Updated on 2021/10/07

写真a

 
TARUTANI Yuuya
 
Organization
Interdisciplinary Science and Engineering in Health Systems Assistant Professor
Position
Assistant Professor
Contact information
メールアドレス
External link

Degree

  • 博士(情報科学) ( 2014.9   大阪大学 )

Research Interests

  • Computer Networks

  • IoT

  • Virtual Network Reconfiguration

Research Areas

  • Manufacturing Technology (Mechanical Engineering, Electrical and Electronic Engineering, Chemical Engineering) / Communication and network engineering

  • Informatics / Information network

  • Informatics / Information security

Education

  • Osaka University   大学院情報科学研究科   情報ネットワーク学専攻

    2012.4 - 2014.9

      More details

    Notes: 博士後期課程

    researchmap

  • Osaka University   大学院情報科学研究科   情報ネットワーク学専攻

    2010.4 - 2012.3

      More details

    Notes: 博士前期課程

    researchmap

  • Osaka University   基礎工学部   情報科学科

    2006.4 - 2010.3

      More details

Research History

  • Okayama University   Graduate School of Interdisciplinary Science and Engineering in Health Systems   Assistant Professor

    2018.12

      More details

  • Osaka University   Cybermedia Center   Assistant Professor

    2014.10 - 2018.11

      More details

Professional Memberships

Committee Memberships

  • 電子情報通信学会分野横断型研究会   専門委員  

    2020.9   

      More details

  • 電子情報通信学会   英文論文誌B小特集 編集委員  

    2018.8 - 2019.3   

      More details

  • 電子情報通信学会ネットワークシステム研究会   専門委員  

    2017.5   

      More details

    Committee type:Academic society

    researchmap

  • 電子情報通信学会   常任査読委員  

    2016.8   

      More details

 

Papers

  • Audio Adversarial Attack に対する音声加工を用いた防御方法の検討

    山本泰成, 樽谷優弥, 福島行信, 横平徳美

    電子情報通信学会技術研究報告   121 ( 66 )   19 - 24   2021.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • TD学習を用いた仮想網マッピング手法の性能改善

    佐川勇太, 福島行信, 樽谷優弥

    電子情報通信学会総合大会講演論文集   2021.3

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • A Server Migration Method Using Q-Learning with Dimension Reduction in Edge Computing Reviewed

    Ryo Urimoto, Yukinobu Fukushima, Yuya Tarutani, Tutomu Murase, Tokumi Yokohira

    in Proceedings of ICOIN 2021   301 - 304   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Proposal of Device Control Method Based on Consensus Building Using Reinforcement Learning Reviewed

    Isato Oishi, Yuya Tarutani, Yukinobu Fukushima, Tokumi Yokohira

    in Proceedings of ICOIN 2021   451 - 456   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • An IP Fast Reroute Method against Multiple Node Failures Reviewed

    Naoto Numata, Masashi Ishigai, Yuya Tarutani, Yukinobu Fukushima, Tokumi Yokohira

    in Proceedings of ICTC 2020   2020.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Performance Evaluation of Feature Encoding Methods in Network Traffic Prediction Using Recurrent Neural Networks Reviewed

    Yusuke Tokuyama, Ryo Miki, Yukinobu Fukushima, Yuya Tarutani, Tokumi Yokohira

    in Proceedings of ICIET 2020   2020.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Poster: Propose a defense method against Audio Adversarial Attack Reviewed

    Yuya Tarutani, Kensuke Ueda, Yoshiaki Kato

    in Proceedings of NDSS Symposium 2020   2020.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • A TCP Incast Avoidance Method Based on Retransmission Requests from a Client Reviewed

    Shiden Kishimoto, Shigeyuki Osada, Yuya Tarutani, Yukinobu Fukushima, Tokumi Yokohira

    in Proceedings of ICTC 2019   2019.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • 様々な嗜好を有する人が混在する環境における合意形成に基づいた制御手法の提案

    樽谷優弥

    第18回情報科学技術フォーラム   2019.9

     More details

    Authorship:Lead author   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Toward an Online Network Intrusion Detection System Based on Ensemble Learning Reviewed

    Ying-Feng Hsu, Zhenyu He, Yuya Tarutani, Morito Matsuoka

    in Proceedings of IEEE Cloud 2019   2019.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • スマートスピーカに対する攻撃への対策手法の提案

