- Data-Driven Key Performance Indicators and Datasets for Building Energy Flexibility: A Review and PerspectivesH. Li, H. Johra, F. de Andrade Pereira, T. Hong, J. Le Dreau, A. Maturo, M. Wei, Y. Liu, A. Saberi-Derakhtenjani, Z. Nagy, A. Marszal-Pomianowska, D. Finn, S. Miyata, K. Kaspar, K. Nweye, Z. O Neill, F. Pallonetto, and B. Dong2022
Energy flexibility, through short-term demand-side management (DSM) and energy storage technologies, is now seen as a major key to balancing the fluctuating supply in different energy grids with the energy demand of buildings. This is especially important when considering the intermittent nature of ever-growing renewable energy production, as well as the increasing dynamics of electricity demand in buildings. This paper provides a holistic review of (1) data-driven energy flexibility key performance indicators (KPIs) for buildings in the operational phase and (2) open datasets that can be used for testing energy flexibility KPIs. The review identifies a total of 81 data-driven KPIs from 91 recent publications. These KPIs were categorized and analyzed according to their type, complexity, scope, key stakeholders, data requirement, baseline requirement, resolution, and popularity. Moreover, 330 building datasets were collected and evaluated. Of those, 16 were deemed adequate to feature building performing demand response or building-to-grid (B2G) services. The DSM strategy, building scope, grid type, control strategy, needed data features, and usability of these selected 16 datasets were analyzed. This review reveals future opportunities to address limitations in the existing literature: (1) developing new data-driven methodologies to specifically evaluate different energy flexibility strategies and B2G services of existing buildings; (2) developing baseline-free KPIs that could be calculated from easily accessible building sensors and meter data; (3) devoting non-engineering efforts to promote building energy flexibility, such as designing utility programs, standardizing energy flexibility quantification and verification processes; and (4) curating datasets with proper description for energy flexibility assessments.
- Real-world challenges for multi-agent reinforcement learning in grid-interactive buildingsKingsley Nweye, Bo Liu, Peter Stone, and Zoltan NagyEnergy and AI Nov 2022
Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning (RL) control, here we propose a non-exhaustive set of nine real world challenges for RL control in grid-interactive buildings (GIBs). We argue that research in this area should be expressed in this framework in addition to providing a standardized environment for repeatability. Advanced controllers such as model predictive control (MPC) and RL control have both advantages and disadvantages that prevent them from being implemented in real world problems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we can investigate the performance of the controllers under a variety of situations and generate a fair comparison. As a demonstration, we implement the offline learning challenge in CityLearn, an OpenAI Gym environment for the easy implementation of RL agents in a demand response setting to reshape the aggregated curve of electricity demand by controlling the energy storage of a diverse set of buildings in a district. We use CityLearn to study the impact of different levels of domain knowledge and complexity of RL algorithms and show that the sequence of operations (SOOs) utilized in a rule based controller (RBC) that provides fixed logs to RL agents during offline training affect the performance of the agents when evaluated on a set of four energy flexibility metrics. Longer offline training from an optimized RBC leads to improved performance in the long run. RL agents that train on the logs from a simplified RBC risk poorer performance as the offline training period increases. We also observe no impact on performance from information sharing amongst agents. We call for a more interdisciplinary effort of the research community to address the real world challenges, and unlock the potential of GIB controllers.
