基於使用者回饋之非侵入式負載監控系統設計與實作

Abstract

非侵入式負載監控系統是一套可幫助使用者了解住家詳細耗電情形的一 套系統，其分析家中某一迴路的電壓與總電流變化，並從這些變化中判別 個別電器狀態，因此可透過單一電錶紀錄每個電器的使用耗電情形供使用 者參考。非侵入式負載監控系統其功能與低成本特性是一套未來智慧家庭 或智慧建築之不可或缺的技術。近年來電腦、通訊與儲存技術的蓬勃發展， 使得收集大量共通使用的非侵入式負載監控的資料庫變得有可行性。因此 在本研究中，提出基於使用者回饋資訊的非侵入式負載監控的電器搜尋方 法，透過使用者確定電器搜尋結果或回饋電器資訊，回傳各種電器的耗電 特徵到特定的資料蒐集中心，以進行耗電情形計算並將結果反饋給使用 者。最後，我們更建立了非侵入式負載監控的評估平台，其能評估與比較 各種非侵入式負載監控系統的精準度,依評估結果顯示本研究提出的非侵入 式負載監控的電器搜尋方法可達到85%到96%的精準度。

Nonintrusive appliance load monitoring (NIALM) system analyzes the changes of voltage and current on an electrical circuit and can disaggregate the usage and power consumption of appliances on the same circuit according to different power consumption signatures of appliances. NIALM system is regarded as a low-cost and one of the most important features for energy monitoring and management in a smart home and smart building. Advances in computing, communication and storage technologies further make an NIALM system possible to accommodate a huge amount of power consumption signatures of appliances, and to detect appliances and/or appliance states through on database search technologies. In this study, we propose a low-cost NIALM system for end-users so that users can contribute the power consumption signatures of their appliances to a datacenter through confirmations or feedbacks of the NIALM search results. Then, a new NIALM search algorithm based on user feedbacks is presented in this paper. To evaluate and compare the performance and accuracy of NIALM search results by employing the proposed algorithm and different approaches, a real evaluation test-bed is established. The experimental results demonstrate that the proposed scheme can achieve 85% to 96% accuracy of appliance search.