Creating Predictive Algorithms for HVAC Optimization in MATLAB
Shawn Wasserman posted on April 06, 2015 |

A new cloud-based HVAC software, dubbed Predictive Energy Optimization (PEO), can help reduce energy consumption by 10%-25% in large-scale buildings during normal operations. The tool uses the data analytic capabilities of MATLAB to create predictive algorithms that can optimize the HVAC systems.

MathWorks and BuildingIQ developed PEO to minimize the cost of HVAC systems in large-scale commercial buildings. The tool uses the MATLAB Signal Processing Toolbox, the Optimization Toolbox, and the Statistics and Machine Learning Toolbox. These MATLAB tools allow for the filtration of data, real-time optimization of the energy efficiency, and the modeling of the electric, solar, heating, cooling and gas flow.

“While companies look for more intelligence from their data, they often lack the resources and expertise in analyzing and visualizing gigabytes of data, quickly developing algorithms, and finding the best suited algorithmic approach,” said Paul Pilotte, Marketing Manager at MathWorks. “BuildingIQ is setting a benchmark with its ability to analyze and visualize big data sets, deploy these advanced optimization algorithms, and run them in a production cloud environment.”

MATLAB Compiler was then used to integrate the tool into the production systems. This saved time as the team no longer had to translate the MATLAB code into C or Java.

“We use MATLAB because it is the best tool available for prototyping algorithms and performing advanced mathematical calculations,” said BuildingIQ’s Lead Data Scientist, Borislav Savkovic. “MATLAB enabled us to transition our prototype algorithms directly into production-level algorithms that deal reliably with real-world noise and uncertainty.”

To learn more about MATLAB’s code generation, follow this link.

Source MathWorks.

Recommended For You