Search NASA⌕ Search

SEARCH · Search NASA

Results for “Non Intrusive Load Monitoring”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

NILM Applications for the Energy-Efficient Home

We present a forecast for systems-focused applications of non-intrusive load monitoring (NILM), which meet the needs of homeowners, the technology sector, the service sector, and/or utilities. We discuss both near- and long-term applications.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Business Case for Nonintrusive Load Monitoring

This report explores how utilities, researchers, and consumers could benefit from a lower cost approach to submetering using non-intrusive load monitoring (NILM). NILM is a process of using data from a single point of monitoring, such as a utility smart meter, to provide an itemized accounting of end use energy consumption in residential and small commercial buildings. Pacific Northwest National Laboratory (PNNL) prepared this report for the Bonneville Power Administration (BPA). PNNL participated in an advisory group as part of a research project sponsored by the U.S. Department of Energy (DOE), the Bonneville Power Administration, and the State of Washington. The Electric Power Research Institute (EPRI) convened the advisory committee for two workshops held to identify ways in which NILM may be used. PNNL, on behalf of DOE, helped to cosponsor the first of these workshops. Results of an end-use monitoring study of a bank branch conducted by PNNL are also presented for purposes of illustrating the need for better data in energy savings modeling (DOE 2013a).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Non-Intrusive Energy Disaggregation Using Non-Negative Matrix Factorization With Sum-to-k Constraint

Energy disaggregation or non-intrusive load monitoring addresses the issue of extracting device-level energy consumption information by monitoring the aggregated signal at one single measurement point without installing meters on each individual device. Energy disaggregation can be formulated as a source separation problem, where the aggregated signal is expressed as linear combination of basis vectors in a matrix factorization framework. In this paper, an approach based on Sum-to-k constrained non-negative matrix factorization (S2K-NMF) is proposed. By imposing the sum-to-k constraint and the non-negative constraint, S2K-NMF is able to effectively extract perceptually meaningful sources from complex mixtures. The strength of the proposed algorithm is demonstrated through two sets of experiments: Energy disaggregation in a residential smart home; and heating, ventilating, and air conditioning components energy monitoring in an industrial building testbed maintained at the Oak Ridge National Laboratory. Furthermore, extensive experimental results demonstrate the superior performance of S2K-NMF as compared to state-of-the-art decomposition-based disaggregation algorithms.

42 ENGINEERING↗

Building Simulation Modelers are we big-data ready?

Recent advances in computing and sensor technologies have pushed the amount of data we collect or generate to limits previously unheard of. Sub-minute resolution data from dozens of channels is becoming increasingly common and is expected to increase with the prevalence of non-intrusive load monitoring. Experts are running larger building simulation experiments and are faced with an increasingly complex data set to analyze and derive meaningful insight. This paper focuses on the data management challenges that building modeling experts may face in data collected from a large array of sensors, or generated from running a large number of building energy/performance simulations. The paper highlights the technical difficulties that were encountered and overcome in order to run 3.5 million EnergyPlus simulations on supercomputers and generating over 200 TBs of simulation output. This extreme case involved development of technologies and insights that will be beneficial to modelers in the immediate future. The paper discusses different database technologies (including relational databases, columnar storage, and schema-less Hadoop) in order to contrast the advantages and disadvantages of employing each for storage of EnergyPlus output. Scalability, analysis requirements, and the adaptability of these database technologies are discussed. Additionally, unique attributes of EnergyPlus output are highlighted which make data-entry non-trivial for multiple simulations. Practical experience regarding cost-effective strategies for big-data storage is provided. The paper also discusses network performance issues when transferring large amounts of data across a network to different computing devices. Practical issues involving lag, bandwidth, and methods for synchronizing or transferring logical portions of the data are presented. A cornerstone of big-data is its use for analytics; data is useless unless information can be meaningfully derived from it. In addition to technical aspects of managing big data, the paper details design of experiments in anticipation of large volumes of data. The cost of re-reading output into an analysis program is elaborated and analysis techniques that perform analysis in-situ with the simulations as they are run are discussed. The paper concludes with an example and elaboration of the tipping point where it becomes more expensive to store the output than re-running a set of simulations.

Sanyal, Jibonananda↗

Personalized Energy Reduction Cyber-Physical System (PERCS): A gamified end-user platform for energy efficiency and demand response.

