Display omitted
•We develop a building energy forecasting model using support vector regression.•Model is applied to data from a multi-family residential building in New York City.•We extend sensor ...based energy forecasting to multi-family residential buildings.•We examine the impact temporal and spatial granularity has on model accuracy.•Optimal granularity occurs at the by floor in hourly temporal intervals.
Buildings are the dominant source of energy consumption and environmental emissions in urban areas. Therefore, the ability to forecast and characterize building energy consumption is vital to implementing urban energy management and efficiency initiatives required to curb emissions. Advances in smart metering technology have enabled researchers to develop “sensor based” approaches to forecast building energy consumption that necessitate less input data than traditional methods. Sensor-based forecasting utilizes machine learning techniques to infer the complex relationships between consumption and influencing variables (e.g., weather, time of day, previous consumption). While sensor-based forecasting has been studied extensively for commercial buildings, there is a paucity of research applying this data-driven approach to the multi-family residential sector. In this paper, we build a sensor-based forecasting model using Support Vector Regression (SVR), a commonly used machine learning technique, and apply it to an empirical data-set from a multi-family residential building in New York City. We expand our study to examine the impact of temporal (i.e., daily, hourly, 10min intervals) and spatial (i.e., whole building, by floor, by unit) granularity have on the predictive power of our single-step model. Results indicate that sensor based forecasting models can be extended to multi-family residential buildings and that the optimal monitoring granularity occurs at the by floor level in hourly intervals. In addition to implications for the development of residential energy forecasting models, our results have practical significance for the deployment and installation of advanced smart metering devices. Ultimately, accurate and cost effective wide-scale energy prediction is a vital step towards next-generation energy efficiency initiatives, which will require not only consideration of the methods, but the scales for which data can be distilled into meaningful information.
Policy directives in several nations are focusing on the development of smart cities, linking innovations in the data sciences with the goal of advancing human well-being and sustainability on a ...highly urbanized planet. To achieve this goal, smart initiatives must move beyond city-level data to a higher-order understanding of cities as transboundary, multisectoral, multiscalar, social-ecological-infrastructural systems with diverse actors, priorities, and solutions. We identify five key dimensions of cities and present eight principles to focus attention on the systems-level decisions that society faces to transition toward a smart, sustainable, and healthy urban future.
•We examine the impact information representation has on energy consumption.•Users were given feedback in kWh or the environmental externality CO2 emissions.•Information representation is shown to ...have a significant impact on consumption.•Results revealed users provided CO2 emissions saved more than users provided kWh.•Conclusions enable future research in eco-feedback information representation.
In response to rising energy costs and concerns over environmental emissions, researchers and practitioners have developed eco-feedback systems to provide building occupants with information on their energy consumption. While such eco-feedback systems have been observed to drive significant reductions in energy consumption, little is known as to what specific design features of these systems are most motivational. One common feature of eco-feedback systems is the way in which energy consumption is represented to users. In this study, we empirically examine the impact that information representation has on energy consumption behavior by comparing the effectiveness of direct energy feedback versus feedback represented as an environmental externality. A 1 month empirical study with 39 participants in an urban residential building was conducted. Participants were divided into two different study groups: one group was provided with feedback in direct energy units and a second group was provided feedback in environmental externality units. Results revealed that information representation has a statistically significant impact on the energy consumption behavior of users, and that users receiving eco-feedback as an environmental externality reduced their consumption more than their counterparts who received feedback in direct energy units. This study represents a crucial first step toward gaining a deeper understanding of how information representation can be leveraged to maximize energy savings.
•Analyzed impacts of Covid-19 on urban residential electricity usage.•Identified substantial increases in both consumption and peak demand.•Increases were closely correlated with both the pandemic’s ...severity and weather.•Forecasted 35%-53% higher peaks should stay-at-homes coincide with hot weather.•Higher usage, including increased hourly peak demand, could challenge grid management.
