Two-step Oscillation Source Locator for Power Grids
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods lack accuracy in identifying the source of forced oscillations in power systems, which are exacerbated by the integration of renewable energy sources and variable loads, posing a risk to system stability and potentially leading to power outages.
Innovation Solution
A two-step approach utilizing machine learning models to initially detect a rough geographical location of the oscillation source on the power grid, followed by an optimization model to refine and pinpoint the specific component causing the oscillation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional oscillation detection methods are used, then oscillation occurrence can be detected, but source identification accuracy deteriorates due to the large scale and complexity of power systems
Solution Approach 1:
The patent divides the power system into multiple predefined regions, each containing a subset of oscillation-prone components. This segmentation allows the system to focus analysis on specific regions rather than evaluating all components system-wide, thereby improving source identification accuracy while managing the complexity of large-scale power systems.
Solution Approach 2:
The patent introduces an intermediary classification system that first identifies candidate regions before pinpointing specific components. This two-stage approach uses region-level analysis as an intermediary step, filtering down from broad geographic areas to specific oscillation sources, which resolves the contradiction between system scale and identification precision.
2Reliability
If comprehensive component analysis is performed across the entire power system, then source identification completeness improves, but computational time and resources worsen
Solution Approach 1:
The patent performs preliminary classification of the power system into predefined regions containing oscillation-prone components before actual oscillation detection occurs. This preliminary organization enables rapid filtering and candidate elimination during real-time operation, ensuring comprehensive coverage of potential sources while minimizing computational time through pre-established regional structures.
Solution Approach 2:
The patent focuses analysis on specific predefined regions containing oscillation-prone components rather than uniformly analyzing all system components. This selective partial action concentrates computational resources on high-probability areas, maintaining identification completeness for oscillation sources while reducing overall computational burden by excluding non-prone components.
3Measurement precision
If detailed component-level monitoring is implemented, then oscillation source detection precision improves, but system complexity and measurement requirements worsen
Solution Approach 1:
The patent applies different levels of monitoring detail to different system regions based on their oscillation propensity. Predefined regions containing oscillation-prone components receive detailed component-level monitoring, while other areas use coarser region-level monitoring. This local differentiation achieves high detection precision where needed while avoiding unnecessary complexity in low-risk areas.
Solution Approach 2:
The patent segments the monitoring system into region-level and component-level monitoring layers. This segmentation allows detailed measurements to be applied only to specific components within predefined oscillation-prone regions, rather than implementing uniform detailed monitoring across the entire system, thereby reducing overall system complexity while maintaining high detection precision where required.
Data Source
AI summary
Provided is a system and method for detecting source(s) of oscillation on a power grid. In one example, the method may include receiving measurements from one or more sensors on a power grid, the measurements including data of an oscillation within the power grid, determining, via execution of one or more machine learning model, a candidate set of power system components disposed on the power grid that are candidates for being the source(s) of the oscillation, identifying, via execution of an optimization model, a component from among the candidate set of power system components which is the source (e.g., location, controller type, and/or asset type) of the oscillation, and displaying, via a user interface, information about the identified component.