The smart thermostat: using occupancy sensors to save energy in homes

  title={The smart thermostat: using occupancy sensors to save energy in homes},
  author={Jiakang Lu and Tamim I. Sookoor and Vijay Srinivasan and Ge Gao and Brian Holben and John A. Stankovic and Eric Field and Kamin Whitehouse},
  booktitle={SenSys '10},
Heating, ventilation and cooling (HVAC) is the largest source of residential energy consumption. [] Key Result In comparison, a commercially-available baseline approach that uses similar sensors saves only 6.8% energy on average, and actually increases energy consumption in 4 of the 8 households.

Optimization of In-House Energy Demand

This chapter investigates energy disaggregation techniques to infer appliance states from an aggregated energy signal measured by a smart meter, and evaluates the approach on real-life energy consumption data from several households, compares the classification accuracy of various machine learning techniques, and explains how to use the inferred appliance states to optimize heating schedules.

Saving Energy in Homes Using Wi-Fi Device Usage Patterns

A model for identifying the Wi-Fi devices that are similar in usage compared to the resident's appliances using machine learning techniques is presented and it is shown that this approach can significantly reduce energy wastage in the homes.

Home Energy saving for Heating/cooling system by distributed intelligent energy controller

An intelligent energy controller algorithm that efficiently manages energy consumption for both heating and cooling spaces is proposed based on considering the home's occupancy and sleep patterns as well as outdoor temperature and user's preferences as inputs.

ThermoSense: Occupancy Thermal Based Sensing for HVAC Control

This paper demonstrates ThermoSense, a new system for estimating occupancy that can condition rooms based on usage and shows that it can save 25% energy annually while maintaining room temperature effectiveness.

Energy disaggregation meets heating control

This study investigates energy disaggregation techniques to infer appliance states from an aggregated energy signal measured by a smart meter, and evaluates the approach on real-life energy consumption data from several households, and compares the classification accuracy of various machine learning techniques.

OBSERVE: Occupancy-based system for efficient reduction of HVAC energy

This paper shows how real time occupancy data from a wireless sensor network can be used to create occupancy models which in turn can be integrated into building conditioning system for usage based demand control conditioning strategies.

PreHeat: controlling home heating using occupancy prediction

In UK homes PreHeat both saved gas and reduced MissTime (the time that the house was occupied but not warm) while removing the need for users to program thermostat schedules.

Smart Control Based Energy Management Setup for Space Heating

One such arrangement has been discussed in which several heaters in a single room and different rooms can be controlled along with a smart thermostat relay control algorithm so that energy is properly utilized.



Energy savings through thermostat setback with residential heat pumps

The effects of thermostat setback on energy consumption by residential heat pumps were studied using a computer simulation based on laboratory and field data. A fixed reduction in room thermostat

The self-programming thermostat: optimizing setback schedules based on home occupancy patterns

Programmable thermostats offer large potential energy savings without sacrificing comfort, but only if setback schedules are defined correctly. We present the concept of a self-programming thermostat

At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line (Nominated for the Best Paper Award)

This work uses machine learning techniques to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove and indicates that the system can learn and classify various electrical events with accuracies ranging from 85-90%.

Detecting Human Movement by Differential Air Pressure Sensing in HVAC System Ductwork: An Exploration in Infrastructure Mediated Sensing

We have developed an approach for whole-house gross movement and room transition detection through sensing at only one point in the home. We consider this system to be one member of an important new

Assessing the quality of activities in a smart environment.

The results indicate that activity recognition and assessment can be automated using machine learning algorithms and smart home technology and will be useful for automating remote health monitoring and interventions.

Activity Recognition in the Home Using Simple and Ubiquitous Sensors

Preliminary results on a small dataset show that it is possible to recognize activities of interest to medical professionals such as toileting, bathing, and grooming with detection accuracies ranging from 25% to 89% depending on the evaluation criteria used.

Factors Influencing Space Heat and Heat Pump Efficiency from a Large-Scale Residential Monitoring Study

Since Florida utilities often experience their system peak during the state’s few cold mornings, understanding influences on space heat performance is important to controlling demand. Analysis of

Protecting your daily in-home activity information from a wireless snooping attack

A new privacy leak in residential wireless ubiquitous computing systems is presented, and guidelines for designing future systems to prevent this problem are proposed, and it is shown how these guidelines can be used in a hybrid fashion to prevent against the FATS attack with low implementation costs.


The PlaceLab is a live-in laboratory for the study of ubiquitous computing technologies in the home where the routine activities and interactions of everyday home life can be observed, recorded for later analysis, and experimentally manipulated.

Accurate activity recognition in a home setting

This paper presents an easy to install sensor network and an accurate but inexpensive annotation method and shows how the hidden Markov model and conditional random fields perform in recognizing activities.