Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Plus Grants Program

McGill University

$12,500.00

Surrogate Models for Maximizing Net Present Value of Renewable Energy Sources

FY 2016-17

Summary
Hydro-Québec supplies electricity to customers in remote off-grid locations by operating diesel plants. Costand environmental concerns motivate the consideration of using several types of renewable energy sources. Theoptimal combination of different energy sources can be determined by solving an optimization problem tomaximize the net present value (NPV) generated by the off-grid electrical network over its lifetime. Thisrequires numerical simulations that are associated with high computational cost and discontinuities in bothfunctions and variables, which does not allow the computation of gradients. IREQ tried to use conventionaltechniques to address these challenges without success. An Engage grant was awarded to develop andimplement a surrogate-assisted, derivative-free optimization framework to alleviate these challenges. Surrogatemodels based on Polynomial Response Surfaces, Kernel Smoothing and Radial Basis Functions weredeveloped exploiting our knowledge of the problem and its structure. Several configurations of these modelswere tested to identify the most promising strategies and model parameters. The surrogate models were alsointegrated with a particular class of derivative-free optimization algorithms termed Mesh-Adaptive DirectSearch (MADS). The obtained results demonstrated the viability and usefulness of the surrogate-assistedoptimization approach: their predictive capability was excellent while accelerating the optimizationconvergence. The research objectives of the Engage Plus project include: i) compute NPV by taking intoaccount key parameters of the electrical network and interactions among different types (not captured in currentmodel) and ii) consider ensembles of surrogate models composed of different types and hyper-parameters,aggregated into a more robust and accurate surrogate model. The outcome of this research will provideHydro-Québec with a powerful tool for off-grid network optimization that can consider renewable energysources to offer economically viable, robust and environmentally benign energy solutions for isolatedcommunities.
Program
Engage Plus Grants Program
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
498903-2016
Name nom
Kokkolaras, Michael
Department département
Mechanical Engineering
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
12500
Program id
EGP2
Program name en
Engage Plus Grants Program
Program name fr
Programme de subvention d'engagement partenarial Plus
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
304
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Electrical energy
Area of application fr
Énergie électrique
Research subject code
1701
Research subject group en
Design and manufacturing
Research subject group fr
Conception et fabrication
Research subject en
Engineering design
Research subject fr
Conception technique
Partie
1
Nb partie
1
Application title
Surrogate Models for Maximizing Net Present Value of Renewable Energy Sources
Keyword
NSERC
Application summary
Hydro-Québec supplies electricity to customers in remote off-grid locations by operating diesel plants. Costand environmental concerns motivate the consideration of using several types of renewable energy sources. Theoptimal combination of different energy sources can be determined by solving an optimization problem tomaximize the net present value (NPV) generated by the off-grid electrical network over its lifetime. Thisrequires numerical simulations that are associated with high computational cost and discontinuities in bothfunctions and variables, which does not allow the computation of gradients. IREQ tried to use conventionaltechniques to address these challenges without success. An Engage grant was awarded to develop andimplement a surrogate-assisted, derivative-free optimization framework to alleviate these challenges. Surrogatemodels based on Polynomial Response Surfaces, Kernel Smoothing and Radial Basis Functions weredeveloped exploiting our knowledge of the problem and its structure. Several configurations of these modelswere tested to identify the most promising strategies and model parameters. The surrogate models were alsointegrated with a particular class of derivative-free optimization algorithms termed Mesh-Adaptive DirectSearch (MADS). The obtained results demonstrated the viability and usefulness of the surrogate-assistedoptimization approach: their predictive capability was excellent while accelerating the optimizationconvergence. The research objectives of the Engage Plus project include: i) compute NPV by taking intoaccount key parameters of the electrical network and interactions among different types (not captured in currentmodel) and ii) consider ensembles of surrogate models composed of different types and hyper-parameters,aggregated into a more robust and accurate surrogate model. The outcome of this research will provideHydro-Québec with a powerful tool for off-grid network optimization that can consider renewable energysources to offer economically viable, robust and environmentally benign energy solutions for isolatedcommunities.