The mission of the Personalized Energy Reduction Cyber-physical System (PERCS) is to create new possibilities for improving building operating efficiency, enhancing grid reliability, avoiding costly power interruptions, and mitigating greenhouse gas emissions. PERCS proposes to achieve these outcomes by engaging building occupants as partners in a user-centered smart service platform. Using a non-intrusive load monitoring approach, PERCS uses a single sensing point in each home to capture smart electric meter data in real time. The household energy signal is disaggregated into individual load signatures of common appliances (e.g., air conditioners), yielding near real-time appliance-level energy information. Users interact with PERCS via a mobile phone platform that provides household- and appliance-level energy feedback, tailored recommendations, and a competitive game tied to energy use and behavioral changes. PERCS challenges traditional energy management approaches by directly engaging occupant as key elements in a technological system.

Sintov, Nicole↗

MFRED, 10 second interval real and reactive power for groups of 390 US apartments of varying size and vintage

Abstract Building electricity is a major component of global energy use and its environmental impacts. Detailed data on residential electricity use have many interrelated research applications, from energy conservation to non-intrusive load monitoring, energy storage, integration of renewables, and electric vs. fossil-based heating. The dataset presented here, Multifamily Residential Electricity Dataset (MFRED), contains the electricity use of 390 apartments, ranging from studios to four-bedroom units. All apartments are located in the Northeastern United States (IECC-climate-zone 4 A), but differ in their heating/cooling system and construction year (early to late 20 th century). To adhere to privacy guidelines, data were averaged across 15 apartments each, based on annual electricity use. MFRED includes real and reactive power, at 10-second resolution, for January to December 2019 (246 million data points). The annual average real power per apartment is 343 W (3.27 W/m 2 of floor area), with strong variation between seasons and apartment size. Considering its large number of apartments, high time resolution, real and reactive power, and 12-month duration, MFRED is currently unique for the multifamily-sector.

97 MATHEMATICS AND COMPUTING↗

HVAC load Disaggregation using Low-resolution Smart Meter Data

Traditional non-intrusive load monitoring (NILM) methods are effective for load disaggregation using high resolution smart meter data collected by power quality meters. However, smart meter data collected and stored by utilities are normally 15-, 30- or 60-minute in granularity, making most NILM methods ineffective. This paper presents a novel sequential energy disaggregation (SED) algorithm for extracting heating, ventilation, and air conditioning (HVAC) energy consumptions from residential and small commercial building loads using 30 min smart meter data. Large, infrequently-used loads are first detected and removed from the total building energy consumption. Then, base energy consumption curves, defined as the energy consumption without heating and cooling loads, are identified using the mild-day method. After that, the heating and cooling loads are extracted using an average value subtracting method. Simulation results with real data show that the proposed SED method is computationally efficient, simple to implement and robust in performance across different types of buildings.

Liang, Ming↗

ShareAnalytics

ShareAnalytics is a lightweight extensible platform for collaborative data analytics and facility characterization via Non-intrusive Load Monitoring (NILM). It consists of three core components: a full stack web application, a dashboard tool for analyzing streaming data and a High Performance Computing (HPC) cluster leveraging slurm for resource management to perform real time analysis. The entire framework is implemented in Docker for ease of deployment and to allow the user to test the platform before making a significant investment in hardware if they require additional computing resources. While many other platforms for analyzing streaming data exists, ShareAnalytics is unique in that HPC capabilities and facility characterization via scored analytics are fully integrated into the platform.

Oesch, TimothyS↗

Electricity Submetering on the Cheap: Stick-on Electricity Meters

We demonstrate a low-cost, 21 x 12 mm prototype Stick-on Electricity Meter (SEM) to replace traditional in-circuit-breaker-panel current and voltage sensors for building submetering. A SEM sensor is installed on the external face of a circuit breaker to generate voltage and current signals. This allows for the computation of real and apparent power as well as capturing harmonics created by non-linear loads. The prototype sensor is built using commercially available components, resulting in a production cost of under $10 per SEM. With no highvoltage install work requiring an electrician, home owners or other individuals can install the system in a few minutes with no safety implications. This leads to an installed system cost that is much lower than traditional submetering technology.. Measurement results from lab characterization as well as a real-world residential dwelling installation are presented, verifying the operation of our proposed SEM sensor. The SEM sensor can resolve breaker power levels below 10W, and it can be used to provide data for non-intrusive load monitoring systems at full sample rate.

