RACE

Challenge

Today, the challenge in the district heating sector is that data can only be used in isolated silos or dedicated systems that are not prepared for data exchange, which is necessary for sharing data and utilizing Machine Learning across systems. Existing suppliers in the district heating sector currently use proprietary solutions with vendor lock-in, reducing the flexibility and system integration needed. This poses a barrier to achieving energy efficiency and savings across the entire district heating system, as achieving the next level of optimization requires real-time data analysis.

Solution

This project addresses the challenge of acquiring real-time pressure and flow data from several new measurement points in the district heating network, gaining insights with Machine Learning-generated predictive Digital Twins, which further facilitate the operational optimization of sector coupling through adaptive AI control systems.

Key Deliverables

• Develop a flexible and modern district heating platform that minimizes dependence on fossil energy.
• Develop Machine Learning & AI control systems that use real-time data from various devices and systems to optimize daily operations toward near real-time management.
• Demonstrate and document that the solution optimizes energy production and distribution and can save 10% of district heating companies' annual energy consumption compared to existing district heating supplies that do not have data from real-time measurement points and system coupling with AI control.

Expected Outcome

The project will demonstrate a real-time controlled district heating system with remotely controlled bypasses via mobile networks, using a newly patented real-time flow sensor and HydroState Control Box, an open and scalable cloud-based data platform, as well as the application of advanced AI control techniques on numerous real-time and external data sources. Data and control are collected by the bypasses and transmitted wirelessly to and from the district heating plant's monitoring and control center for optimized management of temperatures, flow, and pressure.

Depending on the existing control systems of the district heating plants, the solution is expected to generate savings potentials of 5% in already optimized systems and up to 15% in older and less optimized systems.