    樽谷優弥, 上田健介, 加藤嘉明

    電子情報通信学会技術研究報告   2019.6

     More details

    Authorship:Lead author   Language:Japanese  

    researchmap

  • Proposal of a consensus builder for environmental condition setting in spaces where people with various preferences coexist Reviewed

    Yuya Tarutani

    2018.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • ネットワーク境界越が可能なIEEE1888 over Websocket の提案と実装

    樽谷優弥, 村田修一郎, 松田和浩, 松岡茂登

    2016.5

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • Placement of Virtual Storages for Distributed Robust Cloud Storage Reviewed

    Yuya Tarutani, Yuichi Ohsita, Masayuki Murata

    IEICE TRANSACTIONS ON COMMUNICATIONS   E99B ( 4 )   885 - 893   2016.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

    Cloud storage has become popular and is being used to hold important data. As a result, availability to become important; cloud storage providers should allow users to upload or download data even if some part of the system has failed. In this paper, we discuss distributed cloud storage that is robust against failures. In distributed cloud storage, multiple replicas of each data chunk are stored in the virtual storage at geographically different locations. Thus, even if one of the virtual storage systems becomes unavailable, users can access the data chunk from another virtual storage system. In distributed cloud storage, the placement of the virtual storage system is important; if the placement of the virtual cloud storage system means that a large number of virtual storages are possible could become unavailable from a failure, a large number of replicas of each data chunk should be prepared to maintain availability. In this paper, we propose a virtual storage placement method that assures availability with a small number of replicas. We evaluated our method by comparing it with three other methods. The evaluation shows that our method can maintain availability while requiring only with 60% of the network costs required by the compared methods.

    DOI: 10.1587/transcom.2015EBP3292

    Web of Science

    researchmap

  • データセンタの消費電力削減のための遺伝アルゴリズムに基づくタスク配置・空調機設定手法の性能評価

    出口孝明, 菅沼孝二, 樽谷優弥, 長谷川剛, 中村泰, 田村卓三, 松田和浩, 松岡茂登

    2016.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • IEEE1888 over WebSocket for communicating across a network boundary Reviewed

    Yuya Tarutani, Shuuichirou Murata, Kazuhiro Matsuda, Morito Matsuoka

    PROCEEDINGS 2016 IEEE 40TH ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE WORKSHOPS (COMPSAC), VOL 2   332 - 337   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    Some communications between devices are limited by network boundaries for ensuring security. In these cases, IEEE1888 does not provide inter-device communication. We thus propose IEEE1888 over WebSocket for communication between devices across network boundaries. In IEEE1888 over WebSocket, two devices are added to an IEEE1888 network for communication across network boundaries, so devices using traditional IEEE1888 need not to be changed. We implemented an experimental system of IEEE1888 overWebSocket. The results shows that IEEE1888 over WebSocket enables communication across network boundaries.

    DOI: 10.1109/COMPSAC.2016.131

    Web of Science

    researchmap

  • Reducing Power Consumption in Data Center by Predicting Temperature Distribution and Air Conditioner Efficiency with Machine Learning Reviewed

    Yuya Tarutani, Kazuyuki Hashimoto, Go Hasegawa, Yutaka Nakamura, Takumi Tamura, Kazuhiro Matsuda, Morito Matsuoka

    PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON CLOUD ENGINEERING (IC2E)   226 - 227   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    To reduce the power consumption in data centers, the coordinated control of the air conditioner and the servers is required. It takes tens of minutes for changes of operational parameters of air conditioners including outlet air temperature and volume to be reflected in the temperature distribution in the whole data center. So, the proactive control of the air conditioners is required according to the prediction temperature distribution corresponding to the load on the servers. In this paper, the temperature distribution and the power efficiency of air conditioner were predicted by using a machine-learning technique, and also we propose a method to follow-up proactive control of the air conditioner under the predicted optimum condition. Consequently, by the follow-up proactive control of the air conditioner and the load of servers, power consumption reduction of 30% at maximum was demonstrated.

