Grant: Discovery Grants Program - Individual
University of Alberta
$36,000.00
Reliable Power System Operations via Data-Driven Modeling and Optimization
EF 2024-25
Résumé
Introduction: Decarbonization and electrification present unprecedented challenges to power system operators and utilities. In the daily operations, they must adapt to operate numerous uncertain, stochastic and distributed resources such as solar PVs and electric vehicles in a timely and reliable manner. Through the lens of data-driven techniques, this project will bring transformative changes by developing physics-consistent optimization and optimal control frameworks using a variety of available data sources such as phasor measurement units (PMUs), electricity markets and forecasts. The broader impacts of the project include various new courses development on data science and machine learning for electric energy systems, as well as research and outreach opportunities for communities interested in sustainable energy, smart grids, and electric vehicles.
Objectives: This project simultaneously addresses several technical challenges in ensuring reliable operation of power grids with the integration of a large number of emerging distributed energy resources and electric power consumers. By identifying the active role taken by energy system data on improving the situational awareness and resilience of power grids, the program will develop data-driven tools to better quantify and involve uncertainty estimation of intermittent energy resources and stochastic load. The program will also design data-driven tools consistent with model-based approaches which can improve the reliability of power systems under stochastic and distributed generations. These objectives will help achieve my long-term vision on leveraging data from heterogeneous sources of power systems to enhance reliability and efficiency of a sustainable power system.
Novelty: For the underlying nonlinear, high-dimensional systems, the proposed paradigm does not require the full dynamics or parameters in processes such as swing equations, power flow equations and thermodynamics. This project aims to devise a modular data-driven approach to identify the effective representation tailored for control and optimization. The resulting data-driven controller will follow a fully differentiable model design while training the surrogate dynamical models, so that the Pontryagin's maximum principle and optimality conditions can be explicitly incorporated to guide the solution process of optimal decisions in an iterative way. The proposed scheme provides a holistic combination of physical modeling and machine learning.
Significance: This program will investigate how data-driven schemes can enhance the efficiency of power transmission and distribution, improve grid reliability, and elevate the overall quality of power supplied to Canadian electricity energy customers in the next 20 years. Successful application of the proposed project will allow power system operators and utilities to be equipped with more advanced and holistic tools for addressing operation needs and resolving climate change threats.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2024-05015
Name nom
Chen, Yize
Department département
Electrical and Computer Engineering
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
36000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
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
2501
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Power systems
Research subject fr
Réseaux électriques
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Reliable Power System Operations via Data-Driven Modeling and Optimization
Keywords
power system operations; power system control; machine learning; data-driven control; optimization; stochastic optimization; energy systems; smart grids; optimization under uncertainty; load management
Application summary
Introduction: Decarbonization and electrification present unprecedented challenges to power system operators and utilities. In the daily operations, they must adapt to operate numerous uncertain, stochastic and distributed resources such as solar PVs and electric vehicles in a timely and reliable manner. Through the lens of data-driven techniques, this project will bring transformative changes by developing physics-consistent optimization and optimal control frameworks using a variety of available data sources such as phasor measurement units (PMUs), electricity markets and forecasts. The broader impacts of the project include various new courses development on data science and machine learning for electric energy systems, as well as research and outreach opportunities for communities interested in sustainable energy, smart grids, and electric vehicles.
Objectives: This project simultaneously addresses several technical challenges in ensuring reliable operation of power grids with the integration of a large number of emerging distributed energy resources and electric power consumers. By identifying the active role taken by energy system data on improving the situational awareness and resilience of power grids, the program will develop data-driven tools to better quantify and involve uncertainty estimation of intermittent energy resources and stochastic load. The program will also design data-driven tools consistent with model-based approaches which can improve the reliability of power systems under stochastic and distributed generations. These objectives will help achieve my long-term vision on leveraging data from heterogeneous sources of power systems to enhance reliability and efficiency of a sustainable power system.
Novelty: For the underlying nonlinear, high-dimensional systems, the proposed paradigm does not require the full dynamics or parameters in processes such as swing equations, power flow equations and thermodynamics. This project aims to devise a modular data-driven approach to identify the effective representation tailored for control and optimization. The resulting data-driven controller will follow a fully differentiable model design while training the surrogate dynamical models, so that the Pontryagin's maximum principle and optimality conditions can be explicitly incorporated to guide the solution process of optimal decisions in an iterative way. The proposed scheme provides a holistic combination of physical modeling and machine learning.
Significance: This program will investigate how data-driven schemes can enhance the efficiency of power transmission and distribution, improve grid reliability, and elevate the overall quality of power supplied to Canadian electricity energy customers in the next 20 years. Successful application of the proposed project will allow power system operators and utilities to be equipped with more advanced and holistic tools for addressing operation needs and resolving climate change threats.