Power Grid Planning Evaluation With Hybrid Weighting and Regression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional power grid assessment methods rely on subjective judgments, leading to biased and uncertain results due to the lack of an objective weighting method, which affects the accuracy and reliability of distribution network planning and design.
Innovation Solution
A progressive power grid planning evaluation method based on a combination assessment theory, utilizing a combination weighting method, similarity theory assessment, and nonparametric regression, along with a deep learning model using LSTM networks and attention mechanisms, to systematically assess power grid performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If traditional subjective weighting methods are used for assessment indexes, then the assessment process is simple to implement, but the assessment result accuracy and reliability deteriorate due to subjective bias and uncertainty
Solution Approach 1:
The patent combines subjective weighting methods (AHP) with objective weighting methods (entropy method, CRITIC method) to create a comprehensive weighting system. This merging allows the assessment to benefit from both the interpretability of subjective methods and the objectivity of data-driven methods, thereby improving assessment accuracy while maintaining implementability through a structured hybrid approach.
Solution Approach 2:
The patent transforms the weighting parameters from purely subjective expert judgments to a hybrid set that includes both subjective importance weights and objective data-based weights. This parameter change introduces mathematical objective criteria (entropy, CRITIC) alongside subjective inputs, resolving the contradiction by making the assessment more accurate without completely abandoning the simplicity of expert-based methods.
2Measurement precision
If comprehensive assessment index systems are established to accurately measure distribution network performance, then the assessment accuracy improves, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent segments the comprehensive assessment system into distinct functional modules: data collection module, preprocessing module (with cleaning, normalization, dimensionless processing), weighting calculation module (subjective and objective methods), and evaluation module. This segmentation manages complexity by organizing the comprehensive assessment process into manageable, independent components that can be implemented and maintained separately.
Solution Approach 2:
The patent introduces intermediate processing steps including data normalization, dimensionless processing, and multiple weighting calculation layers as mediators between raw data and final assessment results. These intermediaries transform complex, heterogeneous data into standardized formats suitable for comprehensive evaluation, thereby enabling accurate measurement without being overwhelmed by raw system complexity.
3Reliability
If multiple weighting methods are combined to reduce subjective bias, then the assessment reliability improves, but the calculation complexity and time consumption increase
Solution Approach 1:
The patent performs preliminary data preprocessing including cleaning, normalization, and dimensionless processing before applying the multiple weighting methods. This preliminary action prepares the data in advance, reducing the computational burden during the actual weighting calculations and thereby minimizing time loss while maintaining the reliability benefits of multiple methods.
Solution Approach 2:
The patent implements a hierarchical weighting structure where subjective and objective weights are calculated separately and then integrated, rather than applying all possible weighting methods simultaneously. This partial action approach achieves sufficient reliability improvement without the excessive computational overhead of evaluating every possible weighting combination, thus balancing reliability with time efficiency.
Data Source
AI summary
The present invention discloses a progressive power grid planning evaluation method and system based on a combination assessment theory, and relates to the technical field of power grid assessment and optimization. The method includes: correcting a weight of an obtained index by using a combination weighting method; obtaining an assessed value based on a similarity theory assessment method; standardizing an index by dimensionless processing; and performing evaluation based on nonparametric regression. The present invention ensures objectivity and fairness of an assessment result and the efficiency and the accuracy of assessment are improved. The present invention may be adaptively adjusted, making the assessment result closer to reality.