About this Research Topic
In the operation, control, and planning of power systems, real-time and historical data have been employed to make credible decisions and yield reliable engineering judgment for numerous applications. Many efforts have been made to develop efficient and robust methods to produce data-augmented models for power systems of various scales. However, the decarbonization of the power grid with clean energy resources necessitates a complete reassessment of system operation, planning, and control. Inverter-based distributed energy resources (DERs, e.g., solar, wind, and battery energy storage systems) are expected to play a leading role during the massive transformation of grid decarbonization, requiring new or updated operational capabilities, system control and protection schemes, and design of market, financial, and regulatory practices.
Furthermore, rare events primarily driven by climate change have prompted system operators and planners to analyze and respond to low-probability risks associated with unforeseen scenarios more judiciously in an evolving energy landscape. Altogether, these factors make the boundary between “normal” and “abnormal” operating conditions blurry and complex, necessitating a new suite of data-driven, physically explainable models to efficiently capture uncertainty and hidden risks and handle the underlying complexity stemming from high-dimensional nonlinearity and stochasticity in power system data to ensure secure and stable operation and robust control, and make informed planning decisions. Fortunately, the emergence and rapid deployment of new types of sensors, such as phasor measurement units, smart meters, smart inverters, and wireless power line sensors provide abundant data enabling data-driven or learning-based applications.
To this end, this Research Topic collection is aimed at providing researchers a venue to innovate the operation, control, and planning of electricity infrastructure, while exploring the tradeoffs between accuracy and tractability in solving today’s most pressing problems that exclusively leverage power system data.
We welcome submissions that include, but are not limited to, the following sub-topics:
• Data-driven modeling of power grids, renewable energy, and loads
• Data-driven power system monitoring and situational awareness
• Data-driven operations and planning for a resilient power grid under a changing climate
• Scalable machine learning techniques for smart grids
• Physics-informed machine learning techniques for smart grids
• High-performance computing and big data analytics for large-scale power systems
• Data-guided robust control design in power systems
• Data science and quantum computation for power system applications
• Statistical machine learning and Bayesian methods for stochastic optimization in power systems
• Online learning and control of power system dynamics
• Decision making under risk and uncertainty
• Data-driven composite reliability assessment
• Computationally efficient risk assessment under rare (extreme) events
• White-/gray-/black-box optimization for power system applications
• Plug-and-play optimization and control in networked microgrids
• Chance-constrained optimization for large-scale power system problems, including stochastic economic dispatch, unit commitment, etc.
• Application-oriented and regularized learning for power systems
• Distributionally robust approaches for unit commitment, expansion planning, etc.
Furthermore, rare events primarily driven by climate change have prompted system operators and planners to analyze and respond to low-probability risks associated with unforeseen scenarios more judiciously in an evolving energy landscape. Altogether, these factors make the boundary between “normal” and “abnormal” operating conditions blurry and complex, necessitating a new suite of data-driven, physically explainable models to efficiently capture uncertainty and hidden risks and handle the underlying complexity stemming from high-dimensional nonlinearity and stochasticity in power system data to ensure secure and stable operation and robust control, and make informed planning decisions. Fortunately, the emergence and rapid deployment of new types of sensors, such as phasor measurement units, smart meters, smart inverters, and wireless power line sensors provide abundant data enabling data-driven or learning-based applications.
To this end, this Research Topic collection is aimed at providing researchers a venue to innovate the operation, control, and planning of electricity infrastructure, while exploring the tradeoffs between accuracy and tractability in solving today’s most pressing problems that exclusively leverage power system data.
We welcome submissions that include, but are not limited to, the following sub-topics:
• Data-driven modeling of power grids, renewable energy, and loads
• Data-driven power system monitoring and situational awareness
• Data-driven operations and planning for a resilient power grid under a changing climate
• Scalable machine learning techniques for smart grids
• Physics-informed machine learning techniques for smart grids
• High-performance computing and big data analytics for large-scale power systems
• Data-guided robust control design in power systems
• Data science and quantum computation for power system applications
• Statistical machine learning and Bayesian methods for stochastic optimization in power systems
• Online learning and control of power system dynamics
• Decision making under risk and uncertainty
• Data-driven composite reliability assessment
• Computationally efficient risk assessment under rare (extreme) events
• White-/gray-/black-box optimization for power system applications
• Plug-and-play optimization and control in networked microgrids
• Chance-constrained optimization for large-scale power system problems, including stochastic economic dispatch, unit commitment, etc.
• Application-oriented and regularized learning for power systems
• Distributionally robust approaches for unit commitment, expansion planning, etc.
Keywords: Data-driven methods, power systems, learning, artificial intelligence, computing, optimization, decision making, data analytics, large-scale data assimilation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
