Applying science and mathematics to big data for smarter buildings

Area of Science:

• Building Science
• Data Science
• Energy Systems Analysis

Background:

• Buildings generate vast amounts of operational and energy data via Building Management Systems (BMS), sensors, and meters.
• A significant portion of this valuable building data remains underutilized or discarded.
• Effective data utilization is crucial for understanding and optimizing building energy performance.

Purpose of the Study:

• To present an analytical tool designed for comprehensive energy consumption assessment in building portfolios.
• To enable building owners, managers, and tenants to make informed decisions regarding energy efficiency.
• To facilitate the reduction of greenhouse gas emissions through optimized building operations.

Main Methods:

• Development of a novel analytical tool integrating data science and mathematical principles.
• Application of the tool for assessing, benchmarking, diagnosing, tracking, forecasting, and simulating energy consumption.
• Utilizing data from Building Management Systems (BMS), submeters, and smart meters.

Main Results:

• The developed tool provides a systematic approach to analyzing large datasets from building operations.
• It enables accurate energy consumption assessment and identification of energy-saving opportunities.
• Demonstrates potential for improved energy efficiency and reduced greenhouse gas emissions across building portfolios.

Conclusions:

• The analytical tool offers a powerful solution for unlocking the value of building operational data.
• It supports proactive energy management strategies, leading to enhanced building performance.
• Facilitates data-driven decision-making for sustainable building operations and emission reduction.