Nagata, Osamu Akashi, IEICE Technical Report, 115, 256, 25, 30,   2015 10 , http://ci.nii.ac.jp/naid/40020651210
  • Packet Classification for Global Network View of SDN with MDDs, INOUE T, MANO T, MIZUTANI K, MINATO S, AKASHI O, IEICE technical report. Information networks, 114, 207, 1, 6,   2014 09 11 , http://ci.nii.ac.jp/naid/110009950830
    Summary:In software-defined networking, applications are allowed to access a global view of the network so as to provide sophisticated functionalities. They commonly rely on packet classification, but unlike the conventional classification problem to search for the action taken at a single switch, the global network view requires to identify the network-wide behavior of the packet. Conventional classification methods, however, fail to well support network-wide behaviors, since the search space is complicatedly partitioned. This paper proposes a novel packet classification method that efficiently supports network-wide packet behaviors. Our method utilizes a compressed data structure named the multi-valued decision diagram, allowing it to manipulate the complex search space with several algorithms. Experiments with real network datasets show that our method identifies the packet behavior at 20.1 Mpps on a single CPU core with only 8.4 MB memory.
  • Virtual Network Optimization across Multiple Domains without Revealing Private Information, MANO Toru, INOUE Takeru, IKARASHI Dai, HAMADA Koki, MIZUTANI Kimihiro, AKASHI Osamu, IEICE technical report. Information networks, 114, 139, 83, 88,   2014 07 17 , http://ci.nii.ac.jp/naid/110009946990
    Summary:Building optimal virtual networks across multiple domains is an essential technology to offer flexible network services. However, existing research unrealistically assumes that providers will share their private information. Providers, as is well known, never actually do that to remain competitive. Technically, secure multi-party computation, which is a cryptographic tool, can be used to secure optimization, but it is too time-consuming. This paper presents a novel method to optimize virtual networks built over multiple domains, with great efficiency but without revealing any private information. Our method employs secure multi-party computation but only for masking sensitive values to evade time-consuming computation. It is solidly based on the theory of optimality, and is assured of finding reasonably optimal solutions. Experiments show that our method finds nearly optimal solutions in just a few minutes for virtual network with tens of nodes.
  • Packet Classification for Global Network View of Software-Defined Networking, Takeru Inoue, Toru Mano, Kimihiro Mizutani, Shin-ichi Minato, Osamu Akashi, TCS Technical Reports, Division of Computer Science, Hokkaido University, A, 14, 74,   2014 07 , http://www-alg.ist.hokudai.ac.jp/~thomas/TCSTR/tcstr_14_74/tcstr_14_74.pdf
  • Towards Measurement and Analysis of Large-scale Networks, AKASHI Osamu, MIZUTANI Kimihiro, FUKUDA Kensuke, URUSHIDANI Shigeo, IEICE technical report, 114, 6, 77, 82,   2014 04 17 , http://ci.nii.ac.jp/naid/110009874951
    Summary:It is important to analyze the behavior of large-scale networks. However, this analysis is difficult because we have to cope with a huge amount of and various kinds of data. A variety of applicable analysis methods make situation more complicated. We discuss a method to tackle with this problem. The method integrates network-status information in multiple layers and analyzes it from multiple viewpoints. We applies this method to analyze the behavior of SINET, which is one of the major networks in Japan. We visualize and analyze Netflow data, BGP route information, and Darknet data in an integrated fashion and discuss its effectiveness.
  • BS-6-7 Secure Virtual Network Splitting Across Multiple Infrastructure Providers, Mano Toru, Inoue Takeru, Mizutani Kimihiro, Akashi Osamu, Proceedings of the IEICE General Conference, 2014, 2, "S, 200"-"S-201",   2014 03 04 , http://ci.nii.ac.jp/naid/110009850106
  • 複数設備提供者間の情報秘匿型仮想ネットワーク分割手法, 間野暢, 井上武, 水谷后宏, 明石修, 電子情報通信学会 総合大会, BS, 6, 7,   2014 03 , http://jglobal.jst.go.jp/public/201402211272382088
