Air Conditioning (AC) systems have contributed to a high percentage of the residential building energy consumption. Most of the recently released AC models are Internet of Things enabled. The data generated from all these ACs can be analyzed to understand the usage pattern and energy saving. In this paper, we have proposed a Cloud based Artificial Intelligence (AI) solution that uses the data from 37,748 ACs to analyze and generate a novel 2-D Preference Map. We have used the Preference Map in our AI solution to automatically generate Top-K energy saving recommendations. These recommendations will be provided to the user when the AC operational settings are selected. Our solution reduces the AC energy consumption by a median 57.38% (for the Top-1 recommendation) compared to the AC settings that were selected by the user. The use of the AC Preference Maps ensures that a wide range of energy saving recommendations are available. This solution provides recommendations that range from maximum energy saving to recommendations that are closer, in value, to the settings selected by the user.
The data generated by Air Conditioner (AC) consists mainly of sensor and control data. This paper will use the data generated from 53,528 ACs to predict the AC cooling time. The cooling time is the time taken by the AC to cool to a desired temperature. We have observed certain important issues in the data gathered from ACs deployed in dynamic real world environments. Poor prediction accuracies are observed for about 76% of the total ACs due to the lack of data regarding the device behavior, AC settings selection behavior and environmental conditions. During the AC operation, it is observed that the user selects only a small subset of the various combinations of the overall possible settings. Due to unavailability of data, Machine Learning (ML) models cannot be generated for new ACs. This leads to a cold start problem. This paper proposes a common AC prediction model that is generated through data shared from multiple connected ACs. Additionally an Auxiliary Task Learning (ATL) based deep learning model will be used for improving prediction accuracy. The proposed solution provides prediction capabilities for all ACs, compared to 24% of ACs supported by individual prediction models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.