STORM

Self-organising Thermal Operational Resource Management

Project Details

Project date: 
March, 2015 to August, 2018

Budget Information

EU contribution: 
€1,972,126
Total cost : 
€1,972,126
Funding programme: 
H2020
EE 13 - 2014/2015: Technology for district heating and cooling

Pilot Cities

  1. Rottne
  2. Heerlen

The STORM project tackles energy efficiency at district level by developing an innovative district heating & cooling (DHC) network controller. Based on self-learning algorithms, the developed controller will enable to maximize the use of waste heat and renewable energy sources in DHC networks.

The controller has been implemented in two demo sites, Mijnwater BV in Heerlen (the Netherlands) and Växjö Energi in Rottne (Sweden), where the resulting energetic, economic and environmental gains are assessed.

Through replication, dissemination and education efforts, the project outcomes will be transferred to stakeholders across the EU, and will thus contribute to a wider deployment of DHC networks on EU level.

The project has the following objectives:

Global:

Boosting energy efficiency at district level through the use of waste heat, renewable energy sources and storage systems.

Research:

  • Building on state of the art technical developments and advanced business models;
    • Starting from control algorithms suited for both existing and new 4th generation DHC networks
    • Using market-based multi-agent systems combined with reinforcement learning
    • Applying self-learning and self-adaptive control, combining recent developments in model-based multi-agent systems and model-free control
    • Creating an add-on to many existing DHC network controllers and SCADA systems
  • Developing an innovative controller for district heating & cooling (DHC) networks.
    • Balancing supply and demand in a cluster of heat/cold producers and consumers
    • Integrating multiple efficient generation sources (renewable energy sources, waste heat and storage systems)
    • Including three control strategies in the controller (peak shaving, market interaction, and cell balancing). Depending on the network, one or more of these strategies can be activated.

Evaluation:

  • Demonstrating the benefits of smart control systems;
  • Quantifying the energetic, economic and environmental benefits of the controller.

Replicability:

  • Developing innovative business models needed for the large-scale roll-out of the controller at reduced costs;
    • Investigating exploitation possibilities to facilitate the platform market uptake
    • Distributing the value amongst the different market players (producers, transporters, consumers of energy) by applying the control strategies in the controller
    • Taking into account different market set-ups to replicate in other countries than the ones of the demonstrators
  • Designing a scalable and performing self-learning control approach requiring limited external experts;
  • Increasing awareness on the need to control DHC networks in a smart way.