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 $kgC{O}_{2}eq$.

节能在当代社会越来越重要。能源最终用途的很大一部分可归因于空间调节。因此，智能控制系统以智能恒温器的形式被设计和商业化。因此，占用信息的可用性是必不可少的，这样加热和/或冷却计划可以根据用户需求进行定制。通过这种方式，可以在不影响用户满意度的情况下实现节能。然而，先前的研究通常依赖于模拟来估计能源消耗的潜在减少。这项工作旨在量化基于现实生活实验的潜力。展示了智能供暖系统的开发以及在大学宿舍的 14 间单用户学生房间改造该系统的实际现场测试结果。进行了一项实验，其中加热自动转向 1 周（2018 年 3 月 26 日至 2018 年 4 月 1 日）。总节能范围在 26.9% 到 59.5% 之间，并且计算出的热舒适度不受自主控制的显着影响。此外，估计控制周内环境影响减少了 3.2 到 12.9 个生态点，从而减少了 37.5 到 150.2$克GC{哦}_2\mathrm{电子}q$.