dynamic emulation modelling for the optimal operation of water systems: an overview
TRANSCRIPT
![Page 1: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/1.jpg)
Andrea Castelletti1, Stefano Galelli2, Matteo Giuliani1
1 Dipartimento di Elettronica, Informazione, e Bioingegneria, Politecnico di Milano, Milano, Italy 2 Pillar of Engineering Systems and Design, Singapore University of Technology and Design, Singapore
Improving Computational Efficiency in Modeling Complex Environmental Systems
Dynamic emulation modelling for the optimal operation of water systems: an overview
Pollock n. 31
H41J-01
![Page 2: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/2.jpg)
Emulation modelling: reconciling science and decision making …
DM High fidelity Accuracy
Credibility Simplicity
DATA DRIVEN PROCESS BASED
DM
![Page 3: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/3.jpg)
Emulation modelling: reconciling science and decision making …
Emulator: A low-order, computationally efficient model identified from an original large high fidelity model and then used to replace it in computationally intensive applications.
DM High fidelity Accuracy
Credibility Simplicity
DATA DRIVEN PROCESS BASED
DM
![Page 4: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/4.jpg)
EMO’s application tree
Model Emulation
MODEL DIAGNOSTIC
Data assimilation
DECISION MAKING
Model identification
Sensitivity analysis
Optimal planning
What-if analysis
Optimal control
[Castelletti et al. 2012a]
![Page 5: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/5.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
Non-dynamic emulator [Razavi et al. 2013]
![Page 6: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/6.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
N-DEMo
Non-dynamic emulator [Razavi et al. 2013]
![Page 7: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/7.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
N-DEMo
Non-dynamic emulator [Razavi et al. 2013]
![Page 8: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/8.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
Dynamic emulator [Castelletti et al. 2012a]
![Page 9: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/9.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
DEMo
Dynamic emulator
time
red
uc
ed
sta
te
[Castelletti et al. 2012a]
![Page 10: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/10.jpg)
Non-dynamic vs dynamic emulation
decision 1
de
cisi
on
2
objective 1
ob
jec
tive 2
time
sta
te
ext
driv
ers
time
HIGH FIDELITY MODEL
DEMo
Dynamic emulator
time
red
uc
ed
sta
te
[Castelletti et al. 2012a]
![Page 11: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/11.jpg)
How to build a Dynamic Emulator
Transform the state and input/decision vectors into lower dimension vectors through adoption of a suitable aggregation (PCA, SVD, etc)
2. Variable aggregation
Selection of the most relevant aggregated variables in explaining the model output (IVS, PMI, etc)
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo Design a sequence of simulation runs to construct a high dimension sample data-set.
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 12: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/12.jpg)
REAL TIME CONTROL OF MARINA BARRAGE
SINGAPORE
CASE STUDY
![Page 13: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/13.jpg)
Singapore’s 4 national taps strategy
Malaysia
Indonesia
0 100 km
0 10 km
Singapore Strait
Marina Reservoir
(source: URA)
The 4 TAPS [Kristiana et al., 2011] 1. Local catchments water
2. Imported water
3. Reclaimed water (NEWater)
4. Desalinated water
![Page 14: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/14.jpg)
Marina Barrage
Low tide High tide
Seepage
Pumps
Gates
Pipes
Actuators:
§ 7 pumps § 9 weirs § 2 bottom pipes
Water quantity objectives:
§ Water supply § Flood control § Energy usage
Water quality objectives:
§ Maintain low salinity
[Galelli et al. 2014]
SEA SEA
![Page 15: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/15.jpg)
The high fidelity model
2D view 3D view
barrage
cross-section
observation point
m0-1-2-3-4-5-6-7
The DELFT3D-FLOW hydrodynamic model calculates non-steady flow and transport phenomena (i.e., temperature and salinity conditions)
§ 5 states per cell = 5,500 state variables § Real-to-run time ratio 100:1
[Zijl and Twigt 2007]
![Page 16: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/16.jpg)
The real time control framework
DEFLT3D FLOW
DYNAMIC EMULATOR
MODEL PREDICTIVE CONTROL
- STATE - OBJECTIVES
RELEASE DECISIONS
MODEL REDUCTION
- OPTIMAL POLICY HYDROMETEO
DRIVERS
EVALUATION via SIMULATION
-1.71
2.54
12.47
2.06
2.12
6.81
Temp1
log(Lev) Algae
2 54
7
0666
Legend
6.2.45 10 6.3.84 10
7.14.26 107.4.01 10
size: Irr1
orientation: Sed
color: approachNSPCAbased
expertbased
PARETO Front
FAST SIMULATION
- REDUCED STATE - OBJECTIVES
- STREAMFLOW PREDICTIONS
- OBJECTIVES
STREAMFLOW FORECAST
(SOBEK)
RELEASE DECISION
GENERATOR
![Page 17: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/17.jpg)
Building a dynamic emulator of salinity @ the dam
Transform the state and input/decision vectors into lower dimension vectors through adoption of a suitable aggregation.
