Nipun Batra

NILMTK: an open source toolkit for non-intrusive load monitoring

Non-intrusive load monitoring, or energy disaggregation, aims to separate household energy consumption data collected from a single point of measurement into appliance-level consumption data. In recent years, the field has rapidly expanded due to increased interest as national deployments of smart meters have begun in many countries. However, empirically comparing disaggregation algorithms is currently virtually impossible. This is due to the different data sets used, the lack of reference implementations of these algorithms and the variety of accuracy metrics employed. To address this challenge, we present the Non-intrusive Load Monitoring Toolkit (NILMTK); an open source toolkit designed specifically to enable the comparison of energy disaggregation algorithms in a reproducible manner. This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets. Our toolkit includes parsers for a range of existing data sets, a collection of preprocessing algorithms, a set of statistics for describing data sets, two reference benchmark disaggregation algorithms and a suite of accuracy metrics. We demonstrate the range of reproducible analyses which are made possible by our toolkit, including the analysis of six publicly available data sets and the evaluation of both benchmark disaggregation algorithms across such data sets.

It's Different: Insights into home energy consumption in India

Residential buildings contribute significantly to the overall energy usage across the world. Real deployments, and collected data thereof, play a critical role in providing insights into home energy consumption and occupant behavior. Existing datasets from real residential deployments are all from the developed countries. Developing countries, such as India, present unique opportunities to evaluate the scalability of existing research in diverse settings. Building upon more than a year of experience in sensor network deployments, we undertake an extensive deployment in a three storey home in Delhi, spanning 73 days from May-August 2013, measuring electrical, water and ambient parameters. We used 33 sensors across the home, measuring these parameters, collecting a total of approx. 400 MB of data daily. We discuss the architectural implications on the deployment systems that can be used for monitoring and control in the context of developing countries. Addressing the unreliability of electrical grid and internet in such settings, we present Sense Local-store Upload architecture for robust data collection. While providing several unique aspects, our deployment further validates the common considerations from similar residential deployments, discussed previously in the literature. We also release our collected data- Indian data for Ambient Water and Electricity Sensing (iAWE), for public use.

SensorAct: a privacy and security aware federated middleware for building management

The archaic centralized software systems, currently used to manage buildings, make it hard to incorporate advances in sensing technology and user-level applications, and present hurdles for experimental validation of open research in building information technology. Motivated by this, we --- a transnational collaboration of researchers engaged in development and deployment of technologies for sustainable buildings --- have developed SensorAct, an open-source federated middleware incorporating features targeting three specific requirements: (i) Accommodating a richer ecosystem of sensors, actuators, and higher level third-party applications (ii) Participatory engagement of stakeholders other than the facilities department, such as occupants, in setting policies for management of sensor data and control of electrical systems, without compromising on the overall privacy and safety, and (iii) Flexible interfacing and information exchange with systems external to a building, such as communication networks, transportation system, electrical grid, and other buildings, for better management, by exploiting the teleconnections that exist across them. SensorAct is designed to scale from small homes to network of buildings, making it suitable not only for production use but to also seed a global-scale network of building testbeds with appropriately constrained and policed access. This paper describes SensorActs architecture, current implementation, and preliminary performance results.

INDiC: Improved Non-intrusive Load Monitoring Using Load Division and Calibration

Residential buildings contribute significantly to the overall energy consumption across most parts of the world. While smart monitoring and control of appliances can reduce the overall energy consumption, management and cost associated with such systems act as a big hindrance. Prior work has established that detailed feedback in the form of appliance level consumption to building occupants improves their awareness and paves the way for reduction in electricity consumption. Non-Intrusive Load Monitoring (NILM), i.e. the process of disaggregating the overall home electricity usage measured at the meter level into constituent appliances, provides a simple and cost effective methodology to provide such feedback to the occupants. In this paper we present Improved Non-Intrusive load monitoring using load Division and Calibration (INDiC) that simplifies NILM by dividing the appliances across multiple instrumented points (meters/phases) and calibrating the measured power. Proposed approach is used together with the Combinatorial Optimization framework and evaluated on the popular REDD dataset. Empirical results demonstrate significant improvement in disaggregation accuracy, achieved by using INDiC based Combinatorial Optimization, demonstrate significant improvement in disaggregation accuracy.

Experiences with Occupancy based Building Management Systems

Buildings are one of the largest consumers of electricity. Dominant electricity consumption within the buildings, contributed by plug loads, lighting and air conditioning, can be significantly improved using Occupancy-based Building Management Systems (Ob-BMS). In this paper, we address three critical aspects of Ob-BMS i.e. 1) Modular sensor node design to support diverse deployment scenarios; 2) Building architecture to support and scale fine resolution monitoring; and 3) Detailed analysis of the collected data for smarter actuation. We present key learning across these three aspects evolved over more than one year of design and deployment experiences. The sensor node design evolved over a period of time to address specific deployment requirements. With an opportunity at the host institute where two dorm buildings were getting constructed, we planned for the support infrastructure required for fine resolution monitoring embedded in the design phase and share our preliminary experiences and key learning thereof. Prototype deployment of the sensing system as per the planned support infrastructure was performed at two faculty offices with effective data collection worth 45 days. Collected data is analyzed accounting for efficient switching of appliances, in addition to energy conservation and user comfort as performed in the earlier occupancy based frameworks. Our analysis shows that occupancy prediction using simple heuristic based modeling can achieve similar performance as more complex Hidden Markov Models, thus simplifying the analytic framework.

