| NSF Org: |
IIS Division of Information & Intelligent Systems |
| Recipient: |
|
| Initial Amendment Date: | August 30, 2016 |
| Latest Amendment Date: | August 30, 2016 |
| Award Number: | 1633363 |
| Award Instrument: | Standard Grant |
| Program Manager: |
David Corman
IIS Division of Information & Intelligent Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | September 1, 2016 |
| End Date: | August 31, 2020 (Estimated) |
| Total Intended Award Amount: | $952,504.00 |
| Total Awarded Amount to Date: | $952,504.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
300 TURNER ST NW BLACKSBURG VA US 24060-3359 (540)231-5281 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
VA US 24061-0001 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Big Data Science &Engineering |
| Primary Program Source: |
01001617RB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Transforming villages, towns, and cities into smart, connected, and sustainable communities is one of the most critical technological challenges of the coming decade. Realizing this vision is contingent upon enabling existing community infrastructure such as transportation, communications, and energy systems, to seamlessly integrate sustainable components such as renewable sources, smart sensors, and electric vehicles. Such an integration will ensure that tomorrow's communities are truly sustainable and connected by exhibiting desirable qualities that include: a) zero energy, in that they are self-sufficient in their energy production, b) zero outage, in that communication links across the community are ultra-reliable and experience significantly low interruption, and c) zero congestion, in that the traffic congestion is minimized across the community. With this overarching vision, the goal of this project is to develop a new planning framework for smart, connected and sustainable communities that allows meeting such zero-energy, zero-outage, and zero-congestions goals by optimally deciding on how, when, and where to deploy or upgrade a community's infrastructure. These decisions will be driven by massive volumes of community data, stemming from multiple sources that can include mobility, energy, traffic, communication demands, and other socio-technological information, to make informed decisions on how to gradually and organically transform a community into a fully sustainable and truly connected environment. The scale and heterogeneity of this problem necessitates the need for innovation in the tools used to process, analyze, and visualize heterogeneous data, as well as the data-aware metrics used to monitor the performance of this community infrastructure. One key element of this research is creation of a virtual testbed that can accurately reconstruct, simulate, and evaluate the theoretical framework by leveraging real-world big data sets from Virginia Tech and a zero-energy community in Florida as well as other sources, such as the DOE. The testbed is intended to be open access and will be able to support both research at host institution as well as other users requiring non-proprietary multi-domain open-data sets. The holistic nature of this research is thus expected to catalyze the global deployment of sustainable and connected communities. The proposed research will be complemented by a smart community big data challenge event that will enable broad community participation. The educational plan includes new big data-centric courses, as well as a large-scale involvement of graduate and undergraduate students in big data and smart communities research. Broad dissemination is ensured via open-source software and periodic workshops and tutorials. K-12 outreach events will be organized to attract under-represented student groups to big data research.
This transformative research will lay the theoretical and practical foundations of smart, connected, and sustainable communities by developing the first big data-driven holistic approach to joint planning, optimization, and deployment of community infrastructure for systems of critical importance, such as communication, energy, and transportation networks. By bringing together interdisciplinary domain experts from data science, electrical engineering, and civil and architectural engineering, this research will yield several innovations: 1) Novel big data techniques for faithfully creating spatio-temporal models for smart communities that integrate data from heterogeneous sources and shed light on the composition and operation of a given smart community, 2) Novel, data-driven performance metrics that advance powerful mathematical tools from stochastic geometry to explicitly quantify the health of smart communities via tractable notions of zero energy, zero outage, and zero congestion, 3) Advanced analytical tools that bring forward novel ideas from optimization theory to devise the most effective strategies for deploying, upgrading, and operating various community infrastructure nodes, given the scale, dynamics, and structure of both the data and the community, and 4) A virtual smart community testbed that can accurately reconstruct, simulate, and evaluate the theoretical framework by leveraging open non-proprietary real-world big data sets.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Creating smart and connected communities that are connected via reliable communication and transportation infrastructure and are sustainable in their energy resource usage is a grand challenge of global significance. This research addressed this problem by developing data-driven frameworks that can be used to design, deploy, and optimize smart and connected communities that can self-sustain in their resources and that have pervasive connectivity and intelligently designed transportation systems. In particular, the key intellectual merits include interdisciplinary scientific foundations that can be used to exploit big data analytics and machine learning to better understand how to improve wireless connectivity, energy usage, and transportation performance in multiple communities. In particular, by exploiting novel tools from the fields of stochastic geometry and statistics, the proposed research developed new tractable tools and performance metrics to understand and enhance the connectivity of transportation systems while being cognizant of the fact that future transportation systems will also be wireless connected. The ensuing solutions shed important light on how to design and deploy interdependent wireless and transportation systems, and they provide new metrics to quantify the performance of such systems. This thread of research led to interdisciplinary advances to transportation systems, communications, and stochastic geometry. In addition, a suite of data-driven, low-complexity machine learning frameworks were developed to understand how to design, deploy, and optimize communications infrastructure to enhance connectivity in smart and connected communities. The research in this area led to several novel approaches to enhance wireless communications including the use of mobile access points (including those carried by drones) to service hotspot areas and areas with low wireless coverage. The developed approaches combined novel data analytics techniques, that explored publicly available real data to guide the deployment approach, with rigorous mathematical frameworks from optimization theory, in order to design new ways to enhance connectivity and coverage in smart communities. The developed solutions provide generalizable frameworks that can be used to deploy infrastructure of any types. In addition, this project also developed several new learning and data analytics techniques that allow one to merge datasets of different types, in order to design and enhance infrastructure in smart and connected communities. In particular, new techniques that allow one to augment scarce real datasets with synthetically generated datasets were designed using tools from generative adversarial networks. Then, by combining those tools with deep reinforcement learning algorithms, novel data-guided solutions were developed to enable the operation of communication systems under extreme events. Along with those fundamental research tasks, this project also developed a novel virtual testbed, based on tools from Modelica, to simulate, analyze, and design interdependent infrastructure, including communication systems, smart grids, transportation systems, and other infrastructure (e.g., water). The developed testbed uses both physics-based models as well as data-driven inputs to faithfully simulate interdependent systems in a smart community. Among many use cases, this testbed was extended to simulate the energy system of a real-world net-zero energy community in Florida, using real datasets. All developed testbed solutions and frameworks are being used to engage the broad community through tutorials and workshops, so as to accelerate the adoption of the developed approaches in practice. The foundational nature of the research led to broad impacts across multiple disciplines ranging from smart and connected communities to machine learning, data analytics, statistics, stochastic geometry, energy systems, and network science. The broader impacts included a very broad dissemination to various communities that are interested in smart and connected communities. This dissemination included the development of a monograph on the transportation solutions, as well as various workshops and tutorials, including those that used the developed testbed. The research also led to the creation of a new workforce that is well-versed in the fields of data analytics and their applications to smart and connected communities. Outreach events targeted at under-represented female groups were also conducted with the goal of exposing high school and under-represented students to this research. Close collaboration was forged between the involved institutions, as well as a real-world community in Florida. The research also contributed to the education of several graduate students.
Last Modified: 12/22/2020
Modified by: Walid Saad
Please report errors in award information by writing to: awardsearch@nsf.gov.
