2016 ASHRAE Winter Conference

Smart windows are used to reduce energy consumption and improve thermal and visual comfort by controlling the solar flux entering into a building and/or adapting their thermal resistances. A commercial building with integrated electrochromic windows is modeled. The hour-by-hour state of the smart windows required to minimize overall energy consumption (heating, cooling, lighting) while respecting constraints related to visual comfort is determined through an optimization strategy based on genetic algorithms. Then, this optimal control is compared to two other approaches that could be applied in real-time applications: (i) rule-based control, and (ii) predictive control. The impacts of thermal mass, façade orientation and climate are analyzed.

Accurate energy performance prediction of HVAC system plays a significant role for intelligent building operations to improve energy efficiency and reduce energy consumption in buildings. In modern commercial and residential buildings, large amounts of raw data, including electric metering data, are monitored, trended and saved in, for example, Building Automation System (BAS). Due to the complexity of building mechanical and electrical system and the cost, practically speaking, it is impossible to have sensors/meters to monitor the building at a fine granularity. Building total energy consumption (e.g., total electricity consumption) is one of the most commonly available metering data.

Many facility departments have installed energy meters seeking to pin point how, where and when energy is being inefficiently utilized. This has led to the recording of vast amount of data over extended periods of time, which makes it very difficult to manage and manually analyze. Luckily, techniques in machine learning have shown promising results in automated knowledge discovery making it more and more crucial when large data is at hand. This paper applies machine learning (ML) algorithms to detect abnormalities in chilled water systems (CWS) at building level. Two abnormal situations are pursued: chilled water sensor misreadings and low thermal efficiency in terms of delta T. The visualization of building chilled water historical data provides general trends and an initial identification of the building abnormalities; this visualization also helps to lay down the requirements for the abnormality detection algorithms, and eventually, their selection.

The accuracy of experimental results has always concerned engineers and scientists. The uncertainty of each parameter is desired to be minimized because these uncertainties will propagate in the data reduction process. In heat-transfer equipment testing, there are usually two independent measurements of heat-transfer rate in the hot and cold stream respectively (Q_h and Q_c). It is proposed in this paper that Q_ave should be calculated based on a form of weighted-linear average, with weighting factors depending on the individual uncertainties in Q_h and Q_c. Heat-transfer rate which has higher uncertainty will be weighed less in the average, and the other one with lower uncertainty will be weighed more accordingly. Implementing this new methodology will minimize the uncertainty in heat-transfer coefficient and Colburn j factors, which will consequently provide more accurate data for use in the development of correlations or for performance comparison purposes.