JP2004056969A - Method for estimating operating state of electric device with frequently changing power consumption and monitor system of the same device - Google Patents

Method for estimating operating state of electric device with frequently changing power consumption and monitor system of the same device Download PDF

Info

Publication number
JP2004056969A
JP2004056969A JP2002214182A JP2002214182A JP2004056969A JP 2004056969 A JP2004056969 A JP 2004056969A JP 2002214182 A JP2002214182 A JP 2002214182A JP 2002214182 A JP2002214182 A JP 2002214182A JP 2004056969 A JP2004056969 A JP 2004056969A
Authority
JP
Japan
Prior art keywords
power consumption
spectrum
pattern
electric device
power
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP2002214182A
Other languages
Japanese (ja)
Other versions
JP3892358B2 (en
Inventor
Yukio Nakano
中野　幸夫
Katsuhisa Yoshimoto
由本　勝久
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Central Research Institute of Electric Power Industry
Original Assignee
Central Research Institute of Electric Power Industry
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Central Research Institute of Electric Power Industry filed Critical Central Research Institute of Electric Power Industry
Priority to JP2002214182A priority Critical patent/JP3892358B2/en
Publication of JP2004056969A publication Critical patent/JP2004056969A/en
Application granted granted Critical
Publication of JP3892358B2 publication Critical patent/JP3892358B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02B90/20—Smart grids as enabling technology in buildings sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/242—Home appliances
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
    • Y04S40/124—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wired telecommunication networks or data transmission busses

Abstract

<P>PROBLEM TO BE SOLVED: To estimate the operating state of an electric device with frequently changes its power consumption without entering. <P>SOLUTION: A monitoring system 1 includes a measuring sensor 4 installed near a drop line of a consumer 2 for measuring time series data regarding the power consumption, a spectral analysis conducting means 5 for spectrally analyzing the time series data measured by the sensor 4, and an estimating means 6 for the operating state of the electric device based on a pattern of a spectrum obtained by the means 5. <P>COPYRIGHT: (C)2004,JPO

