Ensemble-based data modeling for the prediction of energy consumption in HVAC plants

In these days of the millennium, emerging technologies help to develop and design an intelligent building integration system. Building integration system consists of all building services working jointly and a single controlling and monitoring system is used to manage all the services within a building. Building integrating system includes the automatic supply of lights, heating and cooling load of HVAC system as someone enters in a room and shutting down of all electricity and services after leaving a room. The concept of energy saving is being widely used in smart cities of the urban areas, particularly in commercial buildings. The consumption of energy in enormous amounts is one of the prime areas of concern for researchers globally. The focus is on buildings as they are the biggest consumers of energy. The analysis of energy consumption pattern of buildings diverts our attention towards the heating, ventilation and air conditioning system which according to studies accounts for maximum energy consumption within buildings. This paper presents Ensemble-based intelligence algorithms to analyze the HVAC data obtained from various sensors for a commercial building. The data consist of 1 year (12 months) cooling tower data. In this research, 2-month data have been considered for the analysis purpose and two Ensemble intelligence algorithms of regression variant were employed. The results show that the proposed research approach is an improved method in the existing domain. This research would help to determine abnormal energy consumption due to HVAC plants within a building and can help to identify the cause of wastage of energy and can save energy. © 2021, The Author(s), under exclusive licence to Springer Nature Switzerland AG part of Springer Nature.