    DOI: 10.1109/IC2E.2016.39

    Web of Science

    researchmap

  • データセンタの温度分布予測のためのネットワークモデル

    田代晋也, 樽谷優弥, 長谷川剛, 中村泰, 松田和浩, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • 数値流体力学シミュレーションによるデータセンタ内の温度予測のためのサーバモデルの作成

    北田和将, 樽谷優弥, 長谷川剛, 松田和浩, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • WebSocketを用いたクラウド型HEMSのスケーラビリティの実験評価

    エムヘーテムーレン, 樽谷優弥, 長谷川剛, 松田和浩, 村田修一郎, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • データセンタの省電力化に向けたガウス過程動的モデルによる温度分布予測

    菅沼孝二, 樽谷優弥, 長谷川剛, 中村泰, 浮田宗伯, 松田和浩, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • データセンタにおける空調機の消費電力を削減するための遺伝アルゴリズムに基づくタスク配置手法の性能評価

    出口孝明, 樽谷優弥, 長谷川剛, 中村泰, 田村卓三, 松田和浩, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • データセンタの電力削減のための機械学習法を利用した温度分布予測

    橋本和幸, 樽谷優弥, 長谷川剛, 松田和浩, 田村卓三, 中村泰, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • CEMS における多数端末の同時接続に対する MQTT プロトコルの拡張性の実験評価

    北川貴大, 樽谷優弥, 長谷川剛, 松田和浩, 村田修一郎, 松岡茂登

    2015.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • A Network Model for Prediction of Temperature Distribution in Data Centers Reviewed

    Shinya Tashiro, Yuya Tarutani, Go Hasegawa, Yutaka Nakamura, Kazuhiro Matsuda, Morito Matsuoka

    2015 IEEE 4TH INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET)   261 - 266   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    We propose a novel network model for real-time prediction of temperature distribution in a data center so as to allow energy-efficient task assignment and facility management. We model various physical relationships in the data center as a network, including heat movements caused by airflow and heat generation by servers. Since changes in temperature distribution depend on physical properties of the data center such as equipment locations and server types, model parameters (connection weights in the network) that characterize relationship of nodes are determined by a machine learning technique using actual data center operation data. The proposed method provides prediction results in a shorter time than traditional methods such as model based on computational fluid dynamics and potential flow model, while maintaining prediction accuracy. We evaluate the performance of the proposed model through comparison with actual data from our experimental data center. The evaluation indicates that the proposed model can predict 10-minute future temperature distributions in 60 places in 3.3 ms, with a root mean square error of 0.49 degrees.

    DOI: 10.1109/CloudNet.2015.7335319

    Web of Science

    researchmap

  • Temperature Distribution Prediction in Data Centers for Decreasing Power Consumption by Machine Learning Reviewed

    Yuya Tarutani, Kazuyuki Hashimoto, Go Hasegawa, Yutaka Nakamura, Takumi Tamura, Kazuhiro Matsuda, Morito Matsuoka

    2015 IEEE 7TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING TECHNOLOGY AND SCIENCE (CLOUDCOM)   635 - 642   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    To decrease the power consumption of data centers, coordinated control of air conditioners and task assignment on servers is crucial. It takes tens of minutes for changes of operational parameters of air conditioners including outlet air temperature and volume to be actually reflected in the temperature distribution in the whole data center. Proactive control of the air conditioners is therefore required according to the predicted temperature distribution, which is highly dependent on the task assignment on the servers. In this paper, we apply a machine learning technique for predicting the temperature distribution in a data center. The temperature predictor employs regression models for describing the temperature distribution as it is predicted to be several minutes in the future, with the model parameters trained using operational data monitored at the target data center. We evaluated the performance of the temperature predictor for an experimental data center, in terms of the accuracy of the regression models and the calculation times for training and prediction. The temperature distribution was predicted with an accuracy of 0.095 degrees C. The calculation times for training and prediction were around 1,000 seconds and 10 seconds, respectively. Furthermore, the power consumption of air conditioners was decreased by roughly 30% through proactive control based on the predicting temperature distribution.

    DOI: 10.1109/CloudCom.2015.49

    Web of Science

    researchmap

  • Large-scale ASP-based HEMS Utilizing Interactive Web Technologies Reviewed

    Enkhee Temuulen, Go Hasegawa, Yuya Tarutani, Kazuhiro Matsuda, Morito Matsuoka

    2015 IEEE INTERNATIONAL CONFERENCE ON SMART GRID COMMUNICATIONS (SMARTGRIDCOMM)   798 - 803   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    The concept of a Home Energy Management System (HEMS) as a power-saving technology for home appliances has received much attention. Most of current HEMSs based on the Smart Energy Profile (SEP), KNX, or ECHONET standards are implemented as closed systems within a Home Area Network (HAN); therefore, cost is a serious problem in the large-scale deployment of HEMSs. One possible way to reduce the overhead is to implement a HEMS as a cloud-based Application Service Provider (ASP) service. In such setup, a HEMS server is located in the cloud, and it monitors and controls home appliance devices over the Internet. We propose here a novel HEMS architecture using a cloud-based ASP service. We describe an overall architecture and some potential interactive Web communication technologies that realize a HEMS over the cloudbased ASP services. We also present a mathematical analysis and experimental results for estimating protocol overheads and server loads. These show that the WebSocket protocol is the most suitable protocol, allowing accommodation of twice as many households as other protocols. Finally, we describe our prototype implementation of the proposed architecture with the WebSocket protocol.