“Stay-at-home” orders and other health precautions enacted during the COVID-19 pandemic have led to substantial changes in residential electricity usage. We conduct a case study to analyze data from 390 apartments in New York City (NYC) to examine the impacts of two key drivers of residential electricity usage: COVID-19 case-loads and the outdoor temperature. We develop a series of regression models to predict two characteristics of residential electricity usage on weekdays: The average occupied apartment’s consumption (kWh) over a 9am-5pm window and the hourly peak demand (Watt) over a 12pm-5pm window. Via a Monte Carlo simulation, we forecast the two usage characteristics under a possible scenario in which stay-at-home orders in NYC, or a similar metropolitan region, coincide with warm summer weather. Under the scenario, the 9am-5pm residential electricity usage on weekdays is predicted to be 15% – 24% higher than under prior, pre-pandemic conditions. This could lead to substantially higher utility costs for residents. Additionally, we predict that the residential hourly peak demand between 12pm and 5pm on weekdays could be 35% – 53% higher than that under pre-pandemic conditions. We conclude that the projected increase in peak demand - which might arise if stay-at-home guidelines coincided with hot weather conditions - could pose grid management challenges, especially for residential feeders. We also note that, if there is a longer lasting shift towards work and study-from-home, utilities will have to rethink load profile considerations. The applications of our predictive models to managing future smart-grid technology are also highlighted.
The objective of this study was to compare the hydrological performance of an irrigated, 127 mm deep green roof, planted with vegetation native to the New York City area, to a conventional, ...non-irrigated, 100 mm deep green roof, planted with drought-tolerant Sedum spp. Four years of climate and runoff data from both green roofs were analyzed to determine seasonal stormwater retention. Empirical relationships between rainfall and runoff were developed for both roofs, and applied to historical rainfall data in order to compare stormwater retention values for different rainfall depths. Crop coefficients for the vegetation on each green roof were estimated using the soil moisture extraction function. This function was also used to estimate monthly evapotranspiration. Despite being irrigated, the green roof with native vegetation retained more stormwater per annum (64%) than the non-irrigated green roof planted with Sedum spp. (54%). The green roof planted with native vegetation also had approximately twice the crop coefficient (1.13) than the green roof planted with Sedum spp. (0.57), indicating that the New York City native plants transpire more stormwater than the Sedum spp. plants given certain climate and substrate moisture conditions. Overall, the results of the study indicate that, for the New York City climate region, irrigated green roofs of native vegetation have the capacity to better manage stormwater than non-irrigated green roofs planted with drought-tolerant succulents.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Although the majority of urban green infrastructure (GI) programs in the United States, and elsewhere, are being driven by stormwater management challenges arising as a result of the impervious ...nature of modern cities, GI is also believed to provide other benefits that enhance urban sustainability. This article uses a case study approach to discuss the role that GI systems might play in urban climate adaptation strategies for cities like New York City, where increases in both temperature and precipitation are projected over the coming decades. Examples of work conducted by the author and colleagues in New York City to quantify the performance of urban GI are first summarized. This work includes monitoring efforts to understand how extensive green roofs retain rainfall, reduce surface temperatures, and sequester carbon. Next, a discussion of the advantages that a distributed, or neighborhood-level, GI system might bring to a climate adaptation strategy is provided. The article then concludes with an outline of some of the future work that is needed to fully realize the potential of urban GI systems to address future climate change impacts.
Celotno besedilo
Dostopno za:
BFBNIB, DOBA, GIS, IJS, IZUM, KILJ, KISLJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Abstract
Urban parks became critical for maintaining the well-being of urban residents during the COVID-19 global pandemic. To examine the impact of COVID-19 on urban park usage, we selected New York ...City (NYC) and used SafeGraph mobility data, which was collected from a large sample of mobile phone users, to assess the change in park visits and travel distance to a park based on 1) park type, 2) the income level of the visitor census block group (visitor CBG) and 3) that of the park census block group (park CBG). All analyses were adjusted for the impact of temperature on park visitation, and we focused primarily on visits made by NYC residents. Overall, for the eight most popular park types in NYC, visits dropped by 49.2% from 2019 to 2020. The peak reduction in visits occurred in April 2020. Visits to all park types, excluding Nature Areas, decreased from March to December 2020 as compared to 2019. Parks located in higher-income CBGs tended to have lower reductions in visits, with this pattern being primarily driven by large parks, including Flagship Parks, Community Parks and Nature Areas. All types of parks saw significant decreases in distance traveled to visit them, with the exception of the Jointly Operated Playground, Playground, and Nature Area park types. Visitors originating from lower-income CBGs traveled shorter distances to parks and had less reduction in travel distances compared to those from higher-income CBGs. Furthermore, both before and during the pandemic, people tended to travel a greater distance to parks located in high-income CBGs compared to those in low-income CBGs. Finally, multiple types of parks proved crucial destinations for NYC residents during the pandemic. This included Nature Areas to which the visits remained stable, along with Recreation Field/Courts which had relatively small decreases in visits, especially for lower-income communities. Results from this study can support future park planning by shedding light on the different uses of certain park types before and during a global crisis, when access to these facilities can help alleviate the human well-being consequences of “lockdown” policies.