Description

【０００１】
【発明の属する技術分野】
本発明は、電気機器の動作状態を推定する方法および電気機器モニタリングシステムに関する。さらに詳述すると、本発明は、変動が頻繁に起こる電気機器の動作状態を、電力需要家の家屋内に入らない非侵入的な方法で推定する方法およびシステムに関する。
【０００２】
【従来の技術】
従来、電気機器の動作状態を非侵入的に推定するモニタリングシステムとしては、ＭＩＴ（Ｍａｓｓａｃｈｕｓｅｔｔｓ　Ｉｎｓｔｉｔｕｔｅ　ｏｆ　Ｔｅｃｈｎｏｌｏｇｙ　；　米国）　で開発されたアルゴリスムを用いてＥＰＲＩ（Ｅｌｅｃｔｒｉｃ　Ｐｏｗｅｒ　Ｒｅｓｅａｒｃｈ　Ｉｎｓｔｉｔｕｔｅ；　米国）　が装置化しているものがある。このモニタリングシステムは、電気機器のオン・オフ動作を電力需要家の総電力負荷カーブのステップ状の時間変化として捉え、電気機器の定格消費電力及び力率に基づいてオンあるいはオフとなった電気機器の特定と動作状態の推定を行うものである。
【０００３】
一方、本件出願人によって、電力需要家において設置されている電気機器が発生する高調波電流のパターンに着目し、給電線引込口付近で測定される総負荷電流と電圧から、総負荷電流の基本波並びに高調波の電流及び電圧に対するそれらの位相差を求め、そのパターンから屋内で使用されている電気機器と電気機器個別の動作状態を推定する電気機器モニタリングシステムが提案されている（特開平２０００−２９２４６５号公報等参考）。
【０００４】
【発明が解決しようとする課題】
しかしながら、前者および後者のモニタリングシステムでは、電力需要家の建物内に、洗濯機や炊飯器等の消費電力の変動が頻繁に起こるような電気機器があると、正確な推定が行えない。前者および後者のモニタリングシステムとも、電力需要家の建物内にある全ての電気機器の消費電力は一定時間変動せず一定であることを前提にしており、ある時点での測定データに基づいた推論を行っている。しかし、当該測定の時点において、消費電力の変動が頻繁に起こるような電気機器の動作状態は、過渡状態であることが殆んどである。このため、消費電力の変動が頻繁に起こるような電気機器のオン・オフ動作を、電力需要家の総電力負荷カーブのステップ状の時間変化として捉えるのは困難である。また、消費電力の変動が頻繁に起こるような電気機器では、高調波のパターンが無数に表れるため、高調波のパターンに基づく電気機器の動作状態の特定も困難である。
【０００５】
そこで本発明は、消費電力の変動が頻繁に起こる電気機器の動作状態を非侵入的な方法で推定できる方法およびモニタリングシステムを提供することを目的とする。
【０００６】
【課題を解決するための手段】
かかる目的を達成するため、請求項１記載の発明は、消費電力の変動が頻繁に起こる対象電気機器の動作状態を電力需要家の家屋内に入らずに推定する方法であり、電力需要家の給電線引込口付近において消費電力に関する時系列データを測定し、当該測定された時系列データに対してスペクトル解析を行い、当該スペクトル解析により得られるスペクトルのパターンに基づいて対象電気機器の動作状態を推定するようにしている。
【０００７】
また、請求項２記載の発明は、消費電力の変動が頻繁に起こる対象電気機器の動作状態を電力需要家の家屋内に入らずに推定するモニタリングシステムであり、電力需要家の給電線引込口付近に設置されて消費電力に関する時系列データを測定する測定センサーと、測定センサーで測定された時系列データに対してスペクトル解析を行うスペクトル解析実行手段と、スペクトル解析実行手段により得られたスペクトルのパターンに基づいて対象電気機器の動作状態を推定する推定手段とを備えるようにしている。
【０００８】
消費電力に関する時系列データのスペクトルのパターンには、消費電力の変動が頻繁に起こる電気機器が稼動している場合には、比較的短い周期の成分が突出して大きくなるという特徴が表れるのに対し、消費電力の変動が頻繁に起こる電気機器が稼動しておらず、消費電力の変動が無いか或いは消費電力が変動しても当該変動の周期が長い電気機器が稼動している場合には、そのような特徴は表れない。したがって、測定された時系列データに基づいて当該特徴の有無を調べることで、消費電力が頻繁に変動する電気機器である対象電気機器が動作しているか否かを推定することが可能となる。
【０００９】
また、請求項３記載の発明は、請求項２記載の消費電力の変動が頻繁に起こる電気機器のモニタリングシステムにおいて、推定手段は、対象電気機器が動作している場合に表れる消費電力に関する時系列データのスペクトルのパターンが予め記憶されているデータベースを有し、スペクトル解析実行手段により得られたスペクトルのパターンとデータベースに予め記憶されているスペクトルのパターンとのパターンマッチングを行い、当該パターンマッチングの結果に基づいて対象電気機器の動作状態を推定するようにしている。
【００１０】
この場合、推定手段は、スペクトル解析実行手段により得られたスペクトルのパターンと、データベースに予め記憶されているスペクトルのパターンとを比較して、スペクトル解析実行手段により得られたスペクトルと一致するものをデータベースから検索する。例えば、一致するパターンがあった場合は、対象電気機器は動作状態にある（即ち、電源オンの状態にある）と推定され、一致するパターンがなかった場合は、対象電気機器は電源オフの状態にあると推定される。尚、ここでいう一致とは、必ずしも完全一致には限られず、類似範囲にある場合に一致とみなすようにしても良い。
【００１１】
また、請求項４記載の発明は、請求項２記載の消費電力の変動が頻繁に起こる電気機器のモニタリングシステムにおいて、推定手段は、学習機能を有し、消費電力に関する時系列データのスペクトルのパターンとその時の解答である対象電気機器の動作状態とが教師データとして与えられて予め学習が行われており、スペクトル解析実行手段により得られたスペクトルのパターンから対象電気機器の動作状態をパターン認識によって推定するようにしている。
【００１２】
この場合、推定手段は、スペクトル解析実行手段により得られたスペクトルのパターンが入力されることにより、学習時に与えられた教師データおよび学習によって得られた推定能力によってパターン認識を行い、入力されたスペクトルのパターンの解答である対象電気機器の動作状態の推定結果（例えば、どの対象電気機器の電源がオンまたはオフの状態にあるか）を出力する。
【００１３】
【発明の実施の形態】
以下、本発明の構成を図面に示す実施形態に基づいて詳細に説明する。
【００１４】
図１から図５に本発明の実施の一形態を示す。本発明の消費電力の変動が頻繁に起こる電気機器の動作状態を推定する方法は、電力需要家の給電線引込口付近において消費電力に関する時系列データを測定し、当該測定された時系列データに対してスペクトル解析を行い、当該スペクトル解析により得られるスペクトルのパターンに基づいて消費電力の変動が頻繁に起こる対象電気機器の動作状態を推定するものである。この本発明方法は、図１に示すように、消費電力の変動が頻繁に起こる電気機器の動作状態を推定するモニタリングシステムとして装置化される。即ち、このモニタリングシステム１は、電力需要家２の給電線引込口付近に設置されて消費電力に関する時系列データを測定する測定センサー４と、測定センサー４で測定された時系列データに対してスペクトル解析を行うスペクトル解析実行手段５と、スペクトル解析実行手段５により得られたスペクトルのパターンに基づいて対象電気機器の動作状態を推定する推定手段６とを備えるようにしている。
【００１５】
対象電気機器とは、電力需要家２の屋内に設置されている電気機器のうち消費電力の変動が頻繁に起こる電気機器であって、モニタリングシステム１が動作状態の推定対象とする電気機器である。例えば本実施形態では、電力需要家２の屋内の給電線下流には、電気機器として、テレビジョン受像機３ａ、冷蔵庫３ｂ、エアコンデショナー３ｃ、白熱灯や蛍光灯などの照明機器３ｄ、洗濯機３ｅ、炊飯器３ｆ等が接続されているものとする。消費電力の変動が頻繁に起こる電気機器としては、洗濯動作時において反転を繰り返す洗濯機３ｅや、釜を熱するヒータを頻繁にオン・オフする炊飯器３ｆが挙げられる。テレビジョン受像機３ａ、冷蔵庫３ｂ、エアコンディショナー３ｃ、照明機器３ｄは、消費電力の変動が無いか、或いは消費電力が変動しても当該変動の周期が洗濯機３ｅや炊飯器３ｆと比較してずっと長い。本実施形態では、対象電気機器を洗濯機３ｅおよび炊飯器３ｆとした例について説明する。ただし、対象電気機器は、本例に限定されるものではない。また、対象電気機器は単数または単一種に限られず、複数または複数種であっても良い。尚、電気機器が接続される電力需要家２に設置されている電気機器は、家庭内コンセントに接続され、電力量計から給電線（即ち、引込線７及び電柱８に架設された電線）を介して電気事業者等の電力系統に接続されている。
【００１６】
本実施形態の測定センサー４は、電力需要家２の建物外、例えば電力需要家２の給電線引込口あるいは電力量計の一箇所に設置している。このように測定センサー４を引込口付近に一箇所に設置する構成とすることにより、モニタリングシステム１は非侵入的なシステムとなる。即ち、対象電気機器に測定センサー４を直接取り付ける必要がないため、モニタリングシステム１を電力需要家２に導入するに際して、プライバシーの侵害等の問題は無く、また追加の配線等を施す工事が少なくて済む。
【００１７】
本実施形態の測定センサー４は、例えば電力需要家２の給電線引込口付近において総消費電力を測定する電力計としている。この電力計としては、有効電力を測定するための周知の計器（例えば、電流力計を用いたもの、誘導形（移動磁界）を利用したもの、ホール効果を利用したもの、熱電対やダイオードの二乗特性や時分割乗算回路などを利用したものなど）を用いて良く、電力計の構成が特に限定されるものではない。
【００１８】
ここで、本実施形態では、測定センサー４による時系列データの測定において、最初の測定時刻から最後の測定時刻までの時間を測定時間幅と呼び、測定時間幅内におけるサンプリングの間隔（ある測定時刻から次の測定時刻まで時間）を測定時間間隔と呼ぶ。測定時間間隔および測定時間幅は、例えば、消費電力に関する時系列データのスペクトルのパターンに、対象電気機器の特徴が表れ得るように設定することが好ましい。本発明者等が種々実験検討した結果、測定時間間隔を１秒とし、測定時間幅を５分から１０分としたところ、洗濯機３ｅの消費電力に関する時系列データのスペクトルのパターンおよび炊飯器３ｆの消費電力に関する時系列データのスペクトルのパターンに、他の電気機器とは明確に区別できる特徴が表れることが知見された。そこで、本実施形態では、測定時間間隔を１秒で一定とし、測定時間幅を５分から１０分としている。ただし、これらの値は好適な例であって、測定時間間隔および測定時間幅が本実施形態の例に限定されるものではない。
【００１９】
本実施形態のスペクトル解析実行手段５は、スペクトル解析（フーリエ解析とも呼ばれる）を実行する手段であり、入力信号を周期（もしくは周波数）成分毎に分解して当該成分の大きさを求める手段である。スペクトル解析実行手段５が実行するスペクトル解析には、例えばフーリエ変換やパワースペクトル解析等の既知の方法を採用して良い。例えば本実施形態のスペクトル解析実行手段５は、入力信号としての消費電力の時系列データを、周期成分毎に分解し、各周期成分の大きさをスペクトルとして算出する手段として構成される。尚、スペクトル解析実行手段５は、入力信号としての消費電力の時系列データを、周期成分毎に分解し、各周期成分の大きさをパワースペクトル密度として算出する手段であっても良い。この場合は、周期成分毎のパワースペクトル密度が、スペクトル解析実行手段５により得られるスペクトルのパターンとなる。また、周期の刻み幅は必ずしも整数値でなくても良い。例えば、周期の値とスペクトルの値との関係を示すグラフ（図３，図５参照）を滑らかに描くことができるように、周期の刻み幅を調整しても良い。このようなスペクトル解析実行手段５は、例えば上記演算内容を実行する電子回路を実装した専用機として構成しても良く、或いは例えば汎用計算機（コンピュータ）に上記演算内容を実行させるソフトウェアを実装することにより構成しても良い。
【００２０】
本実施形態の推定手段６は、対象電気機器が動作している場合に表れる消費電力に関する時系列データのスペクトルのパターンが予め記憶されているデータベース９を有し、スペクトル解析実行手段５により得られたスペクトルのパターンとデータベース９に予め記憶されているスペクトルのパターンとのパターンマッチングを行い、当該パターンマッチングの結果に基づいて対象電気機器の動作状態を推定するようにしている。
【００２１】
この推定手段６は、例えば、中央演算処理部（ＣＰＵ）、主記憶装置、外部記憶装置、スペクトル解析実行手段５等との通信インターフェースなどのハードウェア資源と、これらのハードウェア資源を制御するオペレーティングシステムと、対象電気機器が動作している場合に表れる消費電力に関する時系列データのスペクトルのパターンを外部記憶装置に記憶してデータベース９を構築する処理と、スペクトル解析実行手段５により得られたスペクトルのパターンとデータベース９に記憶されているスペクトルのパターンとのパターンマッチング処理とを実行するデータベース管理システムなどのソフトウェア資源とを有するコンピュータとして構成される。
【００２２】
データベース９は、例えば次のようにして予め構築される。即ち、対象電気機器のみを稼動させ、測定センサー４により消費電力の時系列データを測定時間間隔を１秒で且つ測定時間幅を５分から１０分として測定し、スペクトル解析実行手段５により当該時系列データのスペクトルのパターンを得て、当該スペクトルのパターンと稼動させた対象電気機器を特定する情報とを関連付けてデータベース９に格納する。
【００２３】
例えば本実施形態では、洗濯機３ｅのみを稼動させた場合におけるスペクトルのパターンと稼動させた対象電気機器が洗濯機３ｅであることを示すコードとの組と、炊飯器３ｆのみを稼動させた場合におけるスペクトルのパターンと稼動させた対象電気機器が炊飯器３ｆであることを示すコードとの組と、洗濯機３ｅおよび炊飯器３ｆのみを稼動させた場合におけるスペクトルのパターンと稼動させた対象電気機器が洗濯機３ｅおよび炊飯器３ｆであることを示すコードとの組とをデータベース９に格納するようにしている。ただし、洗濯機３ｅおよび炊飯器３ｆを組み合わせて稼動させる必要は必ずしもない。例えば、推定手段６としてのコンピュータが有する演算機能により、複数種の対象電気機器をそれぞれ単独で稼動させた場合のスペクトルのパターンを種々の組み合わせで重ね合わせて、複数種の対象電気機器の種々の組み合わせに対応するスペクトルのパターンを得るようにしても良い。例えば、洗濯機３ｅのみを稼動させた場合におけるスペクトルのパターンと、炊飯器３ｆのみを稼動させた場合におけるスペクトルのパターンとを重ね合わせたパターンを、推定手段６としてのコンピュータが有する演算機能により得て、当該得られたパターンと対象電気機器が洗濯機３ｅおよび炊飯器３ｆであることを示すコードとの組をデータベース９に格納するようにしても良い。この場合、複数種の対象電気機器を組み合わせて種々の動作状態状況を作る必要が無く、複数種の対象電気機器を組み合わせた種々の動作状態状況に対応するスペクトルのパターンを自動生成することができる。
【００２４】
図２は、洗濯機３ｅのみを稼動させた場合における測定センサー４により得られた消費電力の時系列データ（１２８秒間）を示す。図３は、図２に示す時系列データを入力信号としてスペクトル解析実行手段５により得られた周期成分毎のスペクトルを示す。また、図４は、炊飯器３ｆのみを稼動させた場合における測定センサー４により得られた消費電力の時系列データ（１２８秒間）を示す。図５は、図４に示す時系列データを入力信号としてスペクトル解析実行手段５により得られた周期成分毎のスペクトルを示す。図２および図４から、消費電力が頻繁に変動していることが確認できる。尚、スペクトル解析実行手段５が実行するスペクトル解析には、ＦＦＴ（高速フーリエ変換）を用いた。
【００２５】
例えば本実施形態では、スペクトル解析実行手段５により得られたスペクトルの値（数値データ）を周期順に並べてデータ系列を作成し、当該データ系列をスペクトルのパターンとしてデータベース９に格納するようにしている。但し、周期の値とスペクトルの値との関係を表すグラフ（画像データ）をスペクトルのパターンとしてデータベース９に格納するようにしても良く、或いは当該グラフの特徴を抽出して当該特徴をスペクトルのパターンとしてデータベース９に格納するようにしても良い。例えば、図３に示すように、洗濯機３ｅのみを稼動させた場合における周期の値とスペクトルの値との関係を表すグラフには、周期の値が２．５秒、３．３秒、７．５秒であるときに、スペクトルが突出している（即ちピークを形成している）という特徴があることが分かる。
【００２６】
消費電力の変動が無いか或いは消費電力が変動しても当該変動の周期が長い電気機器（例えば冷蔵庫３ｂやテレビジョン受像機３ａなど）では、比較的短い周期（例えば１０秒以下程度）においてスペクトルの値が突出する（即ちピークが形成される）という特徴が表れることはない。したがって、当該特徴の有無を捉えることで、消費電力が頻繁に変動する電気機器である対象電気機器が動作しているか否かを推定することが可能となる。さらに、種類が異なる対象電気機器間では、例えば洗濯機３ｅと炊飯器３ｆとでは、周期の値とスペクトルの値との関係を表すグラフのピークの数や位置或いは大きさ等に差異がある。したがって、当該差異点を捉えることで、複数種の対象電気機器が存在する場合でも、どの対象電気機器が動作しているかを推定することが可能となる。
【００２７】
本実施形態の推定手段６によるパターンマッチング処理は、例えば次のようにして行う。即ち、スペクトル解析実行手段５から推定手段６に周期成分毎のスペクトルの値が入力されると、推定手段６では、当該スペクトルの値を周期順に並べてデータ系列を作成し、当該データ系列を入力のスペクトルのパターン（以下、入力パターンと呼ぶ）として、当該パターンと一致するものを、データベース９から検索する。ここでいう一致とは、必ずしも完全一致には限られず、類似範囲にある場合に一致とみなすようにしても良い。例えば、本実施形態の推定手段６では、入力パターンとデータベース９に格納されているスペクトルのパターン（以下、格納パターンと呼ぶ）との相関係数を求めて、当該相関係数の値が予め定めた値以上となる場合に、入力パターンと格納パターンとが一致していると判断するようにしている。
【００２８】
尚、推定手段６によるパターンマッチング処理は、上記の例に限定されるものではなく、例えば次のように処理しても良い。例えば、データベース９に、対象電気機器についての周期の値とスペクトルの値との関係を表すグラフのピークにおける周期の値とスペクトルの値とを、格納パターンとして予め格納しておく。そして、スペクトル解析実行手段５から推定手段６に周期成分毎のスペクトルの値が入力されると、推定手段６では当該入力データのうちピークを形成するスペクトルの値と当該スペクトルの値に対応する周期の値とを、入力パターンとして抽出する。ピークが複数表れる場合には、全てのピークについてスペクトルの値と当該スペクトルの値に対応する周期の値とを抽出する。次に推定手段６では、このように抽出されたスペクトルのパターン（入力パターン）と一致するものを、データベース９から検索する。ここでいう一致とは、必ずしも完全一致には限られず、類似範囲にある場合（例えば入力パターンと格納パターンとの差が予め定めた許容範囲にある場合に）に一致とみなすようにしても良い。
【００２９】
以上のように構成されるモニタリングシステム１によれば、例えば次のようにして対象電気機器の動作状態を非侵入的な方法で推定する。先ず、測定センサー４では、電力需要家２の家屋内に入らない非侵入的な方法で、消費電力の時系列データを、測定時間間隔を１秒で且つ測定時間幅を５分から１０分として測定する。次に、スペクトル解析実行手段５では、当該測定された時系列データに対してスペクトル解析を行い、周期成分毎のスペクトルを推定手段６に対して出力する。次に、推定手段６では、入力された周期成分毎のスペクトルを周期順に並べて入力パターンとし、データベース９に予め格納されている格納パターンの中に当該入力パターンと一致するものが有るか検索する。
【００３０】
検索の結果、一致する格納パターンがあった場合は、当該格納パターンに関連付けられて記憶されているコードに対応する対象電気機器が、動作状態にある（即ち、電源オンの状態にある）と推定される。一方、入力パターンと一致する格納パターンがなかった場合は、対象電気機器は電源オフの状態にあると推定される。尚、当該推定結果は、ディスプレイやプリンタ等の出力装置に出力するようにしても良く、或いは推定手段６が備える外部記憶装置に記憶するようにしても良く、或いは通信回線（例えば電話回線、光ファイバ専用回線、ＰＨＳ等）を介して遠隔の情報処理装置に送信するようにしても良い。当該推定結果は、電力需要家２自身が利用できる以外に、通信回線を経由して電力会社やＥＳＣＯ（Ｅｎｅｒｇｙ　Ｓｅｒｖｉｃｅ　Ｃｏｍｐａｎｙ）等が利用できる。
【００３１】
２１世紀初頭には、需要家情報ネットワークが整備され、多用な情報サービスが電力需要家２へ提供されると同時に、電力需要家２の側の情報もネットワークを通して収集され、これらの情報は電気事業者等の経営にも反映されてゆくものと期待される。例えば、電気事業者にとって電力需要家２の側の重要な情報の一つに電力需要家２が保有する電気機器の構成や使用実態に関する情報があるが、これらはＤＳＭ（Ｄｅｍａｎｄ　Ｓｉｄｅ　Ｍａｎａｇｅｍｅｎｔ）の効果評価、潜在需要の予測、需要変化の予測、負荷率低下（悪化）の要因分析、きめ細かな季時別料金システムの構築、電力需要家２への各種サービスの提供等を行う上で必要不可欠である。本発明のモニタリングシステム１は、上述したニーズに応えることができる有力なシステムの一つである。
【００３２】
また、本発明の消費電力の変動が頻繁に起こる電気機器のモニタリングシステム１と、従来の電気機器モニタリングシステム（特開平２０００−２９２４６５号公報等参考）を組み合わせて用いることもできる。即ち、従来の電気機器モニタリングシステムでは動作状態の特定が困難となる消費電力の変動が頻繁に起こる電気機器については、本発明のモニタリングシステム１で動作状態を推定し、消費電力の変動が無いか或いは消費電力が変動しても当該変動の周期が長い電気機器については、従来の電気機器モニタリングシステムで動作状態を推定する、といったことが可能となる。これにより、信頼性の高い電気機器モニタリングシステムを構築できる。
【００３３】
なお、上述の実施形態は本発明の好適な実施の一例ではあるがこれに限定されるものではなく、本発明の要旨を逸脱しない範囲において種々変形実施可能である。例えば、上述の実施形態では、測定センサー４は消費電力を測定するものを用いたが、測定センサー４が測定対象とするデータは、必ずしも消費電力に限られない。測定センサー４が測定対象とするデータは、対象電気機器が動作していることに起因する消費電力の頻繁な変動が反映され得るデータであれば良い。
【００３４】
例えば、測定センサー４を電流を測定する電流計としても良い。電流計としては、電流を測定するための周知の計器を用いて良い。測定センサー４により電流の時系列データを測定する場合も上述の実施形態と同様に、当該測定した電流の時系列データにスペクトル解析を施すことにより得られるスペクトルのパターンには、対象電気機器の動作状態を推定できる特徴が表れる。また、測定センサー４は、力率または無効電力を測定する計器であっても良い。
【００３５】
本明細書でいう電力需要家２の給電線引込口付近において測定する「消費電力に関する時系列データ」には、対象電気機器が動作していることに起因する消費電力の頻繁な変動が反映され得るデータ全般（例えば消費電力、電流、力率、無効電力など）が含まれる。そして、測定センサー４は、そのようなデータを測定できる手段であれば良い。
【００３６】
また、例えば推定手段６として、学習機能を有し、消費電力に関する時系列データのスペクトルのパターンとその時の解答である対象電気機器の動作状態とが教師データとして与えられて予め学習が行われており、スペクトル解析実行手段５により得られたスペクトルのパターンから対象電気機器の動作状態をパターン認識によって推定するものを採用しても良い。
【００３７】
このような推定手段６は、例えば帰納学習能力を有するニューラルネットワーク（ニューロコンピュータとも呼ばれる）として実現できる。ニューラルネットワークは、人間の脳の神経細胞を模倣した情報処理システムであり、神経細胞（ニューロン）にあたるユニットを、ネットワーク状に多数結合した構造になっている。各ユニットは、結合された他のユニットからの入力の総和に応じて、出力を発生する。この時、結合の強さ（重み付け）を調整することで、全体の入力に対して最善の出力が得られるように、ニューラルネットワークを学習させることができる。
【００３８】
推定手段６としてのニューラルネットワークの学習は、例えば次のようにして行う。即ち、電力需要家２内に存在する対象電気機器を含む複数の電気機器個々につけられたスイッチを入り切りして、複数の電気機器が種々の動作状態となる状況を作る。当該状況のそれぞれについて、即ち複数の電気機器の種々の動作状態の各組み合わせについて、測定センサー４とスペクトル解析実行手段５とを用いて、消費電力に関する時系列データのスペクトルのパターン（例えば周期成分毎のスペクトル）を得るようにする。そして、当該得られた種々のスペクトルのパターンと、各パターンに対応した解答である対象電気機器の動作状態（例えば、どの対象電気機器の電源がオンまたはオフの状態であったか等）とを、教師データとしてニューラルネットワークに与えて、学習を行う。尚、ニューラルネットワークによる推定精度を向上させるための学習を、電力需要家２の外部から電話回線、光ファイバー専用回線等を利用して外部から行うようにしても良い。このようにしてニューラルネットワークを教師データで学習させた後に、実際に電力需要家２の対象電気機器の動作状態の推定を行うことになる。
【００３９】
この場合、モニタリングシステム１では、例えば次のようにして対象電気機器の動作状態を非侵入的な方法で推定する。測定センサー４では、電力需要家２の家屋内に入らない非侵入的な方法で消費電力に関する時系列データを測定する。尚、測定時間間隔および測定時間幅は、例えば上述の実施形態と同様として良い。次に、スペクトル解析実行手段５では当該測定された時系列データに対してスペクトル解析を行い、スペクトルのパターン（例えば周期成分毎のスペクトル）を推定手段６に対して出力する。推定手段６では、当該スペクトルのパターンが入力されると、学習時に与えられた教師データおよび学習によって得られた推定能力によってパターン認識を行い、入力されたスペクトルのパターンの解答である対象電気機器の動作状態の推定結果（例えば、どの対象電気機器の電源がオンまたはオフの状態にあるか）を出力する。尚、当該推定結果は、ディスプレイやプリンタ等の出力装置に出力するようにしても良く、或いは推定手段６が備える外部記憶装置に記憶するようにしても良く、或いは通信回線（例えば電話回線、光ファイバ専用回線、ＰＨＳ等）を介して遠隔の情報処理装置に送信するようにしても良い。当該推定結果は、電力需要家２自身が利用できる以外に、通信回線を経由して電力会社やＥＳＣＯ（Ｅｎｅｒｇｙ　Ｓｅｒｖｉｃｅ　Ｃｏｍｐａｎｙ）等が利用できる。
【００４０】
尚、推定手段６のパターン認識のアルゴリズムは必ずしもニューラルネットワークを利用したものに限られず、その他の既知または新規のアルゴリズムを採用して良い。
【００４１】
【発明の効果】
以上の説明から明らかなように、請求項１および２に記載の本発明によれば、消費電力の変動が頻繁に起こる電気機器が稼動することにより表れる消費電力に関する時系列データのスペクトルのパターンの特徴に着目し、従来のモニタリングシステムでは動作状態の推定が困難であった消費電力の変動が頻繁に起こる電気機器の動作状態を、非侵入的な方法で推定することができる効果がある。
【００４２】
さらに、請求項３記載の本発明によれば、データベース技術を応用することにより、消費電力の変動が頻繁に起こる電気機器の動作状態を非侵入的な方法で推定することができる。