    DOI: 10.1109/SmartGridComm.2015.7436399

    Web of Science

    researchmap

  • Virtual Network Reconfiguration for Reducing Energy Consumption in Optical Data Centers Reviewed

    Yuya Tarutani, Yuichi Ohsita, Masayuki Murata

    JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING   6 ( 10 )   925 - 942   2014.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OPTICAL SOC AMER  

    Energy consumption by data centers has become a serious problem, and measures for its reduction should be developed. Such measures should address not only the energy consumption of the servers but also that of the network itself, because the latter is responsible for a substantial portion of the total energy consumption. One approach to reducing the energy consumption of the network within a data center is to use optical circuit switches (OCSs) at the core of the data center, where electronic switches are connected to the OCSs. In such a network, a virtual network can be configured by setting the OCSs to connect different ports of the electronic packet switches. Thus, the energy consumption of the network can be reduced by configuring the virtual network to minimize the number of ports required by the electronic packet switches and powering down any unused ports. In this paper, we propose a method called virtual network reconfiguration for data center networks (VNR-DCN) that immediately reconfigures the virtual network so as to reduce the energy consumption under the constraints on the bandwidth and delay between servers in data center networks based on optical communication paths. In VNR-DCN, we configure the virtual network to satisfy the requirements by setting the parameters of the topology, called generalized flattened butterfly, instead of solving an optimization problem. In the evaluation, we show that a virtual network configured by VNR-DCN requires a small number of active ports. In addition, we show the impact of virtual network configuration on energy consumption.

    DOI: 10.1364/JOCN.6.000925

    Web of Science

    researchmap

  • 省電力性と耐故障性を両立するマルチテナント用仮想ネットワーク制御

    樽谷優弥, 大下裕一, 村田正幸

    2014.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • データセンターにおける省電力な仮想ネットワーク構築手法

    樽谷優弥, 大下裕一, 村田正幸

    2014.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • Evaluation of data center network structures considering routing methods Reviewed

    Yuta Shimotsuma, Yuya Tarutani, Yuichi Ohsita, Masayuki Murata

    2013.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Evaluation of data center network structures considering routing methods

    Yuta Shimotsuma, Yuya Tarutani, Yuichi Ohsita, Masayuki Murata

    2012.6

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • 低消費電力を達成する大規模データセンタ内仮想ネットワーク制御手法

    樽谷優弥, 大下裕一, 村田正幸

    2012.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • Optical-Layer Traffic Engineering With Link Load Estimation for Large-Scale Optical Networks Reviewed

    Yuya Tarutani, Yuichi Ohsita, Shin'ichi Arakawa, Masayuki Murata

    JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING   4 ( 1 )   38 - 52   2012.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OPTICAL SOC AMER  

    Traffic information is required to perform opticallayer traffic engineering (TE). However, as the number of nodes in optical networks increases, the overhead for collecting the traffic volume information becomes large. In this paper, we develop a method that reduces the overhead for collecting traffic volume information by selecting a subset of nodes and by only collecting the traffic volume information from the selected nodes. Then, we estimate the traffic volume using the information gathered from the selected nodes. According to the simulation results, we clarify that our method can accurately identify the congested links in real ISP topologies, where the number of traffic demands passing through some links is large; however, the estimation errors of our method become large when the number of traffic demands passing each link is small. Furthermore, optical-layer TE can sufficiently mitigate congestion by using the traffic volume estimated by our method from the information on 50% of all nodes in the case of the Japan topology and 30% of all nodes in the case of the AT&T topology.

