• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

A limited kernel machine inspired by insect's brain and its application for maximum power point tracker for photvoltaics

Research Project

Project/Area Number 24500184
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Intelligent informatics
Research InstitutionChubu University

Principal Investigator

YAMAUCHI Koichiro  中部大学, 工学部, 教授 (00262949)

Project Period (FY) 2012-04-01 – 2015-03-31
Project Status Completed (Fiscal Year 2014)
Budget Amount *help
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2014: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2013: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2012: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords制限付き学習法 / 昆虫脳 / 組み込み用学習アルゴリズム / MPPTマイクロコンバータ / 太陽電池 / learning on a budget / 組み込み用学習エンジン / モデルベース制御 / 昆虫脳のアルゴリズム / マイクロコンバータ / 追加学習 / kernel perceptron / 一般回帰ニューラルネットワーク / incremental learning
Outline of Final Research Achievements

We proposed a tiny learning machine : "limited general regression neural network (LGRNN)", which is inspired by insect's brain. LGRNN learns new instances one by one, and selects important instances, and store them into a limited capacity. This ability is realized by choosing one of several learning options adaptively by estimating an evaluation function, which predicts expected error due to the execution of each learning option.
The proposed method was applied to a micro-converter of photovoltaics, which improves the electricity generation ability of solar panels. The system consists of a conventional hill climbing mechanisum for finding the maximum power point(MPP), and LGRNN. Normally, the device tracks the MPP using the conventional method, while the LGRNN learns the relationships between the current magnitude of solar-irradiation, tempeleture and MPP. When the solar-irradiation changes abruptly, however, LGRNN yields the predicted MPP for controling the chopper circuit quickly.

Report

(4 results)
  • 2014 Annual Research Report   Final Research Report ( PDF )
  • 2013 Research-status Report
  • 2012 Research-status Report
  • Research Products

    (22 results)

All 2015 2014 2013 2012 Other

All Journal Article (8 results) (of which Peer Reviewed: 7 results,  Acknowledgement Compliant: 2 results) Presentation (12 results) Remarks (1 results) Patent(Industrial Property Rights) (1 results)

  • [Journal Article] Incremental Learning on a budget and a quick calculation method using a tree-search algorithm2015

    • Author(s)
      Akihisa Kato, Hirohito Kawahara, Koichiro Yamauchi
    • Journal Title

      Proceedings of International Joint Conference on Neural Networks 2015

      Volume: 未定

    • Related Report
      2014 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] Incremental Learning on a Budget and its Application to Quick Maximum Power Point Tracking of Photovoltaic Systems2014

    • Author(s)
      Koichiro Yamauchi
    • Journal Title

      Journal of Advanced Computational Inteligence and Intelligent Informatics

      Volume: 18

    • NAID

      130007673226

    • Related Report
      2014 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] A Dynamic Pruning Strategy for Incremental Learning on a Budget2014

    • Author(s)
      Yusuke Kondo and Koichiro Yamauchi
    • Journal Title

      Neural Information Processing 21st International Conference, ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings, Part I

      Volume: I Pages: 295-303

    • DOI

      10.1007/978-3-319-12637-1_37

    • ISBN
      9783319126364, 9783319126371
    • Related Report
      2014 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Acceleration of reinforcement learning via game-based renewal energy management system2014

    • Author(s)
      Kenta Igushi, Takaya Ogiso and Koichiro Yamauchi
    • Journal Title

      Proceedings of SCIS&ISIS 2014

      Volume: なし

    • Related Report
      2014 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 昆虫脳をヒントにした学習エンジンとその応用2014

    • Author(s)
      山内康一郎
    • Journal Title

      ARENA

      Volume: 17

    • Related Report
      2014 Annual Research Report
  • [Journal Article] Incremental learning on a budget and its application to quick maximum power point tracking of photovoltaic systems2014

    • Author(s)
      Koichiro Yamauchi
    • Journal Title

      JACIII

      Volume: vol.18, No.4

    • NAID

      130007673226

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Incremental learning on a budget and its application to power electronics2013

    • Author(s)
      Koichiro Yamauchi, Yusuke Kondo, Akinari Maeda, Kiyotaka Nakano, Akihira Kato
    • Journal Title

      Lecture Notes on Computer Science

      Volume: LNCS8826

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] An importance weighted projection method for incremental learning under unstationary environments2013

    • Author(s)
      Koichiro Yamauchi
    • Journal Title

      Neural Networks (IJCNN), The 2013 International Joint Conference on

      Volume: なし Pages: 1-9

    • DOI

      10.1109/ijcnn.2013.6706779

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Presentation] Soft-ProjectionによるGRNNの制限付きオンライン学習法2014