- Design, fabrication, and calibration of the Building EnVironment and Occupancy (BEVO) Beacon: A rapidly-deployable and affordable indoor environmental quality monitorHagen Fritz, Sepehr Bastami, Calvin Lin, Kingsley Nweye, Tung To, Lauren Chen, Dung Le, Angelina Ibarra, Wendy Zhang, June Young Park, William Waites, Mengjia Tang, Pawel Misztal, Atila Novoselac, Edison Thomaz, Kerry Kinney, and Zoltan NagyBuilding and Environment Aug 2022
Indoor Air Quality (IAQ) monitoring is essential to assess occupant exposure to the wide range of pollutants present in indoor environments. Accurate research-grade monitors are often used to monitor IAQ but the expense and logistics associated with these devices often limits the temporal and spatial scale of monitoring efforts. More affordable consumer-grade sensors – frequently referred to as low-cost sensors – can provide insight into IAQ conditions across greater scales but their accuracy and calibration requirements need further evaluation. In this paper, we present the Building EnVironment and Occupancy (BEVO) Beacon. The BEVO Beacon is entirely open-source, including the software, hardware, and design schematics which are all provided on GitHub. We created 20 of these standalone, stationary devices which measure up to 24 parameters at a one-minute resolution of which we focus on carbon dioxide, carbon monoxide, total volatile organic compounds, temperature, and size-resolved particulate matter. We investigated the efficacy of two different calibration approaches – device-specific and environment-averaged – for these sensors as well as also provide an extensive discussion considerations for each of the sensors. Calibrated sensors performed well when compared to reference monitors or calibrated gas standards. The CO sensors yielded the best agreement (r2=0.98-0.99), followed by temperature (r2=0.89-0.99), CO2 (r2=0.62-0.99), and PM2.5 (r2=-0.13-0.91). In all cases, the device-specific calibration approach yielded the most accurate results. We evaluated our devices through a successful 11-week field study where we monitored the IAQ in participants’ bedrooms. The work we present on consumer-grade sensors adds to the existing literature by considering sensor-specific calibration techniques and analysis. The BEVO Beacon adds to the successful line of similarly developed devices by providing an open-source framework that researchers can readily adapt and modify to their own applications.
- Water Demand and Human Behavior during Compounding Disasters: The Case of Winter Storm Uri and the COVID-19 PandemicLauryn A. Spearing, Kingsley Nweye, Helena R. Tiedmann, Zoltan Nagy, Lina Sela, and Kasey M. FaustJun 2022
Engineered systems are designed for a specific operating context based on assumptions about the population served. In turn, management of these systems can be stressed during population shifts (and corresponding demand shifts), such as those seen during both discrete (e.g., hurricanes) and protracted (e.g., pandemics) events. For instance, the COVID-19 pandemic caused drastic changes in society, consequentially changing spatial and temporal water use as people worked from home. In another example, Winter Storm Uri led to utility service disruptions throughout Texas, causing people without power and water to seek shelter, leading to spatial changes in water use in conjunction with physical damage. This sheltering occurred during the COVID-19 pandemic, leading to increased uncertainty in demand and challenges to shelter while ensuring social distancing. Researchers have studied disaster scenarios independently, but there is a gap surrounding compounding disasters as human-infrastructure interactions are likely altered. Here, we assess water demand changes during Winter Storm Uri (which occurred during the COVID-19 pandemic) at the building level. We performed k-means clustering on demand data from four buildings at the University of Texas, Austin. Three buildings showed different daily demand profiles during the storm compared to the spring semester. Interestingly, there were demand increases in buildings not being used as warming centers, perhaps indicating increased occupancy. This trend reveals that people do not necessarily choose to shelter in places that are formally organized. In a museum, water use decreased compared to the already reduced demand during the pandemic, possibly leading to water stagnation and quality concerns.
- Offline Training of Multi-Agent Reinforcement Agents for Grid-Interactive Buildings ControlKingsley Nweye, Zoltan Nagy, Bo Liu, and Peter StoneIn Proceedings of the Thirteenth ACM International Conference on Future Energy Systems Jun 2022
Advanced controllers such as model predictive control and reinforcement learning (RL) control have both advantages and disadvantages that prevent them from being implemented in real world problems. Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning control, we demonstrate in CityLearn, the effect of training off-line from the fixed logs of an external behavior policy. We show that the design of the rule based controller (RBC) used for offline training affects the performance of the RL agents when evaluated on the average daily peak and net electric consumption. While longer offline training from an optimized RBC leads to improved performance in the long run, RL agents that learn from a simplified RBC risk poorer performance as the offline learning period increases.
