This is a project with enormous potential: today, data centres consume around 2% of the world's total energy.
The project benefits from the synergy between IDATHA's experience in the application of neural networks to production processes and that of the team of researchers from the Faculty of Engineering in the mathematical modelling of physical processes and the development of lines of research in artificial intelligence.
Sebastián García, responsible for the execution of the project and CEO of IDATHA, explains that the tool will be based "on artificial intelligence methodologies (specifically neural networks) assisted by mathematical modeling of physical processes". The objective? To control the thermal dynamics and predict the evolution of temperature and relative humidity in a server room based on the operating parameters of the system and the external environmental conditions.
Sebastián points out that energy consumption is one of the main components in the operating cost structure of a data center. Reducing PUE (Power Usage Effectiveness) is a strong indicator of improved energy efficiency and expenditure.
Who benefits?
The tool is designed to benefit companies that have industrial server rooms (data centers) in verticals such as banking and financial services, education, energy, government and public sector, retail, among others. Also to those who provide monitoring and control services to data centers.
"We aspire for GuidAI to reach the state of the art at an international level, innovating in the incorporation of synthetic data generated by mathematical modeling of physical processes into the neural network," says Sebastián. Currently there is no evidence at national and regional level of this type of services to local data centers.
The project contributes to strengthen IDATHA's capabilities in the development and application of artificial intelligence methodologies to monitoring, control, optimization and decision making in industrial processes, while generating specific business opportunities in the provision of services to data centers in the region.
Connect