Research Topic

Data-Driven Approaches for Power System Analysis

About this Research Topic

This Research Topic has been realized in collaboration with Dr. Zhifang Yang, Assistant Professor at Chongqing University in China.

Traditional power system analysis is conducted based on analytical models of power grids and electrical elements. However, this model-driven approach occasionally encounters difficulties facing the increasing scale of the model and unclear power system topology and demands. For example, traditional probabilistic analysis involves repeated power flow calculations and optimization solutions over multiple (tens of thousands) instances in time. Such repeated computation becomes a bottleneck for practical and fast applications in power industries given the increase in sub-system and device complexity. Moreover, in certain regimes like distribution power networks, new optimization problems are being proposed which need to incorporate incomplete information about system state, topology and control logic. In either instance, repeated model-driven power system analysis would be difficult to scale up.

The data-driven approach provides a new way to solve these challenges. While model-driven approaches consider the power system to be a “white box”, data-driven approaches can be either “grey box” or even “black box”. Using partial system knowledge and power flow physics are instances of “grey box”, and plug and play based operations are instances of “black box”. Data-driven methods have the potential to efficiently combine the extensive measured data with prior knowledge and historical data for actionable outputs in various scenarios. On one hand, this can lead to novel ways for event detection, localization and modeling in power grids. On the other, it can lead to reduced search spaces and good warm start for improved convergence of traditional optimization problems in power grids.

This Research Topic serves as a forum to bring together active researchers worldwide to share their recent advances in this exciting area. Specific topics of interest for this Research Topic include but are not limited to:
- History and survey of data-driven power system analysis
- Data-driven forecasting (renewable energy sources, electrical vehicle, etc.)
- Data-driven state estimation approaches
- Data-driven power system analysis
- Data-driven optimization and control in power systems.
- Perspectives on the future power system analysis based on data-driven approaches


Keywords: Power system analysis, Data-driven model


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.

This Research Topic has been realized in collaboration with Dr. Zhifang Yang, Assistant Professor at Chongqing University in China.

Traditional power system analysis is conducted based on analytical models of power grids and electrical elements. However, this model-driven approach occasionally encounters difficulties facing the increasing scale of the model and unclear power system topology and demands. For example, traditional probabilistic analysis involves repeated power flow calculations and optimization solutions over multiple (tens of thousands) instances in time. Such repeated computation becomes a bottleneck for practical and fast applications in power industries given the increase in sub-system and device complexity. Moreover, in certain regimes like distribution power networks, new optimization problems are being proposed which need to incorporate incomplete information about system state, topology and control logic. In either instance, repeated model-driven power system analysis would be difficult to scale up.

The data-driven approach provides a new way to solve these challenges. While model-driven approaches consider the power system to be a “white box”, data-driven approaches can be either “grey box” or even “black box”. Using partial system knowledge and power flow physics are instances of “grey box”, and plug and play based operations are instances of “black box”. Data-driven methods have the potential to efficiently combine the extensive measured data with prior knowledge and historical data for actionable outputs in various scenarios. On one hand, this can lead to novel ways for event detection, localization and modeling in power grids. On the other, it can lead to reduced search spaces and good warm start for improved convergence of traditional optimization problems in power grids.

This Research Topic serves as a forum to bring together active researchers worldwide to share their recent advances in this exciting area. Specific topics of interest for this Research Topic include but are not limited to:
- History and survey of data-driven power system analysis
- Data-driven forecasting (renewable energy sources, electrical vehicle, etc.)
- Data-driven state estimation approaches
- Data-driven power system analysis
- Data-driven optimization and control in power systems.
- Perspectives on the future power system analysis based on data-driven approaches


Keywords: Power system analysis, Data-driven model


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.

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

08 April 2020 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

08 April 2020 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..