【００４３】
さらに、請求項４記載の本発明によれば、ニューラルネットワーク等のパターン認識手法を応用することにより、消費電力の変動が頻繁に起こる電気機器の動作状態を非侵入的な方法で推定することができる。
【図面の簡単な説明】
【図１】本発明の消費電力の変動が頻繁に起こる電気機器の動作状態を推定する方法およびモニタリングシステムの実施の一形態を示す概略構成図である。
【図２】洗濯機のみを稼動させた場合における消費電力の時系列データを示し、縦軸は消費電力［Ｗ］を、横軸は時間経過［秒］を示す。
【図３】図２における消費電力の時系列データについてスペクトル解析を行った結果を示し、縦軸はスペクトル［Ｗ］を、横軸は周期成分［秒］を示す。
【図４】炊飯器のみを稼動させた場合における消費電力の時系列データを示し、縦軸は消費電力［Ｗ］を、横軸は時間経過［秒］を示す。
【図５】図４における消費電力の時系列データについてスペクトル解析を行った結果を示し、縦軸はスペクトル［Ｗ］を、横軸は周期成分［秒］を示す。
【符号の説明】
１　モニタリングシステム
２　電力需要家
４　測定センサー
５　スペクトル解析実行手段
６　推定手段
９　データベース[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a method for estimating an operation state of an electric device and an electric device monitoring system. More specifically, the present invention relates to a method and a system for estimating an operating state of an electrical device that frequently fluctuates in a non-invasive manner that does not enter a house of a power consumer.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, as a monitoring system for non-invasively estimating an operating state of an electric device, EPRI (Electric Power Research Institute; USA) has been implemented using an algorithm developed at MIT (Massachusetts Institute of Technology; USA). There is something. This monitoring system captures the on / off operation of electrical equipment as a step-like change over time in the total power load curve of a power consumer, and turns on or off electrical equipment based on the rated power consumption and power factor of the electrical equipment. Is specified and the operation state is estimated.
[0003]
On the other hand, the applicant focused on the pattern of the harmonic current generated by the electric equipment installed in the electric power consumer, and based on the total load current and the voltage measured near the feed line entrance, the basics of the total load current were calculated. An electrical equipment monitoring system has been proposed in which the phase difference between the current and voltage of waves and harmonics is obtained, and the operating state of the electrical equipment used indoors and the individual electrical equipment is estimated from the pattern (Japanese Patent Laid-Open No. 2000-2000). -292465 reference).
[0004]
[Problems to be solved by the invention]
However, in the former and latter monitoring systems, accurate estimation cannot be performed if there is an electrical device such as a washing machine or a rice cooker that frequently fluctuates in power consumption in a building of a power consumer. Both the former and latter monitoring systems are based on the assumption that the power consumption of all electrical equipment in the power consumer's building does not fluctuate for a certain period of time and remains constant, and makes inferences based on measurement data at a certain point in time. Is going. However, at the time of the measurement, the operation state of the electric device in which the power consumption frequently changes is almost a transient state. For this reason, it is difficult to grasp the on / off operation of the electric device in which the power consumption frequently fluctuates as a step-like time change of the total power load curve of the power consumer. Further, in an electric device in which power consumption fluctuates frequently, an infinite number of harmonic patterns appear, so it is difficult to specify the operation state of the electric device based on the harmonic pattern.
[0005]
Therefore, an object of the present invention is to provide a method and a monitoring system capable of estimating an operation state of an electric device in which power consumption fluctuates frequently by a non-invasive method.
[0006]
[Means for Solving the Problems]
In order to achieve this object, the invention according to claim 1 is a method of estimating an operation state of a target electric device in which power consumption fluctuates frequently without entering a house of a power consumer. Measure time-series data related to power consumption near the feed line entrance, perform spectrum analysis on the measured time-series data, and determine the operating state of the target electrical device based on the spectrum pattern obtained by the spectrum analysis. I try to estimate.
[0007]
According to a second aspect of the present invention, there is provided a monitoring system for estimating an operation state of a target electrical device in which power consumption fluctuates frequently without entering a house of a power consumer. A measurement sensor that is installed in the vicinity to measure time-series data related to power consumption, a spectrum analysis execution unit that performs spectrum analysis on the time-series data measured by the measurement sensor, and a spectrum analysis unit that obtains a spectrum obtained by the spectrum analysis execution unit. Estimating means for estimating the operation state of the target electric device based on the pattern.
[0008]
The spectrum pattern of the time-series data related to power consumption has the characteristic that components with relatively short periods prominently increase when electrical equipment that frequently changes in power consumption is operating. In the case where the electric device in which the power consumption fluctuates frequently is not operating, and the power device does not fluctuate in power consumption or the electric device in which the fluctuation cycle is long even if the power consumption fluctuates, Such features do not appear. Therefore, by examining the presence or absence of the feature based on the measured time-series data, it is possible to estimate whether or not the target electric device, which is an electric device whose power consumption fluctuates frequently, is operating.
[0009]
According to a third aspect of the present invention, in the electrical equipment monitoring system according to the second aspect of the present invention, the power consumption varies frequently, and the estimating means includes a time series related to the power consumption appearing when the target electrical equipment is operating. It has a database in which a spectrum pattern of data is stored in advance, and performs pattern matching between the spectrum pattern obtained by the spectrum analysis execution means and the spectrum pattern stored in advance in the database, and the result of the pattern matching is performed. The operation state of the target electric device is estimated based on the information.
[0010]
In this case, the estimating unit compares the spectrum pattern obtained by the spectrum analysis executing unit with the spectrum pattern stored in advance in the database, and determines the one that matches the spectrum obtained by the spectrum analysis executing unit. Search from database. For example, when there is a matching pattern, it is estimated that the target electric device is in an operating state (that is, in a power-on state), and when there is no matching pattern, the target electric device is in a power-off state. It is estimated that there is. Note that the match here is not necessarily limited to a perfect match, and may be regarded as a match when they are in a similar range.
[0011]
According to a fourth aspect of the present invention, in the electrical device monitoring system according to the second aspect, the power consumption frequently fluctuates, and the estimating means has a learning function, and a spectrum pattern of the time-series data related to the power consumption. And the operation state of the target electric device, which is the answer at that time, is given as teacher data and learning is performed in advance, and the operation state of the target electric device is determined by pattern recognition from the spectrum pattern obtained by the spectrum analysis execution means. I try to estimate.
[0012]
In this case, the estimating means performs pattern recognition based on the teacher data given at the time of learning and the estimating ability obtained by learning by inputting the spectrum pattern obtained by the spectrum analysis executing means. And outputs the result of estimating the operation state of the target electric device (for example, which target electric device is in the ON or OFF state), which is the answer to the above pattern.
[0013]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, the configuration of the present invention will be described in detail based on an embodiment shown in the drawings.
[0014]
1 to 5 show an embodiment of the present invention. The method of the present invention for estimating the operation state of an electrical device in which fluctuations in power consumption frequently occur measures time-series data related to power consumption in the vicinity of a power line entrance of a power consumer, and converts the measured time-series data to the time-series data. The spectrum analysis is performed on the target electric equipment, and the operation state of the target electric device in which the power consumption frequently changes is estimated based on the spectrum pattern obtained by the spectrum analysis. As shown in FIG. 1, the method of the present invention is implemented as a monitoring system for estimating an operation state of an electric device in which power consumption frequently fluctuates. That is, the monitoring system 1 includes a measurement sensor 4 installed near the power supply line entrance of the power consumer 2 for measuring time-series data related to power consumption, and a spectrum sensor for the time-series data measured by the measurement sensor 4. The apparatus includes a spectrum analysis executing means 5 for performing analysis, and an estimating means 6 for estimating an operation state of the target electric device based on a spectrum pattern obtained by the spectrum analysis executing means 5.
[0015]
The target electric device is an electric device whose power consumption frequently changes among electric devices installed indoors of the electric power consumer 2, and is an electric device whose operation state is to be estimated by the monitoring system 1. . For example, in the present embodiment, a television receiver 3a, a refrigerator 3b, an air conditioner 3c, lighting devices 3d such as incandescent lamps and fluorescent lamps, and washing machines 3e are provided downstream of the power supply line inside the power consumer 2 as electric devices. , A rice cooker 3f and the like are connected. Examples of the electrical equipment in which power consumption fluctuates frequently include a washing machine 3e that repeats inversion during a washing operation, and a rice cooker 3f that frequently turns on and off a heater that heats a kettle. In the television receiver 3a, the refrigerator 3b, the air conditioner 3c, and the lighting device 3d, the power consumption does not fluctuate, or even if the power consumption fluctuates, the cycle of the fluctuation is compared with the washing machine 3e and the rice cooker 3f. Much longer. In the present embodiment, an example in which the target electric devices are a washing machine 3e and a rice cooker 3f will be described. However, the target electric device is not limited to this example. Further, the target electric device is not limited to one or a single type, but may be a plurality or plural types. In addition, the electric equipment installed in the electric power consumer 2 to which the electric equipment is connected is connected to a household outlet, and is connected to a power meter via a power supply line (that is, an electric wire installed on the drop-in line 7 and the electric pole 8). Connected to the power system of electric utilities.
[0016]
The measurement sensor 4 of the present embodiment is installed outside the building of the power consumer 2, for example, at a feed line entrance of the power consumer 2 or at one place of a watt-hour meter. The monitoring system 1 is a non-invasive system by installing the measurement sensor 4 at one location near the entrance as described above. That is, since it is not necessary to directly attach the measurement sensor 4 to the target electric equipment, there is no problem of privacy infringement when introducing the monitoring system 1 to the electric power consumer 2, and there is little construction work for providing additional wiring and the like. I'm done.
