Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Plus Grants Program

University of Guelph

$12,500.00

Bayesian optimization for archimedes screw hydro generator model

FY 2015-16

Summary
Bluestreak Equipment, of Delhi, Ontario, is developing Archimedes screw hydro generators (ASGs) that could be utilized at thousands of low head (1-10 m) sites along waterways just in southern Ontario. Several hundred ASGs have been installed in Europe in the past decade, with more in development. ASGs are commercially competitive with other hydro turbines, with very low environmental impacts, including on fish. In the past three years, Bluestreak researched and developed their Archimedes screw generator technology, and successfully installed the first grid-connected Archimedes screw hydro plant in North America. They currently are commercializing their ASG systems, with a second ASG installation in process, and several more in various stages of planning. Bluestreak and Prof. David Lubitz (University of Guelph) have developed and validated a refined engineering model that can reliably predict the power output of a specified Archimedes screw system. The model can be used iteratively to optimize the IRR of a single Archimedes screw generator for a specific site, and is a key part of Bluestreak's business advantage in the microhydro field. In a recently completed Engage project, Dr. Graham Taylor's research team at the University of Guelph developed a technique that replaced the laborious manual tuning of parameters to find an optimal site-specific configuration with Bayesian Optimization-based solution. However, for legacy reasons, the ASG model itself was left as a complex series of Microsoft Excel spreadsheets with the optimizer implemented in Python. This Engage Plus proposes to continue the existing collaboration. In the first stage of the project, we will replace the Excel-based with a programmatic and unified implementation of the ASG model and optimizer. This will enable enhancements in the optimizer to be completed in the second stage, namely, 1) constraint-aware Bayesian optimization; 2) accelerating the bottleneck of the optimizer: the acquisition function; and 3) alternatives to the surrogate model based on neural networks instead of Gaussian Processes.
Program
Engage Plus Grants Program
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
486351-2015
Name nom
Taylor, Graham
Department département
Engineering, School of
Organization id
24
Institution établissement
University of Guelph
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2015
Competition year année de concours
2015
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
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
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
2715
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Optimization
Research subject fr
Optimisation
Partie
1
Nb partie
1
Application title
Bayesian optimization for archimedes screw hydro generator model
Keyword
NSERC
Application summary
Bluestreak Equipment, of Delhi, Ontario, is developing Archimedes screw hydro generators (ASGs) that could be utilized at thousands of low head (1-10 m) sites along waterways just in southern Ontario. Several hundred ASGs have been installed in Europe in the past decade, with more in development. ASGs are commercially competitive with other hydro turbines, with very low environmental impacts, including on fish. In the past three years, Bluestreak researched and developed their Archimedes screw generator technology, and successfully installed the first grid-connected Archimedes screw hydro plant in North America. They currently are commercializing their ASG systems, with a second ASG installation in process, and several more in various stages of planning. Bluestreak and Prof. David Lubitz (University of Guelph) have developed and validated a refined engineering model that can reliably predict the power output of a specified Archimedes screw system. The model can be used iteratively to optimize the IRR of a single Archimedes screw generator for a specific site, and is a key part of Bluestreak's business advantage in the microhydro field. In a recently completed Engage project, Dr. Graham Taylor's research team at the University of Guelph developed a technique that replaced the laborious manual tuning of parameters to find an optimal site-specific configuration with Bayesian Optimization-based solution. However, for legacy reasons, the ASG model itself was left as a complex series of Microsoft Excel spreadsheets with the optimizer implemented in Python. This Engage Plus proposes to continue the existing collaboration. In the first stage of the project, we will replace the Excel-based with a programmatic and unified implementation of the ASG model and optimizer. This will enable enhancements in the optimizer to be completed in the second stage, namely, 1) constraint-aware Bayesian optimization; 2) accelerating the bottleneck of the optimizer: the acquisition function; and 3) alternatives to the surrogate model based on neural networks instead of Gaussian Processes.
University of Guelph - $12,500 Grant (2015-16) | Canada Spends