    DOI: 10.1364/JOCN.4.000038

    Web of Science

    researchmap

  • A virtual network to achieve low energy consumption in optical large-scale datacenter Reviewed

    Yuya Tarutani, Yuichi Ohsita, Masayuki Murata

    2012 IEEE International Conference on Communication Systems, ICCS 2012   45 - 49   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    A data center network should provide communication with sufficiently large bandwidth and small delay between all servers. On the other hand, energy consumption of the data center network should be minimized. To satisfy all of the above requirements, in this paper, we introduce the virtual network configured over the data center network constructed of the optical cross connects (OXCs) and the electronic switches. We design the virtual network topology (VNT) so as to achieve sufficiently large bandwidth and small delay with small energy consumption. To calculate the suitable VNT in a short period, we propose the topology called Generalized Flattened Butterfly and a method to set the parameters so as to suit the current condition. In our evaluation, we clarify that our method achieves the sufficient bandwidth and the target maximum number of hops between top-of rack(ToR) switches with small energy consumption. © 2012 IEEE.

    DOI: 10.1109/ICCS.2012.6406106

    Scopus

    researchmap

  • 一部ノードの観測情報のみを用いた光レイヤトラヒックエンジニアリング

    樽谷優弥, 大下裕一, 荒川伸一, 村田正幸

    2011.8

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • 一部のノードからの情報収集により全リンク上のトラヒック量を推定する手法

    樽谷優弥, 大下裕一, 荒川伸一, 村田正幸

    2010.11

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • リンク使用率推定のための観測リンク選択手法

    樽谷優弥, 大下裕一, 荒川伸一, 村田正幸

    2010.3

     More details

    Language:Japanese   Publishing type:Research paper (other academic)  

    researchmap

  • Estimation of Traffic Amounts on all Links by Using the Information From a Subset of Nodes Reviewed

    Yuya Tarutani, Yuichi Ohsita, Shin'ichi Arakawa, Masayuki Murata

    EMERGING 2010: THE SECOND INTERNATIONAL CONFERENCE ON EMERGING NETWORK INTELLIGENCE   18 - 23   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IARIA XPS PRESS  

    Traffic information is required to perform traffic engineering. However, as the network that require traffic engineering becomes large, the overhead to collect the traffic amount information required for traffic engineering becomes large. In this paper, we propose a method to reduce the overhead to collect the traffic amount information. In our method, we select a subset of nodes and collect the traffic amount information only from the selected nodes. Then, we estimate the traffic amount on each link by using the information collected from the selected nodes. According to simulation results, our method can estimate the traffic amount on each link required for traffic engineering accurately by monitoring 30% of all nodes.

    Web of Science

    researchmap

▼display all

Presentations

  • 大学におけるセキュリティ人材育成 Invited

    樽谷 優弥

    サイエンティフィックシステム研究会 システム技術分科会 会合2019 

     More details

    Presentation type:Symposium, workshop panel (nominated)  

    researchmap

Awards

  • 活動功労賞

    2021.9   電子情報通信学会通信ソサエティ  

    樽谷優弥

     More details

  • 岡山工学振興会科学技術賞

    2021.7   岡山工学振興会  

    樽谷優弥

     More details

  • ベストティーチャー賞

    2020.3   岡山大学工学部  

    樽谷優弥, 西川亘, 鈴木弘朗, 井上良太

     More details

  • FIT奨励賞

    2019.9   情報処理学会   様々な嗜好を有する人が混在する環境における合意形成に基づいた制御手法の提案

    樽谷優弥

     More details

  • 学生研究奨励賞

    2014.2   IEEE関西支部   Optical-Layer Traffic Engineering with Link Load Estimation for Large-Scale Optical Networks

    Yuya Tarutani

     More details

Research Projects

  • 音声認識システムへの攻撃に対する防御機構の開発

    2021.04 - 2022.03

    岡山工学振興会  学術研究助成 萌芽研究 

      More details

    Authorship:Principal investigator 

    researchmap

  • 様々な嗜好を有する人々が共存する環境下における合意形成に基づいた制御

    Grant number:19K20257  2019.04 - 2021.03

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists  Grant-in-Aid for Early-Career Scientists

    樽谷 優弥

      More details

    Grant amount:\4160000 ( Direct expense: \3200000 、 Indirect expense:\960000 )

