AI-Guided Security-Constrained Power Flow for Grid Contingencies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of modern power systems, driven by high penetration of renewable energy sources, poses challenges for determining optimal operation states and power grid extensions, requiring advanced control algorithms and optimization solutions to ensure safe, reliable, and efficient operation.
Innovation Solution
A method utilizing an artificial intelligence module to estimate power flows and reduce the complexity of the security-constrained optimal power flow problem, transforming it into a simpler, computationally less expensive optimization problem, thereby shifting computational effort from real-time operation to a training phase and enabling semi-autonomous or fully autonomous power grid control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If classical analytical approaches are used for short time operation, then the method is simple and computationally efficient, but it cannot deal with the increasing complexity of the power system with high penetration of renewable energy sources
Solution Approach 1:
The patent segments the complex SC-OPF problem into two parts: (1) an AI module that estimates power flows and identifies critical constraints, and (2) a simplified optimization solver that only handles the reduced problem. This segmentation allows the system to handle complex scenarios by preprocessing the complexity through AI, while keeping the actual optimization computationally tractable.
Solution Approach 2:
The AI module performs preliminary action by estimating power flows, identifying binding constraints, and reducing the problem space before the optimization solver is applied. This preliminary processing transforms the complex SC-OPF problem into a simplified form that can be solved efficiently, thereby handling complex scenarios without requiring complex real-time algorithms.
2Reliability
If the power grid size and number of scenarios increase, then the system becomes more comprehensive and handles more contingencies, but the computational effort increases significantly
Solution Approach 1:
The patent extracts the computationally intensive parts of the SC-OPF problem (power flow estimation and constraint identification) and handles them through AI-based preliminary processing. This extraction leaves only the essential optimization problem to be solved, thereby maintaining comprehensive scenario coverage while significantly reducing computational time.
Solution Approach 2:
The AI module changes the parameters of the optimization problem by estimating power flows and identifying which constraints are actually binding. This parameter transformation converts a high-dimensional complex optimization problem into a lower-dimensional simplified problem, reducing computational effort while maintaining reliability across multiple contingencies.
3Reliability
If deterministic analytical approaches are used, then the operation is secure and reliable, but decisions are based on simplified physical models and experience rather than optimal solutions
Solution Approach 1:
The AI module acts as an intermediary between the complex power system scenarios and the optimization solver. It processes the input data, estimates power flows, and identifies critical constraints, thereby bridging the gap between deterministic security requirements and optimal operation determination. This intermediary processing enables both security and accuracy by transforming complex scenarios into structured optimization problems.
Data Source
AI summary
A method can be used to determine a security-constrained optimal power flow (SC-OPF) of a power grid. Input data associated with a power grid scenario is obtained. The input data defines a security-constrained optimization problem (SC-OPF problem). The power grid scenario includes a power grid structure, a power demand and a generator capability and/or cost. Power flows in branches of the power grid that are equal to or greater than limits for a contingency associated with the power grid scenario are estimated based on the obtained input data by an AI. A modified optimization problem which is smaller than the SC-OPF problem is solved based on the estimated power flows.