Artificial Intelligence Based Air Conditioner Energy Saving Using a Novel Preference Map

Abstract

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.

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.…”

A methodology of photovoltaic power integration in air conditioning system – An inverter‐less approach

“…The primary motive of the existing work is concentrated towards using the air conditioner to solve the demand response problem [8,9]. An artificial intelligence based energy saving control of IoT enabled air conditioners is proposed in [10], where the power consumption is reduced by varying the temperature setting. Such approach is not economical and affects the cooling comfort of the user.…”