2019/07/30 by Caio Ponte, Carlos Caminha, Ponte, Caio +7
Computer Science · Engineering · #FOS: Computer and information sciences #Green IT and Sustainability #IoT and Edge/Fog Computing #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Smart Grid Energy Management
paper · pdf · doi:10.48550/arxiv.1907.13246
openalex publication_date 2019/07/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present here the Temporal Clustering Algorithm (TCA), an incremental\nlearning algorithm applicable to problems of anticipatory computing in the\ncontext of the Internet of Things. This algorithm was tested in a specific\nprediction scenario of consumption of an electric water dispenser typically\nused in tropical countries, in which the ambient temperature is around\n30-degree Celsius. In this context, the user typically wants to drinking iced\nwater therefore uses the cooler function of the dispenser. Real and synthetic\nwater consumption data was used to test a forecasting capacity on how much\nenergy can be saved by predicting the pattern of use of the equipment. In\naddition to using a small constant amount of memory, which allows the algorithm\nto be implemented at the lowest cost, while using microcontrollers with a small\namount of memory (less than 1Kbyte) available on the market. The algorithm can\nalso be configured according to user preference, prioritizing comfort, keeping\nthe water at the desired temperature longer, or prioritizing energy savings.\nThe main result is that the TCA achieved energy savings of up to 40% compared\nto the conventional mode of operation of the dispenser with an average success\nrate higher than 90% in its times of use.\n