[0017]
The measurement sensor 4 of the present embodiment is, for example, a wattmeter that measures the total power consumption in the vicinity of the power supply line entrance of the power consumer 2. Examples of the power meter include well-known meters for measuring active power (for example, a device using an ammeter, a device using an inductive type (moving magnetic field), a device using the Hall effect, a thermocouple and a diode). (A configuration using a square characteristic, a time-division multiplication circuit, or the like) may be used, and the configuration of the power meter is not particularly limited.
[0018]
Here, in the present embodiment, in the measurement of the time-series data by the measurement sensor 4, the time from the first measurement time to the last measurement time is referred to as a measurement time width, and a sampling interval (a certain measurement time) within the measurement time width. From the time until the next measurement time) is called a measurement time interval. It is preferable that the measurement time interval and the measurement time width are set, for example, so that the characteristics of the target electric device can be displayed in a spectrum pattern of the time-series data regarding power consumption. As a result of various experiments and studies conducted by the present inventors, when the measurement time interval was set to 1 second and the measurement time width was set to 5 to 10 minutes, the spectrum pattern of the time-series data relating to the power consumption of the washing machine 3e and the rice cooker 3f. It has been found that the pattern of the spectrum of the time-series data on power consumption has characteristics that can be clearly distinguished from other electric devices. Therefore, in the present embodiment, the measurement time interval is fixed at 1 second, and the measurement time width is set to 5 to 10 minutes. However, these values are preferable examples, and the measurement time interval and the measurement time width are not limited to the example of the present embodiment.
[0019]
The spectrum analysis executing means 5 of the present embodiment is a means for executing a spectrum analysis (also called a Fourier analysis), and is a means for decomposing an input signal for each period (or frequency) component and obtaining the size of the component. . For the spectrum analysis executed by the spectrum analysis executing means 5, a known method such as Fourier transform or power spectrum analysis may be adopted. For example, the spectrum analysis execution unit 5 of the present embodiment is configured as a unit that decomposes time-series data of power consumption as an input signal into periodic components and calculates the magnitude of each periodic component as a spectrum. Note that the spectrum analysis executing means 5 may be means for decomposing time-series data of power consumption as an input signal for each periodic component, and calculating the magnitude of each periodic component as a power spectral density. In this case, the power spectrum density for each periodic component is a spectrum pattern obtained by the spectrum analysis executing means 5. Further, the step size of the cycle does not necessarily have to be an integer value. For example, the step size of the cycle may be adjusted so that a graph (see FIGS. 3 and 5) showing the relationship between the value of the cycle and the value of the spectrum can be drawn smoothly. Such a spectrum analysis executing means 5 may be configured as a dedicated machine, for example, on which an electronic circuit for executing the above-described operation is mounted, or, for example, a software for causing a general-purpose computer (computer) to execute the above-described operation is mounted. May be used.
[0020]
The estimating means 6 of the present embodiment has a database 9 in which a spectrum pattern of time-series data relating to power consumption which appears when the target electric device is operating is stored in advance, and is obtained by the spectrum analysis executing means 5. Pattern matching is performed between the obtained spectrum pattern and the spectrum pattern stored in the database 9 in advance, and the operation state of the target electric device is estimated based on the result of the pattern matching.
[0021]
The estimating means 6 includes, for example, hardware resources such as a central processing unit (CPU), a main storage device, an external storage device, a communication interface with the spectrum analysis executing means 5 and the like, and an operating system for controlling these hardware resources. A system, a process of storing a spectrum pattern of time-series data relating to power consumption appearing when the target electric device is operating in an external storage device and constructing a database 9, and a spectrum obtained by the spectrum analysis executing means 5. Is configured as a computer having software resources such as a database management system for executing a pattern matching process between the pattern and the spectrum pattern stored in the database 9.
[0022]
The database 9 is constructed in advance as follows, for example. That is, only the target electrical equipment is operated, the time series data of the power consumption is measured by the measurement sensor 4 at a measurement time interval of 1 second and the measurement time width is 5 minutes to 10 minutes. A spectrum pattern of the data is obtained, and the spectrum pattern is associated with information for specifying the operated target electric device and stored in the database 9.
[0023]
For example, in this embodiment, when only the washing machine 3e is operated, a set of a spectrum pattern, a code indicating that the operated target electric device is the washing machine 3e, and only the rice cooker 3f is operated. , A set of a code indicating that the operated target electric device is the rice cooker 3f, a spectrum pattern when only the washing machine 3e and the rice cooker 3f are operated, and the target electric device operated Is stored in the database 9 with a code indicating that the is the washing machine 3e and the rice cooker 3f. However, it is not always necessary to operate the washing machine 3e and the rice cooker 3f in combination. For example, by using an arithmetic function of a computer as the estimating means 6, a plurality of types of target electric devices are individually operated, and spectrum patterns in a case where the respective target electric devices are individually operated are superimposed in various combinations. A spectrum pattern corresponding to the combination may be obtained. For example, a pattern obtained by superimposing a spectrum pattern when only the washing machine 3e is operated and a spectrum pattern when only the rice cooker 3f is operated is obtained by an arithmetic function of the computer as the estimating means 6. Then, a set of the obtained pattern and a code indicating that the target electric device is the washing machine 3e and the rice cooker 3f may be stored in the database 9. In this case, there is no need to create various operating state conditions by combining a plurality of types of target electrical devices, and it is possible to automatically generate spectrum patterns corresponding to various operating state conditions combining a plurality of types of target electrical devices. .
[0024]
FIG. 2 shows time-series data (128 seconds) of power consumption obtained by the measurement sensor 4 when only the washing machine 3e is operated. FIG. 3 shows a spectrum for each periodic component obtained by the spectrum analysis executing means 5 using the time series data shown in FIG. 2 as an input signal. FIG. 4 shows time-series data (128 seconds) of power consumption obtained by the measurement sensor 4 when only the rice cooker 3f is operated. FIG. 5 shows a spectrum for each periodic component obtained by the spectrum analysis executing means 5 using the time series data shown in FIG. 4 as an input signal. 2 and 4 that the power consumption fluctuates frequently. In addition, FFT (Fast Fourier Transform) was used for the spectrum analysis performed by the spectrum analysis execution means 5.
[0025]
For example, in the present embodiment, a data sequence is created by arranging the spectrum values (numerical data) obtained by the spectrum analysis executing means 5 in a periodic order, and the data sequence is stored in the database 9 as a spectrum pattern. However, a graph (image data) representing the relationship between the period value and the spectrum value may be stored in the database 9 as a spectrum pattern, or the characteristics of the graph may be extracted and the characteristics may be stored in the spectrum pattern. May be stored in the database 9. For example, as shown in FIG. 3, a graph showing the relationship between the cycle value and the spectrum value when only the washing machine 3e is operated has a cycle value of 2.5 seconds, 3.3 seconds, 7 seconds. It can be seen that there is a characteristic that the spectrum is prominent (that is, a peak is formed) at 0.5 seconds.
[0026]
In an electric device (for example, a refrigerator 3b or a television receiver 3a) whose power consumption does not fluctuate or fluctuates even if the power consumption fluctuates, a spectrum is obtained in a relatively short period (for example, about 10 seconds or less). Is not prominent (that is, a peak is formed). Therefore, by grasping the presence or absence of the feature, it is possible to estimate whether or not the target electric device, which is an electric device whose power consumption fluctuates frequently, is operating. Further, among the target electrical devices of different types, for example, between the washing machine 3e and the rice cooker 3f, there is a difference in the number, position, size, etc. of peaks in a graph representing the relationship between the cycle value and the spectrum value. Therefore, by grasping the difference, it is possible to estimate which target electric device is operating even when there are a plurality of types of target electric devices.
[0027]
The pattern matching processing by the estimating means 6 of the present embodiment is performed, for example, as follows. That is, when a spectrum value for each periodic component is input from the spectrum analysis executing means 5 to the estimating means 6, the estimating means 6 creates a data series by arranging the values of the spectrum in the order of the cycles, and converts the data series into an input. The database 9 is searched for a spectrum pattern (hereinafter, referred to as an input pattern) that matches the pattern. The match here is not necessarily limited to a perfect match, and may be regarded as a match when they are in a similar range. For example, the estimation unit 6 of the present embodiment obtains a correlation coefficient between an input pattern and a spectrum pattern stored in the database 9 (hereinafter, referred to as a storage pattern), and determines a value of the correlation coefficient in advance. If the input pattern is equal to or greater than the calculated value, it is determined that the input pattern matches the storage pattern.
[0028]
The pattern matching processing by the estimating means 6 is not limited to the above example, and may be performed, for example, as follows. For example, the value of the cycle and the value of the spectrum at the peak of the graph representing the relationship between the value of the cycle and the value of the spectrum for the target electrical device are stored in the database 9 in advance as a storage pattern. Then, when the spectrum value for each periodic component is input from the spectrum analysis executing means 5 to the estimating means 6, the estimating means 6 determines the value of the spectrum forming the peak among the input data and the period corresponding to the value of the spectrum. Is extracted as an input pattern. When a plurality of peaks appear, a spectrum value and a cycle value corresponding to the spectrum value are extracted for all peaks. Next, the estimating means 6 searches the database 9 for a pattern that matches the spectrum pattern (input pattern) thus extracted. The match here is not necessarily limited to a perfect match, and may be regarded as a match when the input pattern and the storage pattern are in a similar range (for example, when the difference between the input pattern and the storage pattern is within a predetermined allowable range). .
