Saving Energy in Homes Using Wi-Fi Device Usage Patterns

Saving Energy in Homes Using Wi-Fi Device Usage Patterns

Tejasvi Kothapalli (Lynbrook High, San Jose, USA)
Copyright: © 2018 |Pages: 14
DOI: 10.4018/IJEOE.2018070103

Abstract

Reducing power usage in the residential sector is a global problem. Appliances used for space heating, cooling, and lighting are the primary sources of home energy consumption, increased costs, and CO2 emissions. Such devices are a significant source of energy wastage if they are left on and not being used. This article proposes a solution to reduce energy wastage in smart homes. The solution consists of a method to detect the presence of resident activities in the household based on Wi-Fi devices. It presents a model for identifying the Wi-Fi devices that are similar in usage compared to the resident's appliances using machine learning techniques. In addition to displaying the device usage charts, this solution helps in automatically turning off such appliances when they are not in use. A controlled experiment is conducted to evaluate the performance of the solution. The results indicate that this approach can significantly reduce energy wastage in the homes.
Article Preview

1. Introduction

According to a study (D&R International Ltd., 2012), 45% of the energy used within the residential sector is for space heating, 18% is for water heating, 9% is for space cooling, and 6% is for lighting. These four factors make up 78% of the total energy usage in most homes, so a good place to focus energy saving efforts is heating, cooling, and lighting. The same study also predicts that there will be a 13% increase in energy consumption between 2009 and 2035. According to Gardner and Stern (2008) and Armor (1995), direct energy usage by households accounted for approximately 38% of overall US CO2 emissions, or 626 million metric tons of carbon in 2005. These emissions equal about 8% of global emissions, which is larger than the emissions of any country except China. Reducing power consumption in the residential sector is a global problem (Ueno et al., 2006). Studies show 20% to 30% of energy usage can be saved by turning appliances, lighting, cooling, and heating devices off when residents are away from home (Lu, 2010).

Motion sensors or occupancy sensors are used in indoor spaces to control appliances. If no motion is detected, it assumes that space is empty, and thus the sensors do not light the space. These sensors can be manually programmed to turn “off” after a preset time interval. A paper by Garg and Bansal (2000) presented the design of a smart occupancy sensor that saves 5% more energy compared to fixed delay motion sensors. The system learns the variations in residents activity levels based on the time of the day. Based on this knowledge, it varies the delay and turns “off” the lights earlier based on how long a resident is likely to stay in a given room (Torunski et al., 2012). In the paper (Lu et al., 2010), the authors presented the concept of a smart thermostat that sensed occupancy statistics in a home to save energy through improved control of the heating, ventilation, and air conditioning (HVAC) system. They demonstrated how to use wireless motion sensors and door sensors to sense occupancy and sleep patterns in a home, and how to use these patterns to save energy by automatically turning off the home’s HVAC system.

In the commercial sector, recent research was performed in detecting the building occupancy and implementing the energy-saving strategies. The MIT Enernet study (Vaccari, 2009) demonstrates the campus-wide Wi-Fi network activity data shows building occupancy and the information could be utilized in implementing lighting and ventilation strategies across the campus. According to Ouf (2017) and Li (2012), Wi-Fi networks can be used to analyze occupancy at a higher level of accuracy and minimal cost. The paper (Thanayankizil, 2012) explores the methods to detect the office building occupancy using soft sensors such as ID badge scanning systems, Wi-Fi access points, online calendar.

In the residential sector, more research will be needed to make the systems simpler, unobtrusive, and deterministic. Otherwise, they will simply be ignored. New solutions are needed to save energy without requiring daily thought or the intervention of residents. The growth of Internet of Things (IoT) encompasses a wide variety of sensing devices such as smart phones, and through their collaborative operations, billions of such devices will realize the vision of smart homes, smart cities, and beyond (Reinhardt, Christin, & Kanhere, 2014). A smart home can now include app controlled light bulbs, smart plugs, robotic vacuum cleaners, smart coffee makers that synchronize to a morning alarm clock, electronic locks. Programmable smart plugs provide the ability for residents to turn off appliances from a smart phone or tablet and create on/off schedules and rules (Page, 2017). Through Wi-Fi residents can access IoT devices with a smart phone or tablet via a home router (Monnier, 2013). The diffusion of Wi-Fi enabled devices is expected to grow to 3.4 devices and connections per capita by 2020, up from 2.2 per capita in 2015 (Cisco Systems Inc., 2016). These Wi-Fi devices are good indicators of a resident’s presence or activity in a home.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 4 Issues (2019): 1 Released, 3 Forthcoming
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing