SI2-SSE: E-SDMS: Energy Simulation Data Management System Software

Project: Research project

Project Details


SI2-SSE: E-SDMS: Energy Simulation Data Management System Software SI2-SSE: E-SDMS: Energy Simulation Data Management System Software SI2-SSE: E-SDMS: ENERGY SIMULATION DATA MANAGEMENT SYSTEM SOFTWARE Many companies (including Johnson Controls Inc. who is collaborating with us in this project) are developing building energy management systems (BEMSs) and platforms that create and integrate large volumes of data from diverse collections of components, subsystems, and external data sources. If leveraged properly, such data can help reduce energy footprints (and the associated costs) of buildings of all types, leading to more sustainable building systems and architectural designs with monitoring, prioritization, and adaptation of building components and subsystems. In theory, these data can be leveraged starting from the design phase of buildings with data driven building optimization, including the evaluation of the building location, orientation, and alternative energy-saving strategies, to day-to-day operation decisions, and total cost of ownership (TCOs) simulation tools. In practice, however, because of the volume and complexity of the data, the varying spatial and temporal scales at which the key processes operate and we make relevant observations, experts concerned with designing for energy efficiency lack the means to adequately simulate these processes and assess the robustness of conclusions driven from the resulting simulations. While very powerful and highly modular and flexible energy simulation software exists, these suffer from two major challenges that prevent wide-spread usage and reduce potential for transformative impact: cost of modeling and cost of execution. Intellectual Merit: In developing the proposed energy simulation data management system (e-SDMS), we will tackle two key big data challenges that render data-driven energy simulations, today, difficult: The key characteristics of many data sets of urgent interest to data-intensive simulations include the following: (a) voluminous, (b) multi-variate, (c) multi-resolution, (d) correlated, and (d) temporal. We argue that significant savings can be obtained by supporting modular re-use of existing simulation results in new settings. This requires (a) segmentation and indexing of sensory data and simulation along with the corresponding building models and other contextual metadata and (b) re-contextualization and modular re-composition or sketching of building models and new simulation traces based on new building floorplans and contextual metadata. Therefore, this proposal will impact computational challenges that arise from the need to model, analyze, index, visualize, search, and recompose, in a scalable manner, large volumes of multi-variate series resulting from energy observations and simulations. To avoid waste and achieve scalabilities needed for managing large data sets, e-SDMS employs novel multi-resolution data partitioning and resource allocation strategies that can prune unpromising data objects. Therefore, the proposed multi-resolution data encoding, partitioning, and processing algorithms are efficiently computable, leverage massive parallelism, and result in high quality, compact data descriptions. Broader Impacts: According to the US Energy Information Administration, buildings consume more energy than any other sector, with 48.7% of the overall energy consumption and over 75% of the electricity consumption going to buildings. The proposed e-SDMS will fill an important hole in data-driven building design and clean-energy (an area of national priority) and, thus, will enable applications and services with significant economic and environmental impact. In addition to being a Professor of Computer Science and Eng., Candan (PI) is also a Senior Sustainability Scientist at ASUs Global Institute of Sustainability, one of whose missions is to connect researchers with businesses, industry, municipalities, and government. We will complement our collaboration with JCI by leveraging the Institutes connections for dissemination and capacity building. The educational impact of the proposed project will be on graduate education through mentoring of PhD students and on CSE curriculum through incorporation of research challenges and outcomes into existing undergraduate and graduate classes. This will introduce computer science students to big data management, indexing, and analysis, and parallel data processing, as well as will familiarize them with sustainability and clean energy challenges. ASU recruits top-quality undergraduates through a nationally recognized residential Honors College and the Minority Access to Research Careers program and we will recruit undergraduate research interns in the project, with the aim of inspiring them towards graduate research. e-SDMS will also be a testbed for undergraduate Capstone Projects. Since ASU has one of the highest Hispanic student populations in the nation, we will seek to recruit CSE Hispanic students to participate in the project. The PIs have a track record in advising female students and postdocs (including 4 PhD and 1 MS students currently) and will continue to recruit female and minority students. Also, through our collaborations with the ASUs Disability Resources Administration, we will recruit students who are visually impaired or otherwise disabled. Keywords: Energy simulation data management software, Simulation models and temporal data sets, Data and model repurposing
Effective start/end date10/1/139/30/18


  • National Science Foundation (NSF): $499,699.00


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.