Power System Risk Scoring for Correlated Extreme Wind Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power system risk assessment methods fail to accurately consider the geographical distribution of strong winds and their impact on power system stability during extreme weather conditions, leading to inaccurate risk assessments.
Innovation Solution
A method involving deep feature mining that divides the power system into regions based on geographical location, constructs a correlation model for strong wind extreme weather, builds a sample set of scenarios, assigns operating conditions, and uses an extreme learning machine (ELM) with a hybrid kernel function to assess and output risk scores, providing auxiliary decision-making suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing risk assessment methods are used, then the assessment process is simple, but the assessment accuracy is low because geographical distribution of strong winds is not considered
Solution Approach 1:
The power system is divided into multiple regions based on geographical location and wind characteristics. Each region is assigned specific wind speed scenarios and correlation models, allowing localized accurate risk assessment while maintaining overall system comprehensiveness. This segmentation resolves the contradiction by enabling high accuracy through regional specialization without requiring complete reassessment of the entire system.
Solution Approach 2:
Different regions are assigned different wind speed correlation models and scenario sets based on their specific geographical characteristics. The risk assessment adapts local wind patterns, transmission line configurations, and operational conditions to each region, achieving high accuracy through localized modeling rather than uniform assessment across the entire power system.
2Measurement precision
If deep feature mining with multiple kernel functions is used, then the risk assessment accuracy is improved, but the computational complexity increases
Solution Approach 1:
Wind speed correlation models and scenario sample sets are constructed in advance based on historical data and geographical characteristics. The extreme learning machine is pre-trained with comprehensive feature sets including transmission line parameters, wind speed data, and operational conditions. This preliminary preparation enables fast real-time risk assessment without requiring intensive computational resources during actual operation.
Solution Approach 2:
The extreme learning machine uses kernel functions to create transformed feature representations of the input data. Instead of processing raw complex data directly, the system uses kernel mappings to work with transformed feature spaces, reducing computational complexity while maintaining assessment accuracy through efficient mathematical transformations.
3Loss of time
If real-time risk assessment is implemented, then the response time is reduced, but the data processing requirements increase
Solution Approach 1:
The system extracts only the most critical features for real-time assessment, including current wind speed measurements, recent transmission line status, and key operational parameters. By selecting and processing only essential data elements rather than complete historical datasets, the system achieves fast real-time risk assessment with reduced data processing requirements.
Solution Approach 2:
The extreme learning machine dynamically adjusts assessment parameters and thresholds based on current operational conditions and wind scenarios. The system changes evaluation criteria and risk thresholds according to the specific situation, enabling efficient real-time decision-making by focusing computational resources on the most relevant parameters rather than processing all data uniformly.
Data Source
AI summary
A method for risk assessment of a power system in extreme weather conditions considering deep feature mining for risk assessment of a power system. The risk assessment method includes: dividing the entire power system into regions based on geographical locations; combining historical wind speed data to construct a correlation model for strong wind extreme weather in multiple regions of the power system; constructing a strong wind scenario sample set for each region based on the correlation model; obtaining the probability of transmission line failure in the corresponding region under each strong wind scenario in the strong wind scenario sample set; randomly assigning a power system operating condition to each strong wind scenario in each region, and obtaining the operating risk value of the power system under the corresponding operating condition; constructing and training a risk assessment model; and using the model to provide a power system operating risk score assessment.