A class of products that monitor a building’s energy usage from a single point of access and disaggregate energy uses into individual components.

Potential applications for NILMs include: 1) load monitoring/forecasting/research by utilities and energy efficiency organizations, 2) energy audit tool, and 3) component of an energy management system to provide actionable information.

Potential sectors include residential, commercial, and industrial, although most current efforts appear to be focused on residential applications. Access methods and degrees of intrusiveness vary for devices that plug into standard electrical outlets, devices requiring current transformers (CTs) at the electrical panel, devices that are inserted into the utility meter, and some methods that are software only (utilizing SmartMeter data).  With these devices, users can determine which appliances use the most energy and perhaps identify appliances that are left powered on for longer than is necessary.  Users on time of day rates can determine the most cost effective times to use energy intensive appliances. 

Basic operations include: 1) signal processing for methods with hardware, 2) signal uploading to a computer server (typically in “the cloud”), 3) analysis using pattern matching and similar algorithms to identify and classify individual loads, and 4) download to the user using a home energy management display or similar system.

Approaches to identify loads vary and research in this area is ongoing. Some methods require significant user training (turning devices on and off to “teach” the device); other methods seek to leverage pre-loaded signature libraries that gain experience as they are exposed to more loads.

The accuracy of products varies depending on the targeted usage. Accuracy ranges from a goal of very accurate load identification and characterization (at least as accurate as other metering technologies) to simply identifying the top energy uses with 10-20% accuracy.

Existing monitoring techniques are invasive and expensive. They require monitoring devices for each appliance or plug-load, typically cost thousands of dollars per home, and require the installation of numerous pieces of equipment. In residential applications, whole home energy usage information is readily available along with comparative and trend data (e.g. oPower), but information on individual loads is not available, making it difficult to ascertain which loads are responsible for energy usage. Conditional Demand Analysis (CDA) is a modeling technique that can be used to disaggregate end uses, but this requires time intensive field studies and surveys along with relatively large samples to support the statistical characterizations. Note that CDA does not support real-time information but is useful for longer term studies.

Pioneering NILM work was first introduced by George Hart in the 1980s. Enetics has offered products in this area since 1996, based on work by Hart and EPRI. Their product is dated (using a Microsoft Windows 95-type interface), must be installed by an electrician at the utility meter, requires manual appliance identification, and does not provide real-time or automated load identification (although they say they are “working on this”). Their business model and target market is utilities, and the product requires an investment of $1,200/meter and $8,000 for software.

New developments in this area focus on less intrusive monitoring, more sophisticated signal measurements and signal processing, lower costs, real-time load identification, and interfaces with energy management displays. These newer products are in the pre-commercialization phase. Companies currently developing products in this area include (in no particular order): Intel, EMME, Belkin, Enetics, Navetas, Onzo, LoadIQ, PlotWatt and Verdigrist . Other companies are offering products that do not currently provide disaggregating capabilities, but are focused on related areas such as metering, home area networks and home energy management systems. These include TED, PowerHouse Dynamics, Blue Line Innovations, Energy Hub, Tendril, and many others.  

LoadIQ is leveraging advances in signal processing and proprietary algorithms developed over the last decade to deliver load-level energy intelligence from a single hardware connection.  They claim that for commercial buildings, nearly every energy-savings effort can be improved by using more granular energy intelligence. The primary obstacle has always been the cost of acquiring the data. LoadIQ's EI.Monitor is installed at a facility's main electrical distribution panel and is a single hardware connection that delivers load-level energy information.  The Enable.EI platform tracks energy consumption and power quality for specific loads and converts data into intelligence for building owners and operators.  The system is esigned for commercial buildings, 3- phase, 3-wire (delta) and 3-phase, 4-wire (wye) circuits with 100 VAC to 305 VAC (line to neutral/ground). 

NILM represents the evolution of energy management software for building owners and operators, going from utility statements to web-based dashboards and business intelligence/analytics. NILM capabilities allow the software to uncover actionable insights at the load level.  NILM provides answers to the following questions:

*What devices and end-uses are driving energy consumption?
*What loads are responsible for your current peak demand?
*What is the energy cost of operating  a specific piece of equipment?

NILM's can be integrated into leading energy management software applications.  When proposing big ticket energy efficiency measures, it makes sense to access and leverage detailed load-level energy data to justify the retrofit, and then measure the results. If grants or utility rebates are involved, such load monitoring may be required.

The pioneering work in NILMs occurred in the 1980s, but nobody has successfully driven this technology into the marketplace. Microsoft and Google have entered and exited the home energy management market, and a lot of startups as well as established companies are trying to penetrate this market. More volatility in the market is to be expected, making it difficult for consumers and business partners to move forward.

The ability of the technology to successfully differentiate energy sources in a real environment still needs to be proven through lab and field studies. Also, the information must be presented and integrated into a system that provides actionable information (such as a home energy management display) so end users can make decisions that reduce their energy consumption.

There is a danger of providing too much information as well as too little, which could stifle the ability of this technology to penetrate the mass market. Research into the effectiveness of home energy management systems must accompany research into the core NILM technology to ensure energy-saving benefits.

Several products on the market do not disaggregate, but rather rely on low-cost monitoring devices to plug in between appliances and the wall socket. These devices communicate wirelessly to a central unit and display energy uses for devices that are plugged into these monitoring devices. While these products do not contain elegant disaggregating technology, they could provide “good enough” insight into primary energy uses, particularly if a low-cost, non-intrusive method to incorporate whole home energy usage and dedicated circuit loads (such as HVAC, hot water, oven) was included with these products.