Abstract

The ever-growing demand for energy necessitates a shift towards efficient management practices. Buildings, responsible for a significant portion of global energy consumption, present a prime opportunity for optimization. Building Energy Management Systems (BEMS) have emerged as a crucial tool in this endeavor, offering a comprehensive platform for monitoring and integrating various building systems. However, a key functionality within BEMS, energy consumption prediction, has faced limitations in accuracy. This stagnation hinders the full potential of BEMS for achieving optimal energy management strategies. Traditional methods for energy prediction often rely on historical data and lack the sophistication to capture the complex and dynamic nature of building energy consumption. These factors can include weather patterns, occupancy levels, equipment operation, and even human behavior. This complexity necessitates a more advanced approach, and machine learning (ML) offers a promising solution. This research project aims to contribute to this crucial field by developing a novel machine learning model for building energy consumption prediction. Focusing on real-world application, the project will explore the effectiveness of various ML algorithms and their ability to deliver accurate predictions within a commercial building setting. The findings will not only contribute to improved BEMS functionalities but also provide valuable insights into building energy consumption patterns, paving the way for more sustainable and efficient management practices.

Publication Date

12-2024

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Khalil Al Hussaeni

Campus

RIT Dubai

Share

COinS