[0029]
According to the monitoring system 1 configured as described above, the operation state of the target electric device is estimated by a non-invasive method, for example, as follows. First, the measurement sensor 4 measures time-series data of power consumption by a non-invasive method that does not enter the house of the power consumer 2 with a measurement time interval of 1 second and a measurement time width of 5 minutes to 10 minutes. I do. Next, the spectrum analysis execution means 5 performs spectrum analysis on the measured time-series data, and outputs a spectrum for each periodic component to the estimation means 6. Next, the estimating means 6 arranges the input spectra for each periodic component in the order of the cycles to form an input pattern, and searches for a pattern that matches the input pattern among the stored patterns stored in the database 9 in advance.
[0030]
As a result of the search, when a matching storage pattern is found, it is estimated that the target electric device corresponding to the code stored in association with the storage pattern is in an operating state (that is, in a power-on state). Is done. On the other hand, when there is no storage pattern that matches the input pattern, it is estimated that the target electric device is in a power-off state. Note that the estimation result may be output to an output device such as a display or a printer, or may be stored in an external storage device provided in the estimation unit 6, or a communication line (for example, a telephone line, an optical It may be transmitted to a remote information processing device via a dedicated fiber line, PHS, or the like. The estimation result can be used not only by the power consumer 2 itself but also by a power company or an ESCO (Energy Service Company) via a communication line.
[0031]
At the beginning of the 21st century, a customer information network was established, and various information services were provided to the power customer 2. At the same time, information on the side of the power customer 2 was collected through the network. Is expected to be reflected in the management of the elderly. For example, one of the important information on the side of the power consumer 2 for the electric power company is information on the configuration and actual use of the electric equipment held by the power consumer 2, and these are the effects of DSM (Demand Side Management). It is indispensable for evaluation, prediction of potential demand, prediction of demand change, factor analysis of load factor reduction (deterioration), construction of detailed seasonal hourly fee system, provision of various services to power customers 2, etc. is there. The monitoring system 1 of the present invention is one of the leading systems that can meet the needs described above.
[0032]
In addition, the electrical equipment monitoring system 1 according to the present invention in which power consumption fluctuates frequently and a conventional electrical equipment monitoring system (see Japanese Patent Application Laid-Open No. 2000-292465) can be used in combination. That is, with respect to the electric equipment in which the fluctuation of the power consumption that makes it difficult to identify the operation state in the conventional electric equipment monitoring system, the operation state is estimated by the monitoring system 1 of the present invention, and whether the power consumption fluctuates. Alternatively, it is possible to estimate the operation state of the electric device having a long period of the fluctuation even if the power consumption fluctuates, using a conventional electric device monitoring system. As a result, a highly reliable electrical device monitoring system can be constructed.
[0033]
The above embodiment is an example of a preferred embodiment of the present invention, but the present invention is not limited to this, and various modifications can be made without departing from the gist of the present invention. For example, in the above-described embodiment, the measurement sensor 4 that measures power consumption is used, but data to be measured by the measurement sensor 4 is not necessarily limited to power consumption. The data to be measured by the measurement sensor 4 may be data that can reflect frequent fluctuations in power consumption due to the operation of the target electric device.
[0034]
For example, the measurement sensor 4 may be an ammeter for measuring a current. As the ammeter, a well-known instrument for measuring a current may be used. Similarly to the above-described embodiment, when measuring the current time-series data by the measurement sensor 4, the spectrum pattern obtained by performing the spectrum analysis on the measured current time-series data includes the operation of the target electric device. The feature that the state can be estimated appears. Further, the measurement sensor 4 may be an instrument for measuring the power factor or the reactive power.
[0035]
The “time-series data related to power consumption” measured near the power supply line entrance of the power consumer 2 referred to in this specification reflects frequent fluctuations in power consumption due to the operation of the target electric device. Includes overall data to be obtained (eg, power consumption, current, power factor, reactive power, etc.). The measuring sensor 4 may be any means that can measure such data.
[0036]
Further, for example, the estimating means 6 has a learning function, in which a spectrum pattern of the time-series data regarding power consumption and an operation state of the target electric device as an answer at that time are given as teacher data, and learning is performed in advance. In addition, a device that estimates the operation state of the target electric device by pattern recognition from the spectrum pattern obtained by the spectrum analysis executing means 5 may be adopted.
[0037]
Such an estimating means 6 can be realized as, for example, a neural network (also called a neurocomputer) having an inductive learning ability. A neural network is an information processing system that imitates nerve cells of the human brain, and has a structure in which many units corresponding to nerve cells (neurons) are connected in a network. Each unit produces an output responsive to the sum of the inputs from the other units combined. At this time, by adjusting the strength of connection (weighting), the neural network can be trained so that the best output is obtained for all inputs.
[0038]
Learning of the neural network as the estimating means 6 is performed, for example, as follows. That is, the switches provided to the plurality of electric devices including the target electric device existing in the electric power consumer 2 are turned on and off to create a situation where the plurality of electric devices are in various operation states. For each of the situations, that is, for each combination of various operation states of a plurality of electric devices, the measurement sensor 4 and the spectrum analysis execution means 5 are used to determine the spectrum pattern of the time-series data related to power consumption (for example, Spectrum). Then, the obtained various spectral patterns and the operating state of the target electric device corresponding to each pattern (for example, which target electric device was turned on or off, etc.) are identified by the teacher. Learning is performed by giving the data to a neural network. The learning for improving the estimation accuracy by the neural network may be performed from outside the power consumer 2 using a telephone line, an optical fiber dedicated line, or the like. After learning the neural network with the teacher data in this way, the operation state of the target electric device of the power consumer 2 is actually estimated.
[0039]
In this case, the monitoring system 1 estimates the operation state of the target electric device by a non-invasive method, for example, as follows. The measurement sensor 4 measures time-series data on power consumption by a non-invasive method that does not enter the house of the power consumer 2. Note that the measurement time interval and the measurement time width may be the same as those in the above-described embodiment, for example. Next, the spectrum analysis execution means 5 performs spectrum analysis on the measured time-series data, and outputs a spectrum pattern (for example, a spectrum for each periodic component) to the estimation means 6. When the spectrum pattern is input, the estimating means 6 performs pattern recognition based on the teacher data given at the time of learning and the estimation ability obtained by the learning, and obtains the answer of the target electric device which is the answer to the input spectrum pattern. It outputs the estimation result of the operating state (for example, which target electric device is in the ON or OFF state). Note that the estimation result may be output to an output device such as a display or a printer, or may be stored in an external storage device provided in the estimation unit 6, or a communication line (for example, a telephone line, an optical It may be transmitted to a remote information processing device via a dedicated fiber line, PHS, or the like. The estimation result can be used not only by the power consumer 2 itself but also by a power company or an ESCO (Energy Service Company) via a communication line.
[0040]
The algorithm of the pattern recognition of the estimating means 6 is not necessarily limited to the one using a neural network, but may employ another known or new algorithm.
[0041]
【The invention's effect】
As is apparent from the above description, according to the present invention as set forth in claims 1 and 2, the spectrum pattern of the time-series data relating to power consumption, which appears due to the operation of an electric device in which power consumption fluctuates frequently. Focusing on the features, there is an effect that it is possible to estimate the operating state of an electric device in which power consumption fluctuates frequently, which is difficult to estimate in the conventional monitoring system, by a non-invasive method.
[0042]
Furthermore, according to the third aspect of the present invention, by applying the database technology, it is possible to estimate the operating state of the electric device in which the power consumption frequently changes by a non-invasive method.
[0043]
Further, according to the present invention, by applying a pattern recognition method such as a neural network, it is possible to estimate an operating state of an electric device in which power consumption frequently fluctuates by a non-invasive method. it can.
[Brief description of the drawings]
FIG. 1 is a schematic configuration diagram showing an embodiment of a method and a monitoring system for estimating an operation state of an electric device in which power consumption frequently fluctuates according to the present invention.
FIG. 2 shows time-series data of power consumption when only the washing machine is operated, the vertical axis represents power consumption [W], and the horizontal axis represents elapsed time [seconds].
FIG. 3 shows a result of performing a spectrum analysis on the time-series data of power consumption in FIG. 2, in which the vertical axis represents the spectrum [W] and the horizontal axis represents the periodic component [second].
FIG. 4 shows time-series data of power consumption when only the rice cooker is operated, the vertical axis represents power consumption [W], and the horizontal axis represents time elapsed [seconds].
5 shows a result of performing a spectrum analysis on the time series data of the power consumption in FIG. 4, the vertical axis represents the spectrum [W], and the horizontal axis represents the periodic component [second].
[Explanation of symbols]
1 monitoring system
2 Electricity consumers
4 Measurement sensor
5 Spectrum analysis execution means
6 Estimation means
9 Database

