Skip to content Skip to navigation

Technology

Graphs of technology project results

There are several aspects of the Stanford Energy Behavior Initiative's technical platform: hardware and a communications network; an Energy Services Platform (ESP) to streamline the creation of behavioral programs; and several types of algorithms to perform segmentation, disaggregation and automation.

 

Sample avg daily kWh using hourly data
Electric utilities generally market demand-response and energy-efficiency programs to very broad groups.
Brightness, Screen blanking graph
Overlapping, closed commercial standards have plagued and limited flexibility and innovation in Home Area Networks (HANs).
Nest testing Lab
While encouraging user's proactive involvement in reducing their energy use is an important goal, a complementary strategy looks at how automation can improve efficiency with minimal user input.
ESP functional architecture
While encouraging user's proactive involvement in reducing their energy use is an important goal, a complementary strategy looks at how automation can improve efficiency with minimal user input.

Disaggregation:

Three projects on disaggregation, or the separation of a whole home energy signal into appliance specific data to guide people on where they should take action, covered the scope of foundational work necessary to jumpstart significant interest and research in this space.

Performance of different disaggregation algorithms on high-frequency data
Algorithmic approaches to energy disaggregation have traditionally been very simple, and focused solely on detecting changes in a limited number of device states, (e.g., off, on high, on low, sleep mode), in a power signal.
 (Figure from Hart, 1992)
Disaggregation refers to the extraction of appliance level energy use data from an aggregate, or whole-building, energy signal, using statistical approaches.
REDD monitoring device collecting data from a circuit breaker panel
Despite the potential for disaggregation of energy consumption to help residents and small businesses use energy more efficiently, academic work on energy data analytics has been difficult.