HVAC Energy Optimization using MATLAB
HVAC Energy Optimization using MATLAB : BuildingIQ is using data analytics capabilities in MATLAB to speed up the development and deployment of proactive, predictive algorithms for HVAC energy optimization. BuildingIQ engineers have developed Predictive Energy Optimization, a cloud-based software platform that reduces HVAC energy consumption in large-scale buildings by 10%-25% during normal operation. BuildingIQ is a leading provider of advanced energy management software that actively predicts and manages HVAC loads in commercial buildings. BuildingIQ’s cloud-based solution is powering energy and operational savings in buildings across the globe with reductions in HVAC energy costs by as much as 25 percent. BuildingIQ needed to develop PEO as a real-time system that would help minimize HVAC energy costs in large-scale commercial buildings via proactive, predictive optimization.
The team used MATLAB algorithms integrated in a production cloud environment to optimize occupant comfort while minimizing energy costs. BuildingIQ engineers used Signal Processing Toolbox to filter data, Statistics and Machine Learning Toolbox for algorithms to model contributions of gas, electric, and solar power to heating and cooling processes, and Optimization Toolbox to continuously optimize energy efficiency in real time. To integrate the resulting algorithms into the production systems the team used MATLAB Compiler for deployment, saving time and resources from translating MATLAB algorithms into Java or C. The optimization workflow begins in MATLAB, where BuildingIQ engineers import and visualize 3 to 12 months of temperature, pressure, and power data comprising billions of data points. They use Statistics and Machine Learning Toolbox to detect spikes and gaps, and remove noise produced by sensor failures and other sources using filtering functions in Signal Processing Toolbox.. As part of the modeling process, they use SVM regression, Gaussian mixture models, and k-means clustering machine learning algorithms from Statistics and Machine Learning Toolbox to segment the data and determine the relative contributions of gas, electric, steam, and solar power to heating and cooling processes.
The team builds a PEO model in MATLAB that captures the effect of the HVAC system and ambient conditions on internal temperatures in each zone, as well as on the total power consumption for the building. Using Control System Toolbox they analyze HVAC control system poles and zeros to estimate overall power consumption and determine how quickly each zone is likely to converge to its set point.
MATLAB, is a programming environment for algorithm development, data analysis, visualization, and numeric computation. Simulink is a graphical environment for simulation and Model-Based Design for multidomain dynamic and embedded systems. These products are used to accelerate the pace of discovery, innovation, and development in automotive, aerospace, electronics, financial services, biotech-pharmaceutical, and other industries.
“We use MATLAB because it is the best tool available for prototyping algorithms and performing advanced mathematical calculations,” said Borislav Savkovic, lead data scientist at BuildingIQ. “MATLAB enabled us to transition our prototype algorithms directly into production-level algorithms that deal reliably with real-world noise and uncertainty.”
“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, technical marketing manager, 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.”