Lanzisera, Steven↗

Load Disaggregation Technologies: Real World and Laboratory Performance

Low cost interval metering and communication technology improvements over the past ten years have enabled the maturity of load disaggregation (or non-intrusive load monitoring) technologies to better estimate and report energy consumption of individual end-use loads. With the appropriate performance characteristics, these technologies have the potential to enable many utility and customer facing applications such as billing transparency, itemized demand and energy consumption, appliance diagnostics, commissioning, energy efficiency savings verification, load shape research, and demand response measurement. However, there has been much skepticism concerning the ability of load disaggregation products to accurately identify and estimate energy consumption of end-uses; which has hindered wide-spread market adoption. A contributing factor is that common test methods and metrics are not available to evaluate performance without having to perform large scale field demonstrations and pilots, which can be costly when developing such products. Without common and cost-effective methods of evaluation, more developed disaggregation technologies will continue to be slow to market and potential users will remain uncertain about their capabilities. This paper reviews recent field studies and laboratory tests of disaggregation technologies. Several factors are identified that are important to consider in test protocols, so that the results reflect real world performance. Potential metrics are examined to highlight their effectiveness in quantifying disaggregation performance. This analysis is then used to suggest performance metrics that are meaningful and of value to potential users and that will enable researchers/developers to identify beneficial ways to improve their technologies.

Mayhorn, Ebony T.↗

A Novel, Low-Cost, Reduced-Sensor Approach for Providing Smart Renote Monitoring and Diagnostics for Packaged Air Conditioners and Heat Pumps

This report describes conceptually an approach to providing automated remote performance and conditioning monitoring and fault detection for air conditioners and heat pumps that shows great promise to reduce the capital and installation costs of such systems from over $1000 per unit to $200 to $400 per unit. The approach relies on non-intrusive electric load monitoring (NIELM) to enable separation of the power use signals of compressors and fans in the air conditioner or heat pump. Then combining information on the power uses and one or two air temperature measurements, changes in energy efficiency and occurrence of major faults would be detected. By decreasing the number of sensors used from between ten and twenty in current diagnostic monitoring systems to three for the envisaged system, the capital cost of the monitoring system hardware and the cost of labor for installation would be decreased significantly. After describing the problem being addressed and the concept for performance monitoring and fault detection in more detail, the report identifies specific conditions and faults that the proposed method would detect, discusses specific needs for successful use of the NIELM approach, and identifies the major elements in the path from concept to a commercialized monitoring and diagnostic system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Residential Electricity End-use Disaggregation Using Whole Home Disaggregation Technologies

To understand whether a novel, cost effective approach can support a national program that reports on residential energy consumption, a two-phase research study was undertaken by a federal statistical agency and a national laboratory to evaluate the latest load disaggregation technologies. This paper will present the results of the first phase of the study, which explored whether load disaggregation technologies have the potential to inform end-use estimates for a national survey on residential energy consumption Historically, residential submetering projects have been implemented using a combination of plug-load and circuit-level monitoring. This approach is expensive, requires extensive onsite installation, and faces limitations in measuring smaller and portable end uses. In recent years, innovative computing technologies have entered the market that use algorithms to analyze electric signals and disaggregate household end uses. If proven sufficiently accurate and reliable, these technologies would simplify the identification and measurement of distinct end uses and improve end-use consumption estimation. The first phase of the study was planned as an initial assessment of the three load disaggregation products with the objective of determining the strongest candidates for further evaluation in the second phase. The load disaggregation products were evaluated based on their ability to measure total electricity for the home, detect end uses, measure electricity consumption of end uses, and perform reliably without burdening participants. If demonstrated as effective, obtaining end-use energy consumption data through load disaggregation technology would provide an invaluable check for the national survey at a minimum, and could potentially offer insight for enhancements.

Disaggregation accuracy↗

A Contextually Supervised Optimization-Based HVAC Load Disaggregation Methodology

This paper presents a novel contextually supervised optimization-based approach for disaggregating heating, ventilation, and air-conditioning (HVAC) loads using smart meter or Supervisory Control and Data Acquisition data. To disaggregate the load into HVAC loads, large and infrequently used loads (LIUL), and base loads, we formulate an optimization problem to minimize a set of five loss terms, consisting of the reconstruction errors of the overall load profile, the ramp rate losses, and three distinct loss functions linked with the HVAC load, base load, and LIUL, respectively. To enhance accuracy, we incorporate two forms of contextual information into the problem formulation. First, we utilize mutual information to estimate HVAC energy consumption. Second, we employ a base load dictionary to constrain HVAC load estimation errors. The obtained HVAC load profiles are fine-tuned by abnormal ramp detection followed by binary hypothesis testing. Here, the proposed method is developed and tested using sub-metered residential and commercial building data. Simulation results show that the proposed method outperforms existing methods across various data resolutions and load aggregation levels, showing excellent transferability and generalizability.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Flaming Moe