    情報通信技術を用いてネットワークに接続する様々な端末から情報を収集し、消費電力の削減等の目的に応じた機器制御を行うサービスが人の生活環境へも拡がりつつある。特に生活環境では、ユーザの満足度を考慮しつつ目的を達成することが要求される。一方、公共空間やオフィス環境では、多種多様な嗜好を有するユーザが生活するため、全てのユーザの満足度を考慮した機器制御は容易ではない。本研究課題では、異なる嗜好を有するユーザが生活する環境において、制御目的の達成とユーザの満足度の充足が両立可能な機器制御を提案する。本研究では、ユーザの感情、嗜好、反応を識別するユーザの満足度モデルを提案し、満足度モデルを用いた合意形成による機器制御手法を提案・研究開発する。
    本年度は、ユーザの嗜好モデルを仮定して強化学習を用いた制御方法の実装に取り組んだ。深層強化学習を用いてリアルタイムに変化する情報を基に評価環境モデルを構築し、(1)外気温の変化による影響を考慮した機器制御とユーザ満足度の両立を行える強化学習を用いた制御方法の実現、(2)人の入退室を考慮してユーザ満足度と消費電力の低減を行える強化学習を行える制御方法の実現、の2つに取り組んだ。両取組ともに、空調設定と照明設定からユーザの満足度が決まると仮定し、そのうえで合意形成が可能な制御値を強化学習で導くことを目的とした。
    これらの研究の結果、(1)では5人のユーザモデルを与えた時に強化学習によって得られた学習器を用いることで、最適値と比較してほぼ同様、最低でも約90%近似する制御ができることを明らかにした。また、(2)では人の入退室を制御に考慮した強化学習によって、ユーザ満足度や消費電力の報酬を高めることを明らかにした。

    researchmap

  • 環境変動への耐性と省電力を両立したデータセンタの仮想ネットワーク制御技術の研究

    Grant number:13J07115  2013.04 - 2015.03

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for JSPS Fellows  Grant-in-Aid for JSPS Fellows

    樽谷 優弥

      More details

    Grant amount:\1800000 ( Direct expense: \1800000 )

    これまでの研究では、光通信を導入したデータセンターにおいて、仮想ネットワークを制御することによって、データセンタネットワークを省電力化する方法について提案してきた。しかしながら、仮想ネットワーク制御手法のスケーラビリティに関しては検証しておらず、提案手法が大規模な環境でもどうさするかについては明らかにしていない。そこで、今年度の研究では、データセンタネットワーク内のサーバーラック数や収容トラヒック量を増加させた場合について評価を行い、提案手法が大規模なデータセンタネットワークにも適用可能であることについて明らかにする。前年度に提案した手法を用いて、制御対象となるサーバーラック数を増加させた場合も提案手法が要求される性能を満たす仮想ネットワークを少ない数の仮想リンクで構築し、大規模なデータセンターネットワークにも有効であることを明らかにした。
    また、これまではネットワーク制御の観点から、サーバーラック間を接続する仮想ネットワークを制御し、データセンタネットワークの省電力化について取り組んできた。今年度の研究では、サーバの観点からの省電力化に取り組むために、マルチテナント方式のデータセンターにおいて、環境変動として故障への耐性と省電力性を両立する制御手法について検討を行った。本手法では、耐故障性の保障のために、データを複数のチャンクに分割し、レプリカとして複数台の仮想マシンで保持する方式を用いて耐故障性を保障する方法をとる。本提案手法では、機器の故障発生時に通信できなくなくなる仮想マシンの数を調査する方法を提案し、その方法を用いて耐故障性を保証しつつ、省電力な仮想マシンの配置を行う方法を提案した。シミュレーションによる評価により、収容テナント数が増えると少ないレプリカ数でも、省電力な仮想マシンの配置が可能なことを明らかにした。

    researchmap

 

Class subject in charge

  • Technical English for Interdisciplinary Medical Sciences and Engineering (2021academic year) Late  - その他

  • Research Works for Interdisciplinary Medical Sciences and Engineering (2021academic year) Year-round  - その他

  • Electrical and Communication Engineering Lab A (2021academic year) 1st and 2nd semester  - 水2,水3,水4,水5,水6

  • Electrical and Communication Engineering Lab C (2021academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

  • Experiments in Electrical and Electronic Engineering III (2021academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

  • Technical English for Interdisciplinary Medical Sciences and Engineering (2020academic year) Late  - その他

  • Research Works for Interdisciplinary Medical Sciences and Engineering (2020academic year) Year-round  - その他

  • Communication Network Engineering Lab II (2020academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

  • Electrical and Communication Engineering Lab A (2020academic year) 1st and 2nd semester  - 水2,水3,水4,水5,水6

  • Electrical and Communication Engineering Lab C (2020academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

  • Electrical and Communication Engineering Lab III (2020academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

  • Electrical and Communication Engineering Lab I (2020academic year) 1st and 2nd semester  - 水2,水3,水4,水5,水6

  • Experiments in Electrical and Electronic Engineering III (2020academic year) 3rd and 4th semester  - 火3,火4,火5,火6,火7

▼display all