利用熱感應之技術測量電器各別用電量及個人用電狀況

Abstract

由於人類的行為與電器的用電量兩者之間有極強的關聯存在，去探測每個人的用電量可以了解一個人用了多少電，並從中可以給予個人化的回饋與建議幫助使用者節省能源。這篇碩士論文首先提出HeatProbe 系統，它的目標是利用熱感應的技術將總電表的用電資訊細分成每個電器的用電量。ThermalProbe系統為HeatProbe的延伸，藉由熱感應的方式去識別使用者，ThermalProbe希望在多人共同使用的空間，能達到區分出每人在用電資訊。在識別使用者的部分，使用者需配戴一個會發出熱能訊號的裝置，而每個裝置因發出訊號不同而可以被識別。而ThermalProbe也實作了以距離的方式去計算每個使用者總共用了多少電，舉個最單純的情況，將電量歸給最靠近這個電器的使用者。兩個系統都經設計、實作，並且用實驗去評估這個系統。HeatProbe分類每個電器的用電量，其精準度達到了80.2%，而使用的時間誤差平均為125秒。而ThermalProbe在探測每個人的用電量，則達到平均誤差為12.66%。

Given the strong link between energy consumption and human behavior, metering per-user energy consumption is critical for understanding individual energy behavior and for customizing personalized feedback to promote everyday energy-saving behavior. This thesis first proposes an energy metering system called the HeatProbe system that uses thermal-imaging to sense and disaggregate per-appliance energy consumption. By building on top of the thermal-based HeatProbe system, this thesis further develops the ThermalProbe system that meters per-user energy consumption by using thermal-identification to track and disaggregate energy usage among individual occupants in a shared working/living space. In thermal identification, each occupant wears a thermal tag that emits a unique temperature signature for user identification. The system intro-duces location-based per-user energy disaggregation that accounts per-appliance energy usage to individual energy consumer(s), i.e., occupant(s) nearby activated appliances. We have designed, prototyped, and tested both HeatProbe and ThermalProbe systems. Results show that the HeatProbe system achieves 80.2% appliance-level power account-ing accuracy with 125-second average error and the ThermalProbe system meters per-user energy consumption with an average error of 12.66%.