Dataport and NILMTK: A building data set designed for non-intrusive load monitoring

Non-intrusive load monitoring (NILM), or energy disaggregation, is the process of using signal processing and machine learning to separate the energy consumption of a building into individual appliances. In recent years, a number of data sets have been released in order to evaluate such approaches, which contain both building-level and appliance-level energy data. However, these data sets typically cover less than 10 households due to the financial cost of such deployments, and are not released in a format which allows the data sets to be easily used by energy disaggregation researchers. To this end, the Dataport database was created by Pecan Street Inc, which contains 1 minute circuit-level and building-level electricity data from 722 households. Furthermore, the non-intrusive load monitoring toolkit (NILMTK) was released in 2014, which provides software infrastructure to support energy disaggregation research, such as data set parsers, benchmark disaggregation algorithms and accuracy metrics. This paper describes the release of a subset of the Dataport database in NILMTK format, containing one month of electricity data from 669 households. Through the release of this Dataport data in NILMTK format, we pose a challenge to the signal processing community to produce energy disaggregation algorithms which are both accurate and scalable.

NILMTK v0.2: a non-intrusive load monitoring toolkit for large scale data sets: demo abstract

In this demonstration, we present an open source toolkit for evaluating non-intrusive load monitoring research; a field which aims to disaggregate a households total electricity consumption into individual appliances. The toolkit contains: a number of importers for existing public data sets, a set of preprocessing and statistics functions, a benchmark disaggregation algorithm and a set of metrics to evaluate the performance of such algorithms. Specifically, this release of the toolkit has been designed to enable the use of large data sets by only loading individual chunks of the whole data set into memory at once for processing, before combining the results of each chunk.

If You Measure It, Can You Improve It? Exploring The Value of Energy Disaggregation

Over the past few years, dozens of new techniques have been proposed for more accurate energy disaggregation, but the jury is still out on whether these techniques can actually save energy and, if so, whether higher accuracy translates into higher energy savings. In this paper, we explore both of these questions. First, we develop new techniques that use disaggregated power data to provide actionable feedback to residential users. We evaluate these techniques using power traces from 240 homes and find that they can detect homes that need feedback with as much as 84% accuracy. Second, we evaluate whether existing energy disaggregation techniques provide power traces with sufficient fidelity to support the feedback techniques that we created and whether more accurate disaggregation results translate into more energy savings for the users. Results show that feedback accuracy is very low even while disaggregation accuracy is high. These results indicate a need to revisit the metrics by which disaggregation is evaluated.

Gemello: Creating a Detailed Energy Breakdown from Just the Monthly Electricity Bill

The first step to saving energy in the home is often to create an energy breakdown: the amount of energy used by each individual appliance in the home. Unfortunately, current techniques that produce an energy breakdown are not scalable: they require hardware to be installed in each and every home. In this paper, we propose a more scalable solution called Gemello that estimates the energy breakdown for one home by matching it with similar homes for which the breakdown is already known. This matching requires only the monthly energy bill and household characteristics such as square footage of the home and the size of the household. We evaluate this approach using 57 homes and results indicate that the accuracy of Gemello is comparable to or better than existing techniques that use sensing infrastructure in each home. The information required by Gemello is often publicly available and, as such, it can be immediately applied to many homes around the world.

Bits and watts: improving energy disaggregation performance using power line communication modems: poster abstract

Non-intrusive load monitoring (NILM) or energy disaggregation, aims to disaggregate a households electricity consumption into constituent appliances. More than three decades of work in NILM has resulted in the development of several novel algorithmic approaches. However, despite these advancements, two core challenges still exist: i) disaggregating low power consumption appliances and ii) distinguishing between multiple instances of similar appliances. These challenges are becoming increasingly important due to an increasing number of appliances and increased usage of electronics in homes. Previous approaches have attempted to solve these problems using expensive hardware involving high sampling rates better suited to laboratory settings, or using additional number of sensors, limiting the ease of deployment. In this work, we explore using commercial-off-the-shelf (COTS) power line communication (PLC) modems as an inexpensive and easy to deploy alternative solution to these problems. We use the reduction in bandwidth between two PLC modems, caused due to the change in PLC modulation scheme when different appliances are operated as a signature for an appliance. Since the noise generated in the powerline is dependent both on type and location of an appliance, we believe that our technique based on PLC modems can be a promising addition for solving NILM.