- MARTINI: Smart meter driven estimation of HVAC schedules and energy savings based on Wi-Fi sensing and clusteringKingsley Nweye, and Zoltan NagyApplied Energy Jun 2022
HVAC systems account for a significant portion of building energy use. Nighttime setback scheduling is an Energy Conservation Measure (ECM) where cooling and heating setpoints are increased and decreased respectively during unoccupied periods with the goal of obtaining energy savings. However, knowledge of a building’s real occupancy is required to maximize the success of this measure. In addition, there is the need for a scalable way to estimate energy savings potential from ECMs that is not limited by building specific parameters and experimental or simulation modeling investments. Here, we propose MARTINI, a sMARt meTer drIveN estImation of occupant-derived Heating, Ventilation and Air Conditioning (HVAC) schedules and energy savings that leverages the ubiquity of energy smart meters and Wi-Fi infrastructure in commercial buildings. We estimate the schedules by clustering Wi-Fi derived occupancy profiles and, estimate energy savings by shifting ramp-up and setback times observed in typical operational/static load profiles that are obtained by clustering smart meter energy profiles. Our case-study results with five buildings over seven months show an average of 8.1%–10.8% (summer) and 0.2%–5.9% (fall) chilled water energy savings when HVAC system operation is aligned with occupancy. We validate our method with results from Building Energy Performance Simulation (BEPS) and find that estimated average savings of MARTINI are within 0.9%–2.4% of the BEPS predictions. In the absence of occupancy information, we can still estimate potential savings from increasing ramp-up time and decreasing setback start time. In 51 academic buildings, we find savings potentials between 1%–5%.
- CROOD: Estimating crude building occupancy from mobile device connections without ground-truth calibrationJune Young Park, Kingsley Nweye, Edward Mbata, and Zoltan NagyBuilding and Environment May 2022
The occupancy information in buildings is fundamental for smart buildings (e.g., occupant-centric controls). Opportunistic occupancy detection (OOD) uses connection data of mobile devices. While OOD has been developed and applied, one critical drawback is that it requires the ground truth of occupants to calibrate, which is limited to gather. Here, we introduce CROOD: a capture and recapture (CRc) inspired OOD. In ecology, CRc has been established for the estimation of animal populations, when the manual count is impossible. We adopt this unique approach to estimate the number of mobile devices in a building. Then, using a simple estimate on the total population, CROOD determines the relationship between the numbers of occupants and mobile devices. We evaluate CROOD numerically on the synthetic building populations and demonstrate its application in a university library using WiFi connection data. We find that CROOD can estimate the number of mobile devices and subsequently the number of occupants with 1–2 weeks to converge a reasonable accuracy. A long term experiment shows that CROOD can adapt to varying population characteristics (e.g., occupants bring more mobile devices), outperforming the reference sample mean estimator. The real building implementation demonstrates that while in the first 1–2 weeks, the sample mean estimator is superior, eventually CROOD adapts and provides better estimates without ground-truth calibration. Although CROOD has a limitation of building types and systems, our results envision that CROOD could be a viable addition to other OOD methods to better utilize existing mobile device connection data to estimate occupancy in buildings.
- Impact of COVID-19 on Academic Campus Energy UseKingsley Nweye, and Zoltan NagyIn Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation Nov 2020
This poster compares energy use of the campus of the University of Texas at Austin during the COVID-19 pandemic of 2020 to that of previous years. Our results show change in weekly aggregate chilled water and electricity consumption as a result of changes in building operation schedules and the response of utility demand to changing occupancy.
- HVAC Scheduling Based on Wi-Fi Derived OccupancyKingsley Nweye, and Zoltan NagyIn Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation Nov 2020
This poster showcases the integration of building management system data with Wi-Fi derived occupancy data to calibrate a building energy model for energy performance prediction and analysis. Our results show an overall improved building energy savings and unmet hours by the Wi-Fi derived schedules compared to the baseline and at 4% occupied threshold, similar energy consumption as baseline is achieved but with reduced unmet hours.