    • Author(s)
      加藤晶久, 山内康一郎
    • Organizer
      第17回情報論的学習理論ワークショップ(IBIS2014)
    • Place of Presentation
      名古屋大学
    • Year and Date
      2014-11-16 – 2014-11-19
    • Related Report
      2014 Annual Research Report
  • [Presentation] 重み付き射影法によるリソース制限下での追加学習2014

    • Author(s)
      山内康一郎
    • Organizer
      平成26年度 電気・電子・情報関係学会東海支部連合大会
    • Place of Presentation
      中京大学
    • Year and Date
      2014-09-08 – 2014-09-09
    • Related Report
      2014 Annual Research Report
  • [Presentation] Supervised Actor-Critic法を活用した分身エージェントの生成と自動取引への応用2014

    • Author(s)
      加藤 和義, 伊串 健太, 小木曽 貴也, 山内康一郎
    • Organizer
      平成26年度 電気・電子・情報関係学会東海支部連合大会
    • Place of Presentation
      中京大学
    • Year and Date
      2014-09-08 – 2014-09-09
    • Related Report
      2014 Annual Research Report
  • [Presentation] Improved Limited General Regression Neural Network for Embedded Systems2014

    • Author(s)
      Akihisa Kato, Hirohito Kawahara, Koichiro Yamauchi
    • Organizer
      JNNS2014
    • Place of Presentation
      Future University Hakodate
    • Year and Date
      2014-08-27 – 2014-08-29
    • Related Report
      2014 Annual Research Report
  • [Presentation] スマートグリッドゲームと強化学習を組み合わせた売電制御法の検討2013

    • Author(s)
      伊串健太, 山内康一郎
    • Organizer
      第29回ファジィシステムシンポジウム
    • Place of Presentation
      大阪国際大学枚方キャンパス
    • Related Report
      2013 Research-status Report
  • [Presentation] 組み込み用学習法LGRNNとその探索木を用いた高速計算法2013

    • Author(s)
      加藤 晶久, 山内康一郎
    • Organizer
      電子情報通信学会 ニューロコンピューティング研究会
    • Place of Presentation
      岐阜大学サテライトキャンパス
    • Related Report
      2013 Research-status Report
  • [Presentation] ページ置き換えアルゴリズムを導入したLimited General Regression Neural Network2013

    • Author(s)
      近藤 勇祐, 山内康一郎
    • Organizer
      電子情報通信学会 ニューロコンピューティング研究会
    • Place of Presentation
      玉川大学工学部
    • Related Report
      2013 Research-status Report
  • [Presentation] An importance weighted projection method for incremental learning under unstationary environments2013

    • Author(s)
      Koichiro Yamauchi
    • Organizer
      The International Joint Conference on Neural Networks 2013
    • Place of Presentation
      Fair Mont Hotel, Dallas, TX
    • Related Report
      2012 Research-status Report
  • [Presentation] A limited general regression neural network and its application to a quick maximum power point tracker2012

    • Author(s)
      Koichiro Yamauchi, Yusuke Kondo
    • Organizer
      The 22th Annual Conference of Japanese Neural Network Society
    • Place of Presentation
      名古屋工業大学
    • Related Report
      2012 Research-status Report
  • [Presentation] A Quick Maximum Power Point Tracking Converter for Photovoltaic Systems Using A Limited General Regression Neural Network2012

    • Author(s)
      Yusuke Kondo, Koichiro Yamauchi
    • Organizer
      The 22th Annual Conference of Japanese Neural Network Society
    • Place of Presentation
      名古屋工業大学
    • Related Report
      2012 Research-status Report
  • [Presentation] Soft-projection method for incremental learning on a budget2012

    • Author(s)
      Koichiro Yamauchi
    • Organizer
      第15回情報論的学習理論ワークショップ(IBIS2012)
    • Place of Presentation
      筑波大学東京キャンパス文京校舎
    • Related Report
      2012 Research-status Report
  • [Presentation] Incremental learning on a budget and its application to quick maximu power point tracking of photovoltaic systems2012

    • Author(s)
      Koichiro Yamauchi
    • Organizer
      Soft Computing and Intelligent Systems (SCIS) and 13th International Symposium on Advanced Intelligent Systems (ISIS), 2012 Joint 6th International Conference on
    • Place of Presentation
      Kobe Convention Center
    • Related Report
      2012 Research-status Report
  • [Remarks] 山内研究室の研究紹介

    • URL

      http://sakura.cs.chubu.ac.jp/research-renewal-energy-j.html

    • Related Report
      2012 Research-status Report
  • [Patent(Industrial Property Rights)] 太陽光発電ユニット2012

    • Inventor(s)
      山内康一郎
    • Industrial Property Rights Holder
      中部大学
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2012-251792
    • Filing Date
      2012-11-16
    • Related Report
      2012 Research-status Report

URL: 

Published: 2013-05-31   Modified: 2023-03-16  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi