Case-Based Power Grid Control for Real-Time State Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional power grid operation methods, such as the N-1 criterion and predefined Special Protection Schemes, are inadequate for predicting and addressing unforeseen failures and cascading events, especially under real-time conditions, due to their inflexibility and limited predictive capabilities.
Innovation Solution
A method utilizing case-based reasoning to identify critical states in a power grid by comparing current conditions to stored cases, allowing for the automatic or manual execution of switching operations to rectify issues, and continuously updating a case base through simulations and unsupervised learning to improve predictive accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If predefined Special Protection Schemes are used to avoid power failures, then power grid reliability is improved, but the system becomes inflexible and requires large reserves which are complex and expensive
Solution Approach 1:
The system transitions from static predefined protection schemes to dynamic adaptive protection by continuously monitoring grid state and selecting cases based on real-time conditions. The case base allows flexible selection of appropriate responses without requiring large fixed reserves, as the system adapts to actual grid states rather than preparing for all possible scenarios in advance.
Solution Approach 2:
The system changes the operational parameters from fixed predefined actions to variable case-based responses. By storing multiple cases with different grid states and their corresponding successful resolutions, the system can select the appropriate parameter set (switching operations, generator adjustments) based on current conditions, eliminating the need for large constant reserves.
2Reliability
If offline simulations are used to determine parameters for power grid, then N-1 and N-2 scenarios are covered, but real-time prediction and fault elimination capabilities are insufficient
Solution Approach 1:
The system performs preliminary actions by pre-storing successful case resolutions in a case base before real-time incidents occur. During operation, the system quickly retrieves and applies pre-validated solutions rather than performing complex simulations in real-time, thus maintaining both comprehensive scenario coverage and rapid response capability.
Solution Approach 2:
The system creates copies of successful past resolutions and stores them in the case base. Instead of re-simulating scenarios in real-time, the system copies and applies proven solutions from the case base that match current grid states, enabling fast real-time response while maintaining the thoroughness of offline simulation validation.
3Measurement precision
If the case base is continuously expanded through simulations and learning, then predictive accuracy is improved, but data processing requirements increase
Solution Approach 1:
The system performs data processing and case validation in advance through offline simulations before adding cases to the case base. This preliminary processing ensures that only validated, accurate cases are stored, improving predictive accuracy without requiring excessive real-time computational resources. The case base grows with pre-processed, high-quality data.
Data Source
AI summary
The method involves detecting (S101) a state of the power system. One of the case base is determined (S102) by comparing the detected state from the cases with the case base comprised with state descriptions. The determined case to recover the state switching action for the network element to correct the detected state of power system is instructed (S103). The indicated switching action is instructed by displaying the specified switching action by display device for user and/or automatically executing the specified switching operation by switching device for controlling power system. Independent claims are included for the following: (1) computer program product for operating network elements; and (2) device for operating network elements.