PRÄKLIMA FASSADE : AUTARKE ELEMENTFASSADE ZUR RAUMKLIMATISIERUNG MIT PRÄDIKTIVER, SELBSTLERNENDER STEUERUNG

PRAEKLIMA Fassade: Self-sufficient Element Facade for Room Air-Conditioning with Predictive, Self-Learning Control System

Project Abstract

The motivations for the project are:

  • Achieve the target of “Reducing greenhouse gas emissions from energy generation by 40% by 2020 compared to 1990”.
  • Building energy consumption accounts for 40% of total energy consumption.
  • The lifecycle of buildings (service life of ~50 years) need to be considered for the maximum reduction of energy costs.
  • High conversion costs to adapt existing buildings to new external influences.
  • Need to make the buildings' weather control flexible to account for climate change.

Our group is involved in the design of the controller for the facade.

Information

Project title: AUTARKE ELEMENTFASSADE ZUR RAUMKLIMATISIERUNG MIT PRÄDIKTIVER, SELBSTLERNENDER STEUERUNG

Acronym: PRÄKLIMA FASSADE

Funding period: September 2019 - October 2021

Funding program: Zentrales Innovationsprogramm Mittelstand (ZIM) , Bundesministerium für Wirtschaft und Technologie (BMWi)

Principal Investigators:

  • TU Dresden Institut für Baukonstruktion
  • Akash Kumar, TU Dresden Institut für Technische Informatik
  • Die Netz-Werker AG
  • SOMMER Fassadensysteme – Stahlbau – Sicherheitstechnik GmbH & Co. KG
  • Priedemann Facade-Lab GmbH

Project Staff:

Control Element of PRAEKLIMA Fassade

Block diagram of the Control Element:

Software Design

Software Design for the Control Element:

Hardware Design

Hardware Design for the Control Element:

Project Related Publications

  • Baranwal, Akhil Raj, Salim Ullah, Siva Satyendra Sahoo, and Akash Kumar. "ReLAccS: A Multi-level Approach to Accelerator Design for Reinforcement Learning on FPGA-based Systems." IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2020), doi: 10.1109/TCAD.2020.3028350.
  • Siva Satyendra Sahoo, Akhil Raj Baranwal, Salim Ullah, Akash Kumar, "MemOReL: A Memory-oriented Optimization Approach to Reinforcement Learning on FPGA-based Embedded Systems" (to appear), Proceedings of the 2021 on Great Lakes Symposium on VLSI, Association for Computing Machinery, New York, NY, USA, July 2021.