The heating, ventilation, and air conditioning (HVAC) system is a major energy consumer in office buildings, and its operation is critical for indoor thermal comfort. While previous studies have indicated that reinforcement learning control can improve HVAC energy efficiency, they did not provide enough information about end-to-end control (i.e., from raw observations to ready-to-implement control signals) for centralized HVAC systems in multizone buildings due to the limitations of reinforcement learning methods or the test buildings being single zones with independent HVAC systems. This study developed a model-free end-to-end dynamic HVAC control method based on a recently proposed deep reinforcement learning framework to control the centralized HVAC system of a multizone office building. By using the deep neural network, the proposed control method could directly take measurable parameters, including weather and indoor environment conditions, as inputs and control indoor temperature setpoints at a supervisory level. In some test cases, the proposed control method could successfully learn a dynamic control policy to reduce HVAC energy consumption by 12.8% compared with the baseline case using conventional control methods, without compromising thermal comfort. However, an over-fitting problem was noted, indicating that future work should first focus on the generalization of deep reinforcement learning.

The COVID-19 pandemic has impacted electricity consumption patterns and such an impact cannot be analyzed by simple data analytics. In China, specifically, city lock-down policies lasted for only a few weeks and the spread of COVID-19 was quickly under control. This has made it challenging to analyze the hidden impact of COVID-19 on electricity consumption. This paper targets the electricity consumption of a group of regions in China and proposes a new clustering-based method to quantitatively investigate the impact of COVID-19 on the industrial-driven electricity consumption pattern. This method performs K-means clustering on time-series electricity consumption data of multiple regions and uses quantitative metrics, including clustering evaluation metrics and dynamic time warping, to quantify the impact and pattern changes. The proposed method is applied to the two-year daily electricity consumption data of 87 regions of Zhejiang province, China, and quantitively confirms COVID-19 has changed the electricity consumption pattern of Zhejiang in both the short-term and long-term. The time evolution of the pattern change is also revealed by the method, so the impact start and end time can be inferred. Results also show the short-term impact of COVID-19 is similar across different regions, while the long-term impact is not. In some regions, the pandemic only caused a time-shift in electricity consumption; but in others, the electricity consumption pattern has been permanently changed. The data-driven analysis of this paper can be the first step to fully interpret the COVID-19 impact by considering economic and social parameters in future studies.

The transition of the energy model dominated by centralized fossil energy use and the emergence of the Energy Internet and the Integrated Community Energy System (ICES) has gained attention. ICES involved the connection of electricity, heat, gas, and other kinds of energy, and was a significant form of the targeted transformation of conventional single energy networks. Within this system, the traditional demand response (DR) was transformed into an integrated demand response (IDR) in which all energy consumers could participate. The purpose of this study is to discuss the important technologies and models along with assessment and optimization strategies for the implementation of ICES and IDR, based on an extensive literature review. The analysis results show the “IDR + ICES” ecosystem proved to hold great potential for achieving renewable energy penetration, energy efficiency, and climate change control goals, while there are still many limitations in the coordination and reliability of the model and the design of the market mechanism. To conclude, the challenges and opportunities that ICES and IDR face were summarized, and future avenues for research are outlined.

Building-energy consumption is the primary aim of urban energy consumption, which can aid in optimization of building operation and management techniques, creating sustainable building and built environments. However, modellers’ understanding of the relationship between building-energy modelling (BEM) accuracy and computational load is still qualitative and deprived of accurate quantitative study. Based on a bottom-up engineering methodology, this study aims to quantitatively explore the effects of building-model input data with different resolution accuracies on energy simulation results, including evaluation of computational load. According to the actual parameters of the case-study building, 108 models with varying input resolution levels were developed to estimate hourly energy usage and annual mean ambient temperature. The results demonstrated that with input parameters at low resolution levels, geometric parameters such as exterior windows, interior windows, and shading exhibited significantly lower computational loads, resulting in reduced errors in the final simulation performance, whereas the occupancy schedule, thermal zoning, and HVAC configuration parameters exhibited significant declines in simulation performance and accuracy. This study presents a methodology applicable to the majority of low-rise, rectangular office structures. Future work would concentrate on carrying out comparison tests for different building forms and types while gradually improving the automation of the process to enable use of the appropriate accuracy level in assessing the crucial issue of energy-modelling input.

Exterior shading devices and outdoor units can be closely coupled since these two building components are commonly installed next to each other. This study uses a coupled EnergyPlus-Fluent modeling approach to examine how a combination of exterior shading and heat rejection from outdoor units can affect the ambient outdoor environment of a building, and how changes in the ambient outdoor environment can influence cooling loads and indoor PM_2.5 exposure. Three exterior shading devices were simulated, including horizontal overhangs, vertical overhangs, and vertical fins. Data from wind-tunnel experiments and field measurements were used to ensure the accuracy of the airflow model, energy model, and pollution model developed in this study. Results indicate that horizontal overhangs could almost offset the increase in cooling loads due to increased ambient outdoor temperatures caused by heat rejection. The use of vertical overhangs did not always mean lower demand for space cooling when heat rejection was considered. Heat rejection, horizontal overhangs, and vertical overhangs could help reduce indoor PM_2.5 exposure, while indoor air pollution was worse after the implementation of vertical fins. This study shows how exterior shading devices and outdoor units can be coupled to achieve better building energy efficiency and improved occupant health.