Energy conservation is of increasing importance in contemporary society. A large fraction of energy end-use can be attributed to space conditioning. Therefore, intelligent control systems were devised and commercialised in the form of smart thermostats. Hereto, the availability of occupancy information is essential such that heating and/or cooling schedules can be tailored to user needs. This way energy savings can be obtained without jeopardising user satisfaction. However, preceding studies generally rely on simulations to estimate the potential reduction in energy consumption. This work aims at quantifying the potential based on a real life experiment. The development of a smart heating system is presented along with the results of an actual field test of retrofitting this system in 14 single-user student rooms of a university residence hall. An experiment was conducted in which the heating was automatically steered for 1 week (26 March 2018–01 April 2018). Total energy savings range between 26.9% and 59.5% and calculated thermal comfort was not significantly affected by the autonomous control. Furthermore, an environmental impact reduction of 3.2 to 12.9 EcoPoints is estimated for the controlled week, resulting in a reduction of 37.5 to 150.2 kgCO2eq.

An intelligent control system has been developed in the form of a smart thermostat that takes into account the expected occupancy. The use of the smart thermostat allows to save energy without jeopardizing the user's comfort requirements. The goal of this paper is to estimate the required minimal energy saving to achieve environmental and economic benefits by using the intelligent control system for residential heating in Flanders. To this end both Life Cycle Analysis (LCA) and Life Cycle Costing (LCC) methods are applied to provide insight in, and quantify the potential cost savings and environmental avoided burdens.

Modelling the occupancy of buildings, rooms or the usage of machines has many applications in varying fields, exemplified by the fairly recent emergence of smart, self-learning thermostats. Typically, the aim of such systems is to provide insight into user behaviour and incentivise energy savings or to automatically reduce consumption while maintaining user comfort. This paper presents a nonparametric user activity modelling algorithm, i.e. a Dirichlet process mixture model implemented by Gibbs sampling and the stick-breaking process, to infer the underlying patterns in user behaviour from the data. The technique deals with multiple activities, such as , of multiple users. Furthermore, it can also be used for modelling and predicting appliance usage (e.g. ). The algorithm is evaluated, both on cluster validity and predictive performance, using three case studies of varying complexity. The obtained results indicate that the method is able to properly assign the activity data into well-defined clusters. Moreover, the high prediction accuracy demonstrates that these clusters can be exploited to anticipate future behaviour, facilitating the development of intelligent building management systems.

The wide adoption of Internet of Things (IoT) infrastructure in recent years has allowed capturing data from systems that make intensive use of electrical power or consumables typically aiming to create predictive models to anticipate a system’s demand and to optimize system control, assuring the service while minimizing the overall consumption. Several methods have been presented to perform usage anticipation; one promising approach involves a two step procedure: profiling, which discovers typical usage profiles; and, prediction that detects the most likely profile given the current information. However, depending on the problem at hand, the number of observations to characterize a profile can increase greatly, causing high dimensionality, thus complicating the profiling step as the amount of noise and correlated features increase. In addition, the profile detection uncertainty increases, as the cluster intra-variability becomes larger and the distances between the centroids become similar. To overcome the difficulties that a usage profile with high dimensionality poses, we developed a methodology that finds the intrinsic dimensionality of a dataset, containing binary historical usage data, by performing dimensionality reductions to improve the profiling step. Then, the profile detection step makes use of the transformed actual data to accurately detect the current profile. This paper describes the implementation details of the application of such techniques by the analysis of two use cases: (1) usage prediction of a laser cutter machine; and, (2) occupancy prediction in an office environment. We observed that the dataset dimensionality and the cluster intra-variability was greatly reduced, making the profile detection less prone to errors. In conclusion, the implementation of methodologies to enhance the separability of the original data by dimensionality transformations improves the profile discovery and the subsequent actual profile detection.

Much work on sustainable design has focused on product manufacture/assembly and end of life. Gains in products’ technical efficiency address the use phase, but how these products are used clearly affects resource consumption. This paper describes two main approaches to reduce resource consumption during product life. Firstly, interventions aim to change user behavior, through information and feedback, as well as physical product affordances abstracted from lead users to guide or steer users toward the desired behavior. Secondly, automatic adjustment of product systems performance levels based on personal user profiles and anticipated usage is implemented using artificial intelligence techniques.

Tailoring products to user requirements can improve the energy efficiency without sacrificing user satisfaction. This study considers the case of an occupancy-driven smart thermostat in an office environment. Identifying patterns in past user behaviour enables occupancy prediction to control the heating accordingly. Potential energy savings and related environmental impact reductions, compared to a fixed schedule heating system, are calculated for various heating and building types in three regions (Leuven, Calgary and Tokyo) to account for variations in climate. The obtained energy savings range between 93.2 and 546.5 kWh per year and environmental impact reductions between 2 and 38 EcoPoints.

Well-optimized intelligent control of products and systems with a substantial energy and/or consumables demand can allow to reduce the use phase impact of these devices and systems significantly. However, depending on the usage patterns and their variability, the system efficiency and tardiness, as well as comfort-impact avoidance trade-off considerations, the effectiveness of such strategies can greatly differ. This contribution describes models for and analyses the sensitivity of the achievable impact reduction with respect to these factors, thus facilitating use phase oriented eco-design decision making. The observations are illustrated by means of a zone heating and a laser cutting machine case study.

In a worldwide context, space heating is the largest energy consumer in commercial buildings; it accounts for 35% of the total energy consumed in the US. Energy efficient thermostats, that learn occupancy patterns and user preferences, haven been studied in literature. However, they are oriented to single-user environments; therefore, they are not applicable in offices where several users interact, i.e. multi-user environments. To expand the single-user techniques in order to cope with multi-user environments, two methods are proposed to derive the user's expected temperatures demands based on their occupancy profiles and individual preferences in terms of desired temperature and tolerance. This paper presents the implications of the implementation of such techniques by means of a case study of two users in an academic office. We observed that the proposed methods reduced the operational time up to 33% compared to a reference fixed schedule of 12 hours while maintaining user comfort. In conclusion, smart thermostats can also reduce energy consumption in multi-user environments while guaranteeing individual user expectations.

Matching system functionality and user needs by learning from user behaviour enables a significant reduction in energy consumption. Habits and routine behaviour are exploited and captured in user profiles to automatically create customized heating schedules. However, over time the user conduct can change either gradually or abruptly and old occupancy patterns could become obsolete. Hence, a self-learning system should be able to cope with these changes and adapt the identified user profiles accordingly. An approach to track changing behaviour and update the corresponding user profiles, and hence heating schedules, is presented. The proposed strategy is evaluated by comparing prediction accuracy and potential energy savings to the case where learning is static and to incremental learning strategies. The results are illustrated by means of a real-life dataset of a single-user office.