MATLAB data analytics used for energy optimisation

Energy management software provider BuildingIQ has utilised data analytics capabilities in MATLAB, from MathWorks, to speed up the development and deployment of proactive, predictive algorithms for HVAC energy optimisation.

BuildingIQ engineers needed to develop its Predictive Energy Optimisation (PEO) software platform as a real-time system to help minimise HVAC energy costs in large-scale commercial buildings via proactive, predictive optimisation. The team used MATLAB algorithms integrated in a production cloud environment to optimise occupant comfort while minimising energy costs.

The 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 optimise 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.

“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.”

PEO can now reliably reduce HVAC energy consumption in large-scale buildings by 10-25% during normal operation. MathWorks Technical Manager Paul Pilotte said, “BuildingIQ is setting a benchmark with its ability to analyse and visualise big data sets, deploy these advanced optimisation algorithms and run them in a production cloud environment.”

Source