scaleFLEX - Scalable method for optimizing the energy flexibility of districts

Development of a decentrally organized automation method for improving the demand-side flexibility options of buildings and districts. The utilized data-driven algorithm promise high scalability and therefore low installation and operating costs. The developed method will be validated using different building types (high-tech office buildings, low-tech office buildings, residential buildings).

Short Description

Status

starting 1st of January, 2023

Starting point / motivation

Achieving the European climate targets requires a realignment of the entire energy system. In addition to the efficiency measures, decentralized and intelligently interlinked system solutions are needed to offer flexibility options reliable. Through sector coupling technologies, buildings can be integrated in a grid-supporting manner, thus significantly increasing their decarbonization contribution.

While these developments are less expensive than electrical storage capacity, they require the implementation of an intelligent building automation system to continuously adjust energy consumption to the volatile energy supply and regional energy infrastructure.

With increased cross-linking of the assets, the existing automation concepts, with a centrally organized optimization, are reaching their limits. Reasons for this are the high complexity of the overall system, the limited interoperability of the subsystems, the individual user requirements, and data protection.

In addition, the currently available automation methods are dependent on information from the construction phase, which makes innovative refurbishments and portfolio expansions much more difficult. Therefore, new scalable methods for holistic load optimization are needed on building and district level.

Contents and goals

Therefore, in the project a transfer of the centrally organized automation strategy to distributed control units with decentralized intelligence and decision-making authority is proposed. In this context, grid-friendly operation is achieved by higher-level coordination based on the Stackelberg model approach.

Expected results

The synergetic use of data-driven, decentralized optimization units with a higher-level reinforcement learning optimization procedure facilitates the scalability of the developed methodology and its integration into new and existing building. This enhance the utilization of the existing energy infrastructures and support new innovative grid services and business models.

Project Partners

Project management

Forschung Burgenland / Fachhochschule Burgenland

Project or cooperation partners

Dipl.-Ing. (FH) Manfred Rudolf Fuhrmann
EAM Systems GmbH

Contact Address

Forschung Burgenland / Fachhochschule Burgenland
Christian Heschl
Steinamangerstraße 21
A-7423 Pinkafeld
Tel.: + 43 (5) 7705 - 4121
E-Mail: christian.heschl@fh-burgenland.at
Web: www.forschung-burgenland.at und www.fh-burgenland.at