  • Secure Resource Provisioning Across Multiple Domains, MANO Toru, MIZUTANI Kimihiro, AKASHI Osamu, IEICE technical report. Internet Architecture, 112, 489, 157, 162,   2013 03 14 , http://ci.nii.ac.jp/naid/110009712528
    Summary:Network resource provisioning is an important technique for infrastructure providers (infra-providers). However, to fully satisfy user requests it is probably necessary to use facilities across multiple domains, for which the conventional resource provisioning methods are unsuitable for the multiple domains because they require unre- vealed information from infraproviders. In this paper, we propose a method for resource provisioning across multiple domains that uses infraproviders ' confidential information without exposing it to other infra-providers. Evaluation results show that the computational overhead is tractable and that the average utility fee is at least on the same level as that of the conventional methods.
  • An Inplementation and Its Fundamental Evaluation of a Distributed Computing Platform Based on Structured Overlay Network, MIZUTANI Kimihiro, MANO Toru, AKASHI Osamu, FUKUDA Kensuke, IEICE technical report. Information and communication management, 112, 378, 109, 114,   2013 01 17 , http://ci.nii.ac.jp/naid/110009727350
    Summary:We propose new distributed computing platform for analyzing big data such as traffic and sensor data. The proposed platform solves the task synchronization problem and task bias problem by using ShpList tree architecture. In concrete terms, the proposed platform enables nodes to synchronize children tasks by consisting tree connections. In addition, the proposed platform realizes the task smoothing among nodes by considering the amount of nodes' task. In evaluation, we shows the concrete behevier of the proposed platform and the abalability.
  • An Inplementation and Its Fundamental Evaluation of a Distributed Computing Platform Based on Structured Overlay Network, MIZUTANI Kimihiro, MANO Toru, AKASHI Osamu, FUKUDA Kensuke, IEICE technical report. Life intelligence and office information systems, 112, 379, 109, 114,   2013 01 17 , http://ci.nii.ac.jp/naid/110009727835
    Summary:We propose new distributed computing platform for analyzing big data such as traffic and sensor data. The proposed platform solves the task synchronization problem and task bias problem by using ShpList tree architecture. In concrete terms, the proposed platform enables nodes to synchronize children tasks by consisting tree connections. In addition, the proposed platform realizes the task smoothing among nodes by considering the amount of nodes' task. In evaluation, we shows the concrete behevier of the proposed platform and the abalability.
  • B-14-16 A Study of Effective Management of Variable Bit Rate Flows, Mizutani Kimihiro, Akashi Osamu, Mano Toru, Proceedings of the IEICE General Conference, 2012, 2,   2012 03 06 , http://ci.nii.ac.jp/naid/110009463045
  • A Proposal of Scalable Publisher/Subscriber Computing Infrastructure with Structured Overlay Network, MIZUTANI Kimihiro, AKASHI Osamu, FUKUDA Kensuke, IEICE technical report. Information and communication management, 111, 382, 61, 66,   2012 01 19 , http://ci.nii.ac.jp/naid/110009480821
    Summary:We propose a new distributed computing infrastructure for managing big data such as massive traffic and sensor information effectively. Our infrastructure stores the big data onto structured overlay network and analyzes the big data through distribute cooperation. To analyze the big data through the cooperation, an administrator, who manages the big data, only have to subscribe an analysis policy for the overlay. After the subscribing, the overlay publishes the result of the analyzing to the administrator autonomously.
  • A Proposal of Scalable Publisher/Subscriber Computing Infrastructure with Structured Overlay Network, MIZUTANI Kimihiro, AKASHI Osamu, FUKUDA Kensuke, 電子情報通信学会技術研究報告. ICM, 情報通信マネジメント : IEICE technical report, 111, 382, 61, 66,   2012 01 12 , http://ci.nii.ac.jp/naid/10031099004
