Abstract

This thesis explores howmachine learning can be used to support better energy management in smart homes. Many smart home systems today collect a large amount of data through sensors and smart meters, but they still depend on simple rules and do not make predictive or automatic decisions. In the academic field, energy forecasting and energy optimization are often studied separately, which creates a gap in understanding how the two components can work together in a real setting. Because of this, there is a need to test an integrated approach that uses both forecasting and optimization in one framework. In this research, the Almanac of Minutely Power dataset (AMPds) After identifying the strongest forecasting model, the next step was to test whether the predictions could support a simple home energy decision. A linear optimization model was created using the PuLP library to schedule a 1000W, 3-hour deferrable appliance under a Time-of-Use (TOU) electricity tariff. The system successfully avoided the expensive peak period and selected a cheaper running time based on the forecasted demand. Although the cost difference in the specific test case was small, the experiment shows that combining forecasting and optimization can provide practical value in a smart home environment. This thesis does not aim to build a complete smart home system. Instead, it provides a proof-of-concept demonstration with a limited dataset, one appliance, and a simple tariff. The results show that an integrated approach is possible and can be improved in future work by adding more households, more appliances, and more advanced optimization methods.

Library of Congress Subject Headings

Home automation--Data processing; Dwellings--Energy conservation--Data processing; Internet of things; Machine learning; Mathematical optimization

Publication Date

12-2025

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Khalid Ezzeldeen

Campus

RIT Dubai

Plan Codes

PROFST-MS

Download

Share

COinS