AC Cooling Time Prediction Using Common Representation Model

Abstract

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.

Device Interaction Graph: Directed Decision Graph for Settings Auto-Completion

“…Next, we have considered ML and Deep DL approaches to recommend the 8-settings for each WM. For predicting the preferred wash settings using ML and DL model based [27,28,36] and LSTM [37]. All these models have been generated using the same input data available in WM DST.…”

“…We have compared the proposed solution with data mining approaches, Machine Learning (ML) and Deep Learning (DL) approaches in the section on Experiments. The use of big data processing in combination with ML/DL models, to predict outcomes involving large number of connected IoT devices is discussed in [27,28]. There are well known data mining techniques to extract knowledge from large volumes of data (big data), generated by IoT devices [29].…”

“…The Random Forest Algorithm uses a collection of decision trees to predict the outcome. For the case of DL algorithms, we have considered Fully Connected Neural Network (FCNN) [27,28,36] and Long Short Term Memory (LSTM) sequence model [37].…”

“…The data generated from 158,213 IoT enabled WMs are processed and analyzed on the cloud. The processing of the WM data using cloud infrastructure is similar to the methods we have applied for IoT enabled Air Conditioners in [27,28]. The event logs from the WM were sent to the cloud using IoT infrastructure.…”

Prediction of Vehicle Driver’s Facial Air Temperature With SVR, ANN, and GRU

“…Machine Learning (ML) algorithms are appropriate data-driven method of obtaining head temperature [3], [13]- [20]. Many former researchers have applied these methods to predict the temperature in other fields [21]- [23]. Xiao, C. J et al used the machine learning methods to predict the Sea surface temperature with a high accuracy [24].…”