A comparison of machine learning algorithms for forecasting indoor temperature in smart buildings

Abstract

The international community has largely recognized that the Earth's climate is changing. Mitigating its global effects requires international actions. The European Union (EU) is leading several initiatives focused on reducing the problems. Specifically, the Climate Action tries to both decrease EU greenhouse gas emissions and improve energy efficiency by reducing the amount of primary energy consumed, and it has pointed to the development of efficient building energy management systems as key. In traditional buildings, households are responsible for continuously monitoring and controlling the installed Heating, Ventilation, and Air Conditioning (HVAC) system. Unnecessary energy consumption might occur due to, for example, forgetting devices turned on, which overwhelms users due to the need to tune the devices manually. Nowadays, smart buildings are automating this process by automatically tuning HVAC systems according to user preferences in order to improve user satisfaction and optimize energy consumption. Towards achieving this goal, in this paper, we compare 36 Machine Learning algorithms that could be used to forecast indoor temperature in a smart building. More specifically, we run experiments using real data to compare their accuracy in terms of R-coefficient and Root Mean Squared Error and their performance in terms of Friedman rank. The results reveal that the ExtraTrees regressor has obtained the highest average accuracy (0.97%) and performance (0,058%) over all horizons.

Prophet model for forecasting occupancy presence in indoor spaces using non-intrusive sensors

“…Therefore, it should not come as a surprise that previous models used for occupancy detection have also been explored for occupancy forecasting in indoor spaces. Alawadi et al (2020) provide a comprehensive comparison of 36 offline machine learning models applied for forecasting the indoor temperature by combining temperature sensor data from an indoor space and the meteorological conditions from a nearby weather station. Using the Friedman rank and the Rcoefficient to evaluate the accuracy of three forecast horizons, they conclude that the neural network models (e.g.…”

“…These interactions can also be associated with activities, including meeting someone, giving a lecture, or working on a desk. Due to the stochastic nature of occupant behavior, previous occupancy forecasting models considerably diverge in terms of the types of sensors being used to gather occupancy data; the complexity level of single versus multi-occupant forecasting; and the arbitrary selection of short versus long-term forecast horizons (Hutchins et al, 2007;Chen et al, 2018;Alawadi et al, 2020).…”

Dynamic User Preference Parameters Selection and Energy Consumption Optimization for Smart Homes Using Deep Extreme Learning Machine and Bat Algorithm

“…The indoor weather conditions have significant importance in smart homes; hence, selecting suitable algorithms for indoor forecasting is important. A comparison of 36 machine learning algorithms has been presented that can be used in smart buildings to predict indoor Temperature [36]. For the management of IoT systems and energy efficiency, authors in [37] presented a smart building template.…”

AC Cooling Time Prediction Using Common Representation Model

“…A survey of algorithm based intelligent HVAC (Heating, Ventilation and Air Conditioning) control systems for predicting outdoor and indoor temperature, user presence, thermal preference and energy reduction are discussed in [1]. A comparison of machine learning algorithms to forecast indoor temperature in buildings with HVAC systems is discussed in [2]. There are research papers that deal with the problem of predicting energy consumption using various algorithms [3,4,5].…”