2. Variable aggregation
Selection of the most relevant aggregated variables in explaining the model output.
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo Design a sequence of simulation runs to construct a high dimension sample data-set.
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 18: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/18.jpg)
Building a dynamic emulator of salinity @ the dam
Transform the state and input/decision vectors into lower dimension vectors through adoption of a suitable aggregation.
2. Variable aggregation
Selection of the most relevant aggregated variables in explaining the model output.
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 19: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/19.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Selection of the most relevant aggregated variables in explaining the model output.
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 20: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/20.jpg)
Variable aggregation
Cluster 1 (Salinity): saline layer.
m0-1-2-3-4-5-6-7
![Page 21: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/21.jpg)
Variable aggregation
m0-1-2-3-4-5-6-7
Cluster 2 (Salinity): saline layer.
![Page 22: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/22.jpg)
Variable aggregation
m0-1-2-3-4-5-6-7
Cluster 3 (Salinity): saline layer.
![Page 23: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/23.jpg)
Variable aggregation
m0-1-2-3-4-5-6-7
Cluster 4 (Salinity): ‘buffer zone’ at a depth of 4 – 5 m, between the saline layer and the freshwater area.
![Page 24: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/24.jpg)
Variable aggregation
m0-1-2-3-4-5-6-7
Cluster 5 (Salinity): upper layers of the reservoir (max depth of about 4 m), with a uniform salinity of 3 ppt.
![Page 25: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/25.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Selection of the most relevant aggregated variables in explaining the model output.
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 26: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/26.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Recursive Variable Selection [Galelli and Castelletti, 2013a] = 32 to 1 state
3. Variable selection
Selection of a family of models for the emulator, calibration, validation, and physical interpretation.
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 27: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/27.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Recursive Variable Selection [Galelli and Castelletti, 2013a] = 32 to 1 state
3. Variable selection
Extremely Randomized Trees [Galelli and Castelletti, 2013b]
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 28: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/28.jpg)
Variable selection
Cluster 2 salinity
Salinity @ dam
Release from pipes
Groundwater seepage
CONTROL
EXTERNAL DRIVER
STATE OUTPUT
Seepage
Pumps
Gates
Pipes SEA
![Page 29: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/29.jpg)
Emulator calibration and validation
R2 – cross-validation (April – December
2009)
0.989
R2 – validation (January – December
2010)
0.970
![Page 30: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/30.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Recursive Variable Selection [Galelli and Castelletti, 2013a] = 32 to 1 state
3. Variable selection
Extremely Randomized Trees [Galelli and Castelletti, 2013b]
4. Emulator calib. & validation
MODEL REDUCTION
The dynamic emulator is used in the task is was designed for.
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 31: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/31.jpg)
Building a dynamic emulator of salinity @ the dam
Hierarchical Agglomerative Time Series Clustering [Magni et al., 2008] = 5,500 to 32 states
2. Variable aggregation
Recursive Variable Selection [Galelli and Castelletti, 2013a] = 32 to 1 state
3. Variable selection
Extremely Randomized Trees [Galelli and Castelletti, 2013b]
4. Emulator calib. & validation
MODEL REDUCTION
Model Predictive Control [Scattolini, 2007]
Model use
DEMo 300,000 samples by pseudo random sampling = 5,500 state variables
1. DOE and simulation runs
[Castelletti et al. 2012a]
![Page 32: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/32.jpg)
Real time control with and without quality target
Period: April 2009 – December 2010
Objective (minimize) Without wq With wq
Water deficit [Mm3/year] 75.04 74.81
Flood control [hours/year] 305.67 302.15
Energy usage [Mm3/year] 17.28 16.19
Min salinity [ppt] 9.95 5.63
Max salinity [ppt] 30.97 29.52
Mean salinity [ppt] 28.41 22.24
![Page 33: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/33.jpg)
Salinity simulated with DELTF3d Flow at the observation point (water column)
Obj.: water quantity Obj.: water quantity
Obj.: water quantity + quality Obj.: water quantity + quality
April – December 2009 January – December 2010
cross-section
observation point
Real time control with and without quality target
![Page 34: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/34.jpg)
Salinity simulated along the cross-section (dry period vs. wet period)
Obj.: water quantity
Distance from the barrage Distance from the barrage
Water intake Water intake
cross-section
observation point
Obj.: water quantity + quality
Real time control with and without quality target
![Page 35: Dynamic emulation modelling for the optimal operation of water systems: an overview](https://reader033.vdocuments.us/reader033/viewer/2022042701/55a203391a28ab4d268b4805/html5/thumbnails/35.jpg)
Conclusions
DEMo as a tool to put more science into decision-making, by …
… preserving the accuracy of the original high fidelity model
… providing some explanatory capability and thus credibility
… allowing to solve complex task such as real time control.