Deploying a Deep Learning-based Application for an Efficient Thermal Energy Storage Air-Conditioning (TES-AC) System: Design Guidelines

Abstract

Facility management and maintenance of the Thermal-Energy-Storage AirConditioning (TES-AC) system is a tedious task at a large scale mainly due to the charging load that can increase energy consumption if needed to be charged at peak hours. Besides, maintenance of TES-AC at a large scale gets complex as it contains many sensor data. By utilizing deep learning techniques on the sensor data, charging load prediction can be made possible, so facility managers can prepare in advance. However, a deep learning-based application will be unusable if it is not deployed in a userfriendly manner where facility managers can benefit from this application. Hence, this research focuses on gathering design guidelines for a deep learning-based application and further validates the design considerations with a developed application for efficient human-computer interaction through qualitative analysis. The approach taken to gather design guidelines demonstrated a positive correlation between expert-suggested features and the user-friendly aspect of the application as 67.08% of participants found the features suggested by experts to be most satisfactory. Furthermore, it evaluates user satisfaction with the advanced developed application for TES-AC according to the gathered design guidelines.