Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory
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...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/24/6714 |
id |
doaj-c3eb5f8ae1c146658924fa397327a03c |
---|---|
record_format |
Article |
spelling |
doaj-c3eb5f8ae1c146658924fa397327a03c2020-12-20T00:02:07ZengMDPI AGEnergies1996-10732020-12-01136714671410.3390/en13246714Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective MemoryMarius Reich0Jonas Gottschald1Philipp Riegebauer2Mario Adam3Centre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, GermanyCentre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, GermanyCentre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, GermanyCentre of Innovative Energy Systems, University of Applied Sciences Duesseldorf, 40476 Duesseldorf, GermanyInnovative 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<sub>2</sub> emissions) can be seen in comparison with a standard control system. The investigation of different scenarios illustrates the high relevance of the presented methodology.https://www.mdpi.com/1996-1073/13/24/6714model predictive controlmachine learningsimulationdistrict heating systemGaussian process regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Marius Reich Jonas Gottschald Philipp Riegebauer Mario Adam |
spellingShingle |
Marius Reich Jonas Gottschald Philipp Riegebauer Mario Adam Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory Energies model predictive control machine learning simulation district heating system Gaussian process regression |
author_facet |
Marius Reich Jonas Gottschald Philipp Riegebauer Mario Adam |
author_sort |
Marius Reich |
title |
Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory |
title_short |
Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory |
title_full |
Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory |
title_fullStr |
Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory |
title_full_unstemmed |
Predictive Control of District Heating System Using Multi-Stage Nonlinear Approximation with Selective Memory |
title_sort |
predictive control of district heating system using multi-stage nonlinear approximation with selective memory |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2020-12-01 |
description |
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<sub>2</sub> emissions) can be seen in comparison with a standard control system. The investigation of different scenarios illustrates the high relevance of the presented methodology. |
topic |
model predictive control machine learning simulation district heating system Gaussian process regression |
url |
https://www.mdpi.com/1996-1073/13/24/6714 |
work_keys_str_mv |
AT mariusreich predictivecontrolofdistrictheatingsystemusingmultistagenonlinearapproximationwithselectivememory AT jonasgottschald predictivecontrolofdistrictheatingsystemusingmultistagenonlinearapproximationwithselectivememory AT philippriegebauer predictivecontrolofdistrictheatingsystemusingmultistagenonlinearapproximationwithselectivememory AT marioadam predictivecontrolofdistrictheatingsystemusingmultistagenonlinearapproximationwithselectivememory |
_version_ |
1724377328478322688 |