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.