  • A Study of OS Kernel Functions for Estimating Available Bandwidth, KUGIMOTO Takeshi, MIYAKE Shigeki, MIZUTANI Kimihiro, MARUYAMA Mitsuru, 電子情報通信学会技術研究報告. NS, ネットワークシステム, 111, 277, 55, 60,   2011 11 03 , http://ci.nii.ac.jp/naid/10031093891
  • BS-6-31 Cooperative load balancing mechanism among data centers(BS-6. Planning, Control and Management on Networks and Services), Mizutani Kimihiro, Akashi Osamu, Terauchi Atushi, Maruyama Mitsuru, Proceedings of the Society Conference of IEICE, 2011, 2, "S, 90"-"S-91",   2011 08 30 , http://ci.nii.ac.jp/naid/110008725358
  • A Proposal of A Reinforcement Learning-Based Dynamic Session Management in Virtual Server Environments, MIZUTANI Kimihiro, KOYANAGI Izumi, TACHIBANA Takuji, IEICE technical report, 109, 378, 51, 56,   2010 01 14 , http://ci.nii.ac.jp/naid/110007999835
    Summary:In a virtualized server environment, machine resources such as CPU and memory are shared by multiple services. In such a environment, as the number of sessions for each service increases, the amount of resources that are utilized by the services increases. If thrashing occurs due to the lack of resources, the performance of the server is degraded. It is effective to estimate the amount of used resources, however, it is hard to estimate the amount of resources that are used dynamically by multiple services. In this paper, we propose a dynamic session management based on a reinforcement leaning in order to utilize the resources effectively and avoid the thrashing. In the proposed method, a learning agent estimates the amount of used resources from the response time for a service request. Then, the agent decides the acceptance or reject of all arriving session request with Q-learning. Because this method can be implemented easily in a virtualized machine, it is expected that our proposed method is used in a real environment. We evaluate the performance of our proposed method with simulation. From simulation results, we show that the proposed method can allocate the resources to multiple services effectively while avoiding the thrashing and can perform the priority control for multiple services.
  • A system for parallel estimation of multiple overlay network routing algorithms by a plug-in architecture, MIZUTANI Kimihiro, DOI Shinichi, MATSUURA Satoshi, FUJIKAWA Kazutoshi, SUNAHARA Hideki, IPSJ SIG technical reports, 2009, 8, 9, 16,   2009 01 22 , http://ci.nii.ac.jp/naid/110007137950
    Summary:As a lot of researchers study overlay network, a kind of routing algorithms are proposed. If you propose a new algorithm, you will need to prove the superiority of your algorithm. Using past estimation systems, you can estimate only one algorithm at the same time. Therefore you have to reconstruct an environment in order to estimate other algorithms. In this research, we propose a new estimation system. Our system is based on one fundamental overlay network and enables a parallel estimation of multiple routing algorithm at the same instant by a plug-in architecture. Our system offers a environment where you can estimate and compare routing algorithms on the same experimental circumstance.

Awards & Honors

  •   2017 , IEEE Global Communications Conference (GLOBECOM), Best Paper Award, A Tensor Based Deep Learning Technique for Intelligent Packet Routing
  •   2017 , 日本ソフトウェア科学会, 第21回研究論文賞, Stable Load Balancing with Overlapping ID-space Management in Range-based Structured Overlay Networks
  •   2016 , IEEE International Conference on Communications (ICC),, Best Paper Award, A Mobility-Based Mode Selection Technique for fair Spatial Dissemination of Data in Multi-Channel Device-to- Device Communication
  •   2010 , International MultiConference of Engineers and Computer Scientists(IMECS), Best Student Paper Award, Dynamic Session Management Based on Reinforcement Learning in Virtual Server Environment
  •   2010 , 情報処理学会MBL研究会, 優秀プレゼンテーション賞, An Implementation of a Framework for Integrating Churn Managements among Structured Overlay Networks

Research Grants & Projects

  • Information-technology Promotion Agency, Japan, The Mitoh Youth Project, Development of Programmable Overlay Network

Educational Activities

Teaching Experience

  • Network Technology 2, Kindai University