Minimizing Plant Energy Consumption – Climate Control News
Chilled water power plants represent an important part of the energy used in buildings.
This session will present machine learning techniques to develop an optimal control strategy to reduce energy consumption while maintaining the required chilled water production.
The strategy identifies in real time the optimal number of chillers, cooling load distribution among chillers, and condenser water flow setpoints that minimize plant energy consumption.
Presenter Michael Berger, Head of R&D at Conserve It, will show how he built a digital twin of the plant that automatically updates based on operating data.
Berger said the data relied on data pre-processing and expert knowledge-driven stresses, to capture changes in equipment performance over time.
Computing efficiency was a fundamental requirement, leveraging improvements in the computing capabilities of Edge devices in recent years, to allow the solution to be fully deployable on-premises, without the need for cloud components.
This removed obstacles such as ongoing charges and security or stability issues that can arise with constant internet connection requirements.
The results of the deployment on several sites will be presented to demonstrate significant energy savings.
As Head of R&D at Conserve It, Berger leads research, prototyping, and machine learning algorithms for real-time analysis and optimization of live equipment in the built environment.
Applications range from innovative cooling plant optimization and predictive maintenance to advanced control solutions.
Berger obtained a master’s degree in engineering in France before gaining experience in a leading research center.
He gained experience at the consultancy firm Environmentally Sustainable Design in Singapore. He joined Conserve It in 2014, where he draws on years of experience in energy efficiency, cooling plant optimization and machine learning.