•We study the effect of green roof (GR) size on retention, peak reduction, and lag.•Storm events from 3 GRs with different drainage areas are observed and modeled.•We find GR drainage area has the ...greatest impact on peak runoff reduction.•GR rainfall retention and peak reduction decrease with increased rainfall volume.•A 1-D infiltration model only partially predicts GR behavior across different scales.
Green roofs offer many benefits for dense urban environments, one of which is their potential to supplement existing stormwater management infrastructure. The ability of green roof systems to act as a decentralized rainwater retention and detention network has been the topic of many recent studies. While these studies have provided important insight into the hydrologic performance of green roofs, none to date, to the knowledge of the authors, have specifically examined the effect of green roof drainage area on system performance in an urban climate. This research aims to understand how rainfall characteristics and green roof scale impact the peak and cumulative volume of green roof runoff during individual storm events. The performance of three extensive green roofs in New York City, each having the same engineered components and age but different drainage areas, is analyzed. It is found that green roof drainage area has the greatest impact on peak runoff reduction – peak runoff reduction increases with increasing drainage area – whereas rainfall retention and the time to peak runoff are not greatly influenced by drainage area. Data collected from the three green roofs are used to examine the applicability of a one-dimensional infiltration model, HYDRUS-1D, in predicting hydrologic behavior across the different green roof spatial scales. It is found that model performance improves as the green roof drainage area and rainfall volume increases. However, in general, HYDRUS-1D is only partially able to capture the hydrologic behavior of extensive green roofs across the different rooftop scales examined during this study.
•We examined the question—can social influence drive energy savings?•Empirical data was collected of users exposed to normative eco-feedback.•Two methods are proposed to detect social influence in ...energy consumption data.•Both methods reveal that social influence impacts energy consumption behavior.•Results enable future research avenues regarding social dynamics and energy usage.
Eco-feedback systems provide a significant opportunity to reduce energy consumption. Previous studies have demonstrated a link between providing users with socially contextualized feedback on their energy consumption and reductions in energy use. Yet, the question—can social influence drive energy savings—remains unanswered. In this paper, we develop an algorithmic approach based on stochastic and social network test procedures to assess whether social influence impacts energy consumption behavior and apply the approach to an empirical data set of users exposed to unit-level socially contextualized feedback. We conducted a 47-day empirical experiment in a New York City midrise residential building occupied by students to capture energy consumption and user interaction data for participants in self-identified social networks. Social influence effects on peer network energy consumption were successfully characterized and isolated using adapted social network tests. These results indicate that future research should focus on how social influence and social networks can be leveraged to maximize savings in energy conservation programs.
Building sector energy consumption represents a significant fraction of the overall energy consumption in urban communities. While there has been increasing focus on the development of smart ...environments to support energy savings in urban commercial buildings, the development of smart environments for the residential sector has been less common. Instead, urban residential energy-saving efforts have focused on improving a building's physical infrastructure, introducing energy-saving appliances, and motivating residents to adopt energy conservation practices. This paper illustrates that creating an affinity between a building resident's thermal preferences and a building apartment's unregulated thermal environment represents an alternative means of generating an energy-efficient environment for multi-family, residential buildings. Two years of 15-min interval summer data, obtained from smart cyber-physical systems installed in 310 apartments across two New York City buildings, is used to develop data-enabled (D-E) models of resident thermal preference and unregulated apartment temperatures. Both of these models use a linear mixed-effects approach. The alignment of optimal resident-apartment pairs is then formulated as an integer-programming problem to explore the building energy saving (BES) potential associated with minimizing the difference between unregulated apartment temperature and the residents' thermal preference based on summer cooling loads. The work shows that the energy saving potential vary with a building's physical characteristics as well as the variation in residents' thermal preferences. The work further demonstrates that both the unregulated temperature and the resident's preferred temperature in a given apartment are not only affected by outside temperature and external relative humidity, but also strongly affected by the apartment's geographic orientation. For the specific buildings considered, up to 28% cooling energy saving is possible with full alignment. The paper provides all building monitoring data as an open source data set.