Community Research and Development Information Service - CORDIS

H2020

STORM Report Summary

Project ID: 649743
Funded under: H2020-EU.3.3.1.

Periodic Reporting for period 1 - STORM (Self-organising Thermal Operational Resource Management)

Reporting period: 2015-03-01 to 2016-10-31

Summary of the context and overall objectives of the project

Smart DHC networks can not only reduce greenhouse gas emissions in the DHC network itself, but also at the production site of the electrical grid. In fact, we believe that the large flexibility in DHC networks will be essential in the large-scale roll-out of smart electrical grids. Therefore, intelligent controlled DHC networks are indispensable systems in the transition towards zero carbon solutions. It is in this field that STORM positions itself. The STORM project tackles energy efficiency at district level by developing an innovative district heating & cooling (DHC) network controller. The project partners have developed a first version of the STORM controller based on self-learning algorithms, algorithms which can learn the behavior of the network and the buildings, which is currently experimented in two STORM demo sites, Mijnwater BV in Heerlen (NL) and Växjö Energi in Rottne (SE), where the resulting energetic, economic and environmental gains are evaluated.

Simulations has shown that for the demo site in Rottne a peak reduction of the district heating load up to 20% compared to a classic DH controller can be reached. This is in line with the project objectives and gives large energy saving potentials for other DH networks. One of the benefit of the STORM controller is that DHC networks will be cheaper to operate and more friendly to their environment. In the Rottne case the objective is to reduce or eliminate the use of the bio fuel oil boiler by using the STORM controller. After the winter period of 2016 a technical and environmental evaluation will be done of the STORM controller.

The STORM partners also contributed to the creation of awareness and knowledge building of advanced DHC controllers by participating in national anad international conferences and events. Dissemination activities were started with the creation of a website, Twitter and LinkedIn account, templates for reporting, factsheet and poster. The project results were presented at many national and international conferences and events. In the first period also the educational activities started with the setting up of the first lay-out of the educational packages.

Besides these development and implementation activities, the partners have identified the key exploitable results of the project and are now in the phase of investigating how the future of the STORM project can be handled. STORM shows a great applicability potential of district heating controllers in new and existing networks by demonstrating and implementing our technology in 2 different demonstration cases each with different energy systems, networks and technologies.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The main achievements for the first reporting period are:
• A survey and classification of DHC networks was carried out and for a number of countries a more detailed analysis was made. Information of these networks was gathered in relation to the development and features of the controller and in-depth interviews with energy companies were carried out to get insight in their business cases, the economic and environmental drivers and the technical challenges that they are facing.
• A Matlab simulation model of the demo sites in Rottne (SE) and Mijnwater (NL) was built to evaluate the performance of the controller. The simulation results show a peak reduction of the district heating load up to 20% compared to a classic DH controller. This is in line with the project objectives and gives large energy saving potentials for other DH networks.
The first version of the STORM controller was developed featuring forecasting, tracking and planner algorithms and the features were implemented on the commercial NODA platform. These features were first pre-tested in the Rottne demo before the real life implementation started and showed no major drawback that can hurdle the real life implementation. The STORM version 1 controller is now in operation in Rottne and Mijnwater will follow soon. For the Mijnwater site, a communication interface with the PRIVA building management system (BMS) was developed in order to transform the BMS data into the NODA controller. The developed features of the controller are the second key exploitable result of the project.
• VITO together with NODA is currently looking at the market potential of the controller and how the controller can be exploited on a wider scale. Activities as licensing, setting up of a spin off company, third party licensing, etc. are being investigated.
• Dissemination activities were started with the creation of a website, Twitter and LinkedIn account, templates for reporting, factsheet and poster. The project results were presented at many national and international conferences and events.
• IPR discussions were started with an inventory of the key exploitable results and the intentions of the partners to exploit them. As of today 4 key exploitable results (KER) were identified within the project.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The work done so far in the STORM project is related to the development and implementation of a first version of a district heating and cooling controller based on self learning techniques. Heat demand forecasting is in one form or another an integrated part of most optimisation solutions for district heating and cooling (DHC). Since DHC systems are demand driven, the ability to forecast this behaviour becomes an important part of most overall energy efficiency efforts. The prior work of the STORM partners, based mainly on certain decision tree based regression algorithms, is expanded to include other forms of decision tree solutions as well as neural network based approaches. These algorithms are analysed both individually and combined in an ensemble solution.

The primary purpose of this project is to implement online machine learning forecasting algorithms in an industrial, fully operational real-time environment using actual weather forecasts as input for the system. Basically to run the system as it would have been used in an operational environment. A selection of three algorithms was used to perform the tests, one of which is similar in construction to the algorithm presented in the previous work. Based on the results from the previous study only aggregated data was used to construct models (second approach). This also means that data such as meter data from production facilities can be used as input for the training. The first algorithm used is the Extra-Trees Regressor (ETR), which uses randomized decision trees in relation to sub-sets of the dataset in combination with averaging to increase predictive accuracy and to minimize over-fitting. The ETR algorithm is the one similar to algorithms used previous work. The second algorithm is Extreme Learning Machines (ELM) which is a feed-forward neural network used for regression analysis. An ELM uses a single layer of hidden nodes with randomized weights assigned to the input to the hidden layer. The third algorithm is an expansion of the ELM algorithm, in which a regularisation factor was added to prevent over-fitting of the training data. These algorithms were implemented in the demo sites.

It is shown that the results are in line with expectations based on prior work, and that the demand predictions have a robust behaviour within acceptable error margins. Applications of such predictions in relation to intelligent network controllers for district heating are explored and the initial results of such systems are discussed.

Related information

Record Number: 198344 / Last updated on: 2017-05-18
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top