Welcome to the Intelligent Infrastructure Research Laboratory (INFER Lab), from the Civil and Environmental Engineering Department at Carnegie Mellon University.
We are interested in improving the operational efficiency of our physical infrastructure, as well as increasing its resilience, adaptiveness and autonomy. In an increasingly resource-constrained world, our infrastructure systems will need to be able to interact with their environment and with each other in order to maximize their efficiency and minimize risks. Hence, our lab interested in solving these challenges by providing answers to questions such as: (a) how can we utilize the data generated by instrumentation systems to provide better feedback, learn from experience and better plan for the future?, (b) how can we improve and leverage the interconnectedness of our infrastructure?, and (c) to what extent can we utilize the resources that are already present in our infrastructure to help solve these problems?
The INFERLab is led by Prof. Mario Bergés from the Department of Civil and Environmental Engineering at Carnegie Mellon University.
The project focuses on modelling of the energy consumed by buildings and their outdoor environment at the neighbourhood scale to evaluate strategies that can mitigate urban heat islands and climate change.
This project focuses on the development of novel strategies for increasing the autonomy of space habitats; primarily: 1) root cause analysis of faults, and 2) uncertainty quantification in digital twins.
The project aims to develop enabling methods for practical deployment of reinforcement learning for building control.
In this project we focus on a specific class of unsupervised algorithms based on deep learning techniques that can learn instantaneous power waveforms for individual devices as well as their activation patterns given sufficient data from a single meter.
In this project we focus on estimating the effects of climate change on electric power systems.
The GridBallast project will create low-cost demand-side management technology to address resiliency and stability concerns accompanying the growth of distributed energy resources.
The primary goal of this project is to design, implement, and evaluate a human-in-the-loop sensing and control system for energy efficiency of HVAC and lighting systems based on a novel depth-imaging occupancy sensor.
The primary goal of this project is to design, implement, and evaluate a human-in-the-loop sensing and control system for energy efficiency of HVAC and lighting systems based on a novel depth-imaging occupancy sensor.
To be completed.
This project targets the development of a metadata inference framework to provide operational information, i.e., the metadata associated with sensors and actuators.
Through this project, we seek to develop an integrated framework for predicting extreme temperature risks in urban areas.
This project focuses on the development of statistical models for relating pipeline infrastructure characteristics and the results of methane leak detection surveys.
In this project we study the potential of existing datasets to provide information necessary for decision-making in different contexts: from solar home systems for low-income rural residents in Africa, to utility net-metering datasets from United States households.
Publications that we are especially proud of right now
Best Paper Runner-up at ACM e-energy'21
Best Student Paper Nominee at IEEE SmartGridComm'20
This paper presents the Plug-Load Appliance Identification Dataset (PLAID), a labelled dataset containing records of the electrical voltage and current of domestic electrical appliances obtained at a high sampling frequency (30 kHz). The dataset contains 1876 records of individually-metered appliances from 17 different appliance types (e.g., refrigerators, microwave ovens, etc.) comprising 330 different makes and models, and collected at 65 different locations in Pittsburgh, Pennsylvania (USA). Additionally, PLAID contains 1314 records of the combined operation of 13 of these appliance types (i.e., measurements obtained when multiple appliances were active simultaneously). Identifying electrical appliances based on electrical measurements is of importance in demand-side management applications for the electrical power grid including automated load control, load scheduling and non-intrusive load monitoring. This paper provides a systematic description of the measurement setup and dataset so that it can be used to develop and benchmark new methods in these and other applications, and so that extensions to it can be developed and incorporated in a consistent manner.
Best Paper Award at ACM BuildSys'20
Global urbanization projections suggest that a great majority of human beings will be living in urban areas by the middle of this century. This trend imposes significant strains on urban infrastructure systems and adds additional challenges to achieving environmental, social and economic sustainability goals set by many city governments. Smart city products and services, backed by IoT systems, have been proposed as effective solutions to increase efficiency, reduce costs and improve services. However, as with any technology, IoT solutions for smart cities bring about great opportunities and, at the same time, threats to, among others, governance, security, privacy and community autonomy. As we accumulate experience with these smart city deployments, we must ask ourselves: What would we later regret not regulating now? What good opportunities might certain types of regulation hold back and how can this be mitigated? We offer our perspective on these questions and argue in favor of human-centered IoT systems that are owned, operated and managed much in the same way that other public urban infrastructure systems (e.g., wastewater) are.