Claims (4)

消費電力の変動が頻繁に起こる対象電気機器の動作状態を電力需要家の家屋内に入らずに推定する方法であり、前記電力需要家の給電線引込口付近において消費電力に関する時系列データを測定し、当該測定された時系列データに対してスペクトル解析を行い、当該スペクトル解析により得られるスペクトルのパターンに基づいて前記対象電気機器の動作状態を推定することを特徴とする消費電力の変動が頻繁に起こる電気機器の動作状態を推定する方法。This is a method of estimating the operating state of a target electrical device in which power consumption fluctuations frequently occur without entering a house of a power consumer, and measuring time-series data on power consumption in the vicinity of a power supply line entrance of the power consumer. The power consumption fluctuations are characterized by performing spectrum analysis on the measured time-series data and estimating the operation state of the target electric device based on a spectrum pattern obtained by the spectrum analysis. Method for estimating the operating state of electrical equipment that occurs in 消費電力の変動が頻繁に起こる対象電気機器の動作状態を電力需要家の家屋内に入らずに推定するモニタリングシステムであり、前記電力需要家の給電線引込口付近に設置されて消費電力に関する時系列データを測定する測定センサーと、前記測定センサーで測定された時系列データに対してスペクトル解析を行うスペクトル解析実行手段と、前記スペクトル解析実行手段により得られたスペクトルのパターンに基づいて前記対象電気機器の動作状態を推定する推定手段とを備えることを特徴とする消費電力の変動が頻繁に起こる電気機器のモニタリングシステム。A monitoring system for estimating the operation state of a target electrical device in which power consumption fluctuations frequently occur without entering a house of a power consumer, which is installed near a power supply line entrance of the power consumer and relates to power consumption. A measurement sensor for measuring series data, a spectrum analysis execution unit for performing spectrum analysis on the time series data measured by the measurement sensor, and the target electric power based on a spectrum pattern obtained by the spectrum analysis execution unit. A monitoring system for an electrical device in which power consumption fluctuates frequently, comprising an estimating means for estimating an operation state of the device. 前記推定手段は、前記対象電気機器が動作している場合に表れる消費電力に関する時系列データのスペクトルのパターンが予め記憶されているデータベースを有し、前記スペクトル解析実行手段により得られたスペクトルのパターンと前記データベースに予め記憶されているスペクトルのパターンとのパターンマッチングを行い、当該パターンマッチングの結果に基づいて前記対象電気機器の動作状態を推定することを特徴とする請求項２記載の消費電力の変動が頻繁に起こる電気機器のモニタリングシステム。The estimating means has a database in which a spectrum pattern of time-series data relating to power consumption which appears when the target electric device is operating is stored in advance, and the spectrum pattern obtained by the spectrum analysis executing means is provided. 3. The power consumption according to claim 2, wherein pattern matching is performed between the target electric device and a spectrum pattern stored in the database in advance, and an operation state of the target electric device is estimated based on a result of the pattern matching. A monitoring system for electrical equipment that fluctuates frequently. 前記推定手段は、学習機能を有し、消費電力に関する時系列データのスペクトルのパターンとその時の解答である前記対象電気機器の動作状態とが教師データとして与えられて予め学習が行われており、前記スペクトル解析実行手段により得られたスペクトルのパターンから前記対象電気機器の動作状態をパターン認識によって推定することを特徴とする請求項２記載の消費電力の変動が頻繁に起こる電気機器のモニタリングシステム。The estimating means has a learning function, and a learning is performed in advance by giving a spectrum pattern of time-series data regarding power consumption and an operation state of the target electric device as an answer at that time as teacher data, 3. The electrical equipment monitoring system according to claim 2, wherein the operation state of the target electrical equipment is estimated by pattern recognition from a spectrum pattern obtained by the spectrum analysis executing means.
JP2002214182A 2002-07-23 2002-07-23 Method for estimating the operating state of electrical equipment in which power consumption frequently changes and monitoring system for electrical equipment in which power consumption frequently changes Expired - Fee Related JP3892358B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2002214182A JP3892358B2 (en) 2002-07-23 2002-07-23 Method for estimating the operating state of electrical equipment in which power consumption frequently changes and monitoring system for electrical equipment in which power consumption frequently changes

