{"product_id":"ieej-btb2025056","title":"電力使用データに基づく太陽光発電および蓄電池所有の同定手法","description":"\u003cp\u003e\u003cstrong\u003eカテゴリ：\u003c\/strong\u003e部門大会\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e論文No：\u003c\/strong\u003e056\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eグループ名：\u003c\/strong\u003e【B】令和7年電気学会電力・エネルギー部門大会\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e発行日：\u003c\/strong\u003e2025\/9\/5\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eタイトル(英語)：\u003c\/strong\u003eIdentification of Households with PV and Battery Systems Using Electricity Usage Profiles\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名：\u003c\/strong\u003e三浦輝久（電力中央研究所），松田勝弘（東北電力）\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名(英語)： \u003c\/strong\u003eTeruhisa Miura (Central Research Institute of Electric Power Industry), Katsuhiro Matsuda (Tohoku Electric Power Company, Incorporated)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eキーワード：\u003c\/strong\u003e分散型エネルギーリソース,スマートメータ,太陽光発電,蓄電池,Distributed Energy Resource,Smart Meter,photovoltaic,battery storage\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(日本語)：\u003c\/strong\u003eThis study proposes a simple yet effective method for classifying residential households into three categories—no distributed energy resource (DER), photovoltaic (PV) only, and PV with battery storage—using only 30-minute interval electricity consumption data. A logistic regression model is employed to achieve high-accuracy classification, even under limited training data. Furthermore, for censored data where exported power is recorded as zero, the proposed method is applied to estimate PV and battery ownership with reasonable accuracy. The method offers several advantages: it relies solely on widely available electric consumption data, requires minimal labeled data for training, and produces interpretable results with clear contributions from each feature. These characteristics make it highly practical for identifying DER configurations across large-scale residential populations. This approach is expected to support demand response the design of demand response (DR) program by estimating controllability and DER penetration among households. It is also useful for planning control strategies, especially when targeting energy storage devices. Future work includes extending the method to detect other DER types such as electric vehicles (EVs), adopting time-series modeling to track changes in DER ownership, and incorporating semi-supervised learning under limited labeled data scenarios.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003ePDFファイルサイズ：\u003c\/strong\u003e874Kバイト\u003c\/p\u003e","brand":"IEEJ-PDF","offers":[{"title":"PDFダウンロード（一般価格440円\/会員価格220円） \/ A4 \/ 6","offer_id":47681977385199,"sku":"IEEJ-BTB2025056-PDF","price":440.0,"currency_code":"JPY","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0718\/9512\/2159\/files\/IEEJ-PDF_bumontaikai_48f96ced-15aa-4155-9eac-a90e0d22c813.png?v=1770872660","url":"https:\/\/ieej.bookpark.ne.jp\/products\/ieej-btb2025056","provider":"電気学会 電子図書館","version":"1.0","type":"link"}