Improvement of the remote expert system based on software OTEA
- /
- POC
- /
- Improvement of the remote...
Heating and cooling contribute to half of the EU’s energy demand. To meet climate goals, the sector must reduce energy consumption. Machine Learning models and statistical techniques can help manage maintenance, optimize processes, and minimize costs. HPC infrastructures support these services.
Start date: 01/11/2015
Duration in months: 18
Problem Description
A deterministic system with brute force conditions is currently applied to detect comfort anomalies. New facilities with a growing number of HVAC machines producing huge amounts of data allow ML models and statistical techniques to be applied, competing with traditional brute force methods.
Goals
New services
Challenges
Like the brute force model the ML model is numerically intensive and needs the use of HPC.
Innovation results
The OTEA remote expert system was developed as a remote management system with an aim for energy optimization through the premature detection of incidents based on historical records. HPC infrastructures offer the required capabilities to support these services and to provide scalable resources.
Business impact
Real-time decision support for clients is offered, reducing energy consumption by 7% per installation, 30% in preventive maintenance visits, and 20% in corrective maintenance. EcoMT expects to double the number of controlled facilities and generate 1 million euros in annual revenue.