Current clamp measurements collected on various small electronic devices. Details on the data set can be found in J. M. Vann, T. P. Karnowski, R. Kerekes, C. D. Cooke and A. L. Anderson, A Dimensionally Aligned Signal Projection for Classification of Unintended Radiated Emissions, in IEEE Transactions on Electromagnetic Compatibility, vol. 60, no. 1, pp. 122-131, Feb. 2018, doi: 10.1109/TEMC.2017.2692962.

24 POWER TRANSMISSION AND DISTRIBUTION↗

TAS::89 0927::TAS RECOVERY - The Lean Green Energy Controller Machine

Achieving efficiency improvements and providing demand-response programs have been identified as key elements of our national energy initiative. The residential market is the largest, yet most difficult, segment to engage in efforts to meet these objectives. This project developed Energy Management System that engages the consumer and enables Smart Grid services, applications, and business processes to address this need. Our innovative solution provides smart controller providing dynamic optimization of energy consumption for the residential energy consumer. Our solution extends the technical platform to include a cloud based Internet of Things (IoT) aggregation of data sensors and actuators the go beyond energy management and extend to life style services provided through compelling mobile and console based user experiences.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Disaggregating Smart Meter Data to Identify Electric Loads and Control Opportunities

As utility data, such as smart meter data, becomes more broadly available, there is general interest in using it to improve utility operations and enable adoption of other advanced technology - such as solar photovoltaics (PV), energy storage, and controls. We explore one such use case - identifying electric resistance water heaters from smart meter data, as well as characterizing their potential for load-shifting to support grid voltage stability under high-penetration PV adoption. This paper shows the limitation of typical 15-minute data, and how shortterm capture of additional 1-minute data is needed to enable the desired application. Results indicate about 4 kWh water heating load can be shifted to align with peak sun hours in a low use home. This methodology is an example, and can be adapted to other grid-integrated efficient building use cases.

14 SOLAR ENERGY↗

Sensing Service Transformer Secondary Currents using Planar Magnetic Pick-up Coils

The rapid deployment of distributed energy resources (DERs) is creating stresses on utility assets in the distribution networks. The service transformer, which is the most commonly used utility asset is often not monitored, since the cost of available sensing solutions is as high as the transformer itself. This paper presents a method to use an array of printed circuit board coils to intelligently monitor North American pole top service transformers. The approach, uses a novel, self-calibrating algorithm to infer the fixed geometry of the installation, by recording data over an extended period of time. The proposed method can enable rapid installation of a non-intrusive sensor that can be used to monitor loading levels of the distribution transformer. Furthermore, these sensors can help in planning, prognostics and advanced situational awareness for utilities.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Non-Intrusive Appliance Identification with Appliance-Specific Networks

The problem of noninstrusive load monitoring (NILM) is usually formulated as a single-channel blind source separation task, whose successful solution enable fast and convenient load identification and energy disaggregation. When applied at test time, NILM algorithms aim to identify the operating characteristics of individual appliances from an aggregate power measurement of the entire house. Recent advances in deep learning gave rise to many methods that mostly focus on learning a direct mapping from aggregate measurement to individual appliance power. However, these methods are not only computationally expensive, but they often suffer from overfitting and do not generalize very well. In this article, we propose a novel NILM method that leverages advances in statistical learning that have not been properly applied in this domain before. The proposed method consists of three stages: first, a Bayesian nonparametric learning-based approach for appliance state extraction; second, synthetic minority oversampling technique for data augmentation and mitigating the heavy imbalance in switching events; and third, appliance-specific lightweight long short-term memory networks for status classification for each appliance. Here, we adopt a “differential” input (the difference before and after the switching event) to reduce the complexity of network training and make the proposed method robust to multiappliance switching events. Experiments are conducted to demonstrate the effectiveness of the proposed method, achieving superior performance when compared to recent methods. An ablation study is conducted to demonstrate the effectiveness of each module of our method. Finally, we investigate the quality of generated synthetic samples.

42 ENGINEERING↗