Towards an intelligent HVAC system automation using Reinforcement Learning

HVAC systems are among the biggest energy consumers in buildings and therefore in the focus of optimal control research. In practice, rule-based control and PID controllers are typically used and implemented at the beginning of the building operation. Since this approach neither guarantees optimal or even good control, optimal control algorithms (which can be predictive and adaptive) are in the focus of research. The problem with most of the approaches is that a model of the system is often needed which comes with high engineering efforts. Further, the required computing power can quickly exceed the capacities, even in modern buildings. Therefore, in this paper we investigate the application of a state-of-the-art Reinforcement Learning (RL) algorithm, as a self-calibrating valve controller for two water-air heat exchangers of a real-world air handling unit. We choose a generic problem formulation to pre-train the algorithm with a simulation of an admixing heater and use it to control an injection heater and a throttle cooler. Our results show that after only 70 hours, the control quality significantly increases. Therefore, it seems evident that with pre-trained RL algorithms, a self-improving HVAC automation can be realized with little hardware requirements and without extensive modelling of the system dynamics.

Cloud-based Hardware-in-the-Loop testing of building automation controllers

This paper aims to fill the gap in knowledge about building control testing, thus encouraging control evaluation, to ultimately improve energy efficiency in building operation. A hardware controller and its digital twin are tested in real-time in a separate platform in the cloud, and the results are analyzed to determine what insights can tests on virtual controllers give about the behaviors of their real-life hardware counter-parts. Key performance indicators (KPIs) from literature are used to evaluate the control. It is shown that although the controllers differ in their control output time-series, their overall performance profile along the entire simulation run follows a similar pattern (KPI percent error varies between 3% and 8%). This implies that virtual controller testing can be a good indicator of hardware controller behavior.

Photovoltaic Facade Performance Evaluation

A high-rise building façade with integrated photovoltaic panels, located in the Central European region with temperate climatic conditions was tested. The PV façade was monitored for three years. Results of the PV system monitoring show that the façade positively influence the energy efficiency and reduction of carbon dioxide emissions from the building operation.

Review of new systems and trends

Innovative and integrative lighting solutions are a rapidly developing trend among BMS manufacturers. They are being implemented in various systems from industry-leading firms, however they are met with a challenge of finding the best possible compromise between occupant expectations and optimization of building operation.