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2002214182A JP3892358B2 (en) 2002-07-23 2002-07-23 Method for estimating the operating state of electrical equipment in which power consumption frequently changes and monitoring system for electrical equipment in which power consumption frequently changes

Publications (2)

Publication Number Publication Date
JP2004056969A true JP2004056969A (en) 2004-02-19
JP3892358B2 JP3892358B2 (en) 2007-03-14

Family

ID=31936572

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2002214182A Expired - Fee Related JP3892358B2 (en) 2002-07-23 2002-07-23 Method for estimating the operating state of electrical equipment in which power consumption frequently changes and monitoring system for electrical equipment in which power consumption frequently changes

Country Status (1)

Country Link
JP (1) JP3892358B2 (en)

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006017456A (en) * 2004-06-04 2006-01-19 Mitsubishi Electric Corp Electrical apparatus working state estimating system, and database construction method for estimating electrical apparatus working state
JP2009303415A (en) * 2008-06-16 2009-12-24 Nec System Technologies Ltd Equipment discriminator, program and method
WO2010116989A1 (en) * 2009-04-10 2010-10-14 オムロン株式会社 Equipment operation state measurement device, equipment operation state measurement method, and control program
KR20110009338A (en) * 2009-07-22 2011-01-28 엘지전자 주식회사 Power monitoring device
JP2011176985A (en) * 2010-02-25 2011-09-08 Nec System Technologies Ltd Power supply system, power supply method, and program
JP2011193602A (en) * 2010-03-12 2011-09-29 Omron Corp Energy attribute determination unit and energy attribute determination method
JP2012016270A (en) * 2010-07-02 2012-01-19 Jiaotong Univ Electric power monitoring device and method of identifying state of electric appliance
JP2012055100A (en) * 2010-09-02 2012-03-15 Yazaki Corp Device for identifying electric apparatus being used and method for determining electric apparatus being used
KR101135985B1 (en) 2012-01-20 2012-04-17 굿어스 주식회사 Power monitoring system
JP2012110218A (en) * 2010-11-17 2012-06-07 General Electric Co <Ge> Power consumption compliance monitoring system and method
JP2012516133A (en) * 2009-01-26 2012-07-12 ジュネーブ クリーンテック インコーポレイテッド Energy monitoring device, identification method and generation method
JP2012161165A (en) * 2011-01-31 2012-08-23 Mitsubishi Electric Corp Signal generation device, equipment operation detection device, equipment operation detection system, equipment operation detection method and program
JP2012161164A (en) * 2011-01-31 2012-08-23 Mitsubishi Electric Corp Device behaviour detecting system, signal generator and switch device
JP2012526281A (en) * 2009-05-04 2012-10-25 シンクエコ インコーポレイテッド Systems and methods for public use, monitoring and management of electricity
JP2013518556A (en) * 2010-01-25 2013-05-20 ジェネヴァ クリーンテック インコーポレイテッド Automatic detection of home appliances
JP2013150508A (en) * 2012-01-23 2013-08-01 Nippon Telegr & Teleph Corp <Ntt> Current waveform identification apparatus
JP2013538552A (en) * 2010-09-22 2013-10-10 コーニンクレッカ フィリップス エヌ ヴェ Disaggregation device for identifying devices in electrical networks
WO2013157294A1 (en) * 2012-04-18 2013-10-24 ソニー株式会社 Operating state estimating device for electrical apparatus, operating state estimating method for electrical apparatus, program, feature vector registration device for electrical apparatus, feature vector registration method for electrical apparatus, server apparatus, and operating state estimating system for electrical apparatus
JP2013238523A (en) * 2012-05-16 2013-11-28 Nippon Telegr & Teleph Corp <Ntt> Electric apparatus detecting and power consumption monitoring systems
JP2014075964A (en) * 2012-09-11 2014-04-24 Ricoh Co Ltd Type determination device, type determination method, and program
CN103853131A (en) * 2012-12-03 2014-06-11 财团法人资讯工业策进会 power monitoring device and power analysis method thereof
JP2016102775A (en) * 2014-11-12 2016-06-02 日本電信電話株式会社 Electrical apparatus operating state identification method and system
JP2016522669A (en) * 2013-06-14 2016-07-28 コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． Separation equipment used in multi-group electrical networks
WO2016157927A1 (en) * 2015-03-31 2016-10-06 日本電気株式会社 Data processing apparatus, data processing method, and program
JP2017034989A (en) * 2015-07-28 2017-02-09 エルエス産電株式会社Lsis Co., Ltd. Power metering system, and system and method for monitoring load power using the same
JP2017096984A (en) * 2017-02-10 2017-06-01 サターン ライセンシング エルエルシーＳａｔｕｒｎ Ｌｉｃｅｎｓｉｎｇ ＬＬＣ Information processing apparatus and information processing method
JP2017153359A (en) * 2014-07-11 2017-08-31 エンコアード テクノロジーズ インク Server and information adding method
JP2021022290A (en) * 2019-07-30 2021-02-18 双葉電機工業株式会社 Control state monitoring system and program
CN113533875A (en) * 2020-04-22 2021-10-22 杭州释普科技有限公司 Method for intelligently judging laboratory equipment running state and calculating equipment utilization rate

