Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Machine learning based user activity prediction for smart homes

Goutham, Mithun
http://rave.ohiolink.edu/etdc/view?acc_num=osu1595493258565743

Abstract Details

2020, Master of Science, Ohio State University, Mechanical Engineering.
The increasing penetration of renewable sources of energy has resulted in an increased likelihood of power over-generation and ramp rate requirements at the electricity supplier end. By incorporating temporally varying costs of electricity provided to the customer, the grid supplier may choose to offer demand-response programs that encourage the customer to defer high load activities to periods of low grid load, effectively overcoming these challenges and increasing machine life. Smart homes optimally activate appliances at the appropriate time with an objective to minimize load at high-price periods, so that at the user end, the total electricity price is lowered. The work presented in this thesis focuses first on the development of models for energy demand and generation associated with electric vehicle (EV) charging and solar power generation, and their integration in an existing residential energy modeling framework. For this enhanced residential power demand model, machine learning (ML) techniques are used to develop a prediction of the user activities for single-resident and multi-resident households. The predicted power demand can be integrated into the smart home algorithm to enhance the optimal activation of appliances to minimize electricity cost and inconvenience.
Stephanie Stockar (Advisor)
Manoj Srinivasan (Committee Member)
90 p.
Alternative Energy; Artificial Intelligence; Energy; Engineering; Mechanical Engineering
Smart Home; Photovoltaic system; Electric Vehicle; Energy demand; Activity Prediction; Power Prediction; Peak-shaving Valley-filling; Time of use pricing; Machine Learning; Neural Networks; Battery Modeling;

Recommended Citations

Citations

  • Goutham, M. (2020). Machine learning based user activity prediction for smart homes [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1595493258565743

    APA Style (7th edition)

  • Goutham, Mithun. Machine learning based user activity prediction for smart homes. 2020. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1595493258565743.

    MLA Style (8th edition)

  • Goutham, Mithun. "Machine learning based user activity prediction for smart homes." Master's thesis, Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1595493258565743

    Chicago Manual of Style (17th edition)

osu1595493258565743
244
© 2020, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.