Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory

Marius Reich, Jonas Gottschald, Philipp Riegebauer and Mario Adam
Additional contact information
Marius Reich: Centre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, Germany
Jonas Gottschald: Centre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, Germany
Philipp Riegebauer: Centre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, Germany
Mario Adam: Centre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, Germany

Energies, 2020, vol. 13, issue 24, 1-25

Abstract: Innovative heating networks with a hybrid generation park can make an important contribution to the energy turnaround. By integrating heat from several heat generators and a high proportion of different renewable energies, they also have a high degree of flexibility. Optimizing the operation of such systems is a complex task due to the diversity of producers, the use of storage systems with stratified charging and continuous changes in system properties. Besides, it is necessary to consider conflicting economic and ecological targets. Operational optimization of district heating systems using nonlinear models is underrepresented in practice and science. Considering ecological and economic targets, the current work focuses on developing a procedure for an operational optimization, which ensures a continuous optimal operation of the heat and power generators of a local heating network. The approach presented uses machine learning methods, including Gaussian process regressions for a repeatedly updated multi-stage approximation of the nonlinear system behavior. For the formation of the approximation models, a selection algorithm is utilized to choose only essential and current process data. By using a global optimization algorithm, a multi-objective optimal setting of the controllable variables of the system can be found in feasible time. Implemented in the control system of a dynamic simulation, significant improvements of the target variables (operating costs, CO 2 emissions) can be seen in comparison with a standard control system. The investigation of different scenarios illustrates the high relevance of the presented methodology.

Keywords: model predictive control; machine learning; simulation; district heating system; Gaussian process regression (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/1996-1073/13/24/6714/pdf (application/pdf)
https://www.mdpi.com/1996-1073/13/24/6714/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:13:y:2020:i:24:p:6714-:d:465093

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().