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006017456A (en) * 2004-06-04 2006-01-19 Mitsubishi Electric Corp Electrical apparatus working state estimating system, and database construction method for estimating electrical apparatus working state
JP2009303415A (en) * 2008-06-16 2009-12-24 Nec System Technologies Ltd Equipment discriminator, program and method
JP2012516133A (en) * 2009-01-26 2012-07-12 ジュネーブ クリーンテック インコーポレイテッド Energy monitoring device, identification method and generation method
WO2010116989A1 (en) * 2009-04-10 2010-10-14 オムロン株式会社 Equipment operation state measurement device, equipment operation state measurement method, and control program
JP2010262627A (en) * 2009-04-10 2010-11-18 Omron Corp Facility operation state measuring device, facility operation state measuring method, and control program
JP2012526281A (en) * 2009-05-04 2012-10-25 シンクエコ インコーポレイテッド Systems and methods for public use, monitoring and management of electricity
KR20110009338A (en) * 2009-07-22 2011-01-28 엘지전자 주식회사 Power monitoring device
KR101652109B1 (en) 2009-07-22 2016-08-29 엘지전자 주식회사 Power monitoring device
JP2013518556A (en) * 2010-01-25 2013-05-20 ジェネヴァ クリーンテック インコーポレイテッド Automatic detection of home appliances
JP2011176985A (en) * 2010-02-25 2011-09-08 Nec System Technologies Ltd Power supply system, power supply method, and program
JP2011193602A (en) * 2010-03-12 2011-09-29 Omron Corp Energy attribute determination unit and energy attribute determination method
JP2012016270A (en) * 2010-07-02 2012-01-19 Jiaotong Univ Electric power monitoring device and method of identifying state of electric appliance
JP2012055100A (en) * 2010-09-02 2012-03-15 Yazaki Corp Device for identifying electric apparatus being used and method for determining electric apparatus being used
US9523718B2 (en) 2010-09-22 2016-12-20 Philips Lighting Holding B.V. Disaggregation apparatus for identifying an appliance in an electrical network
JP2013538552A (en) * 2010-09-22 2013-10-10 コーニンクレッカ フィリップス エヌ ヴェ Disaggregation device for identifying devices in electrical networks
JP2012110218A (en) * 2010-11-17 2012-06-07 General Electric Co <Ge> Power consumption compliance monitoring system and method
JP2012161164A (en) * 2011-01-31 2012-08-23 Mitsubishi Electric Corp Device behaviour detecting system, signal generator and switch device
JP2012161165A (en) * 2011-01-31 2012-08-23 Mitsubishi Electric Corp Signal generation device, equipment operation detection device, equipment operation detection system, equipment operation detection method and program
KR101135985B1 (en) 2012-01-20 2012-04-17 굿어스 주식회사 Power monitoring system
JP2013150508A (en) * 2012-01-23 2013-08-01 Nippon Telegr & Teleph Corp <Ntt> Current waveform identification apparatus
JPWO2013157294A1 (en) * 2012-04-18 2015-12-21 ソニー株式会社 Electrical device operation state estimation device, electrical device operation state estimation method, program, electrical device feature vector registration device, electrical device feature vector registration method, server device, and electrical device operation state estimation system
WO2013157294A1 (en) * 2012-04-18 2013-10-24 ソニー株式会社 Operating state estimating device for electrical apparatus, operating state estimating method for electrical apparatus, program, feature vector registration device for electrical apparatus, feature vector registration method for electrical apparatus, server apparatus, and operating state estimating system for electrical apparatus
JP2013238523A (en) * 2012-05-16 2013-11-28 Nippon Telegr & Teleph Corp <Ntt> Electric apparatus detecting and power consumption monitoring systems
JP2014075964A (en) * 2012-09-11 2014-04-24 Ricoh Co Ltd Type determination device, type determination method, and program
CN103853131A (en) * 2012-12-03 2014-06-11 财团法人资讯工业策进会 power monitoring device and power analysis method thereof
JP2016522669A (en) * 2013-06-14 2016-07-28 コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． Separation equipment used in multi-group electrical networks
JP2017153359A (en) * 2014-07-11 2017-08-31 エンコアード テクノロジーズ インク Server and information adding method
JP2016102775A (en) * 2014-11-12 2016-06-02 日本電信電話株式会社 Electrical apparatus operating state identification method and system
WO2016157927A1 (en) * 2015-03-31 2016-10-06 日本電気株式会社 Data processing apparatus, data processing method, and program
JPWO2016157927A1 (en) * 2015-03-31 2018-01-25 日本電気株式会社 Data processing apparatus, data processing method, and program
US10712374B2 (en) 2015-03-31 2020-07-14 Nec Corporation Data processing device, data processing method, and non-transitory storage medium
JP2017034989A (en) * 2015-07-28 2017-02-09 エルエス産電株式会社Lsis Co., Ltd. Power metering system, and system and method for monitoring load power using the same
JP2017096984A (en) * 2017-02-10 2017-06-01 サターン ライセンシング エルエルシーＳａｔｕｒｎ Ｌｉｃｅｎｓｉｎｇ ＬＬＣ Information processing apparatus and information processing method
JP2021022290A (en) * 2019-07-30 2021-02-18 双葉電機工業株式会社 Control state monitoring system and program
CN113533875A (en) * 2020-04-22 2021-10-22 杭州释普科技有限公司 Method for intelligently judging laboratory equipment running state and calculating equipment utilization rate
CN113533875B (en) * 2020-04-22 2024-02-23 释普信息科技（上海）有限公司 Method for intelligently judging running state of laboratory equipment and calculating equipment utilization rate

Also Published As

Publication number Publication date
JP3892358B2 (en) 2007-03-14

Similar Documents

Publication Publication Date Title
JP3892358B2 (en) Method for estimating the operating state of electrical equipment in which power consumption frequently changes and monitoring system for electrical equipment in which power consumption frequently changes
Mengistu et al. A cloud-based on-line disaggregation algorithm for home appliance loads
Athanasiadis et al. Real-time non-intrusive load monitoring: A light-weight and scalable approach
US10114050B2 (en) Utility consumption identification
JP5751872B2 (en) Device state detection device and device state detection system
EP3217182B1 (en) Systems and methods to emulate high frequency electrical signatures
TWI491136B (en) Method and system for monitoring load of electric device
US8694291B2 (en) System and method of waveform analysis to identify and characterize power-consuming devices on electrical circuits
JP5604089B2 (en) Power consumption measurement system, control device, and power consumption measurement method
Yu et al. Nonintrusive appliance load monitoring for smart homes: Recent advances and future issues
US20120278014A1 (en) Method and apparatus for monitoring power consumption
JP5235479B2 (en) Electrical device estimation apparatus and electrical device estimation method
US20140163908A1 (en) Electrical device monitoring apparatus, method thereof and system
WO2014054330A1 (en) State estimation device, state estimation method and program
CN111242391A (en) Machine learning model training method and system for power load identification
US10942205B2 (en) Method and system for analyzing electricity consumption
CN109447473B (en) Power load monitoring method, device, equipment and readable storage medium
JP5727949B2 (en) Current waveform identification device
US20160109492A1 (en) Method and system for analysing electricity consumption
KR20130046693A (en) Power management apparatus and method for controlling the same
Nardello et al. A low-cost smart sensor for non intrusive load monitoring applications
Ghosh et al. Non-intrusive identification of harmonic polluting loads in a smart residential system
Welikala et al. A real-time non-intrusive load monitoring system
WO2015087571A1 (en) Bill information determination device, bill information output system and bill information determination method and program
CN105305437A (en) Tri-reliability matching and identification method of electric load

Legal Events

Date Code Title Description
RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20041022

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20050225

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20060621

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20060818

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20061129

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20061206

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20101215

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20101215

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20111215

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20131215

Year of fee payment: 7

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250

LAPS Cancellation because of no payment of annual fees