Genetic Algorithm Restoration Switching Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for multi-layer restoration in electrical power distribution networks face challenges in efficiently processing a large number of variables and achieving computational efficiency, while avoiding network violations and minimizing switching operations during fault isolation and load restoration.

Innovation Solution

A genetic algorithm-based method is employed, utilizing a chromosome architecture that represents actions for normally open tie switches, with a fitness function to evaluate candidate network configurations and ensure validity, aiming to minimize switching operations and unserved loads, and incorporating a Reactive Tabu Search to optimize the restoration process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multi-layer restoration switching analysis is performed to restore power to out-of-service load areas, then power restoration capability is improved, but computational complexity and processing time increase significantly

Engineering Contradiction:
Improvepower restoration capabilityVSAvoidcomputational processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The restoration problem is segmented into multiple layers (first layer, second layer, third layer, etc.) based on the topological distance of restoration switches from the fault location. First layer switches are directly connected to the faulted area, second layer switches are one step further, and so on. This segmentation allows the system to process restoration options in a structured sequence, evaluating closer switches before more distant ones, thereby reducing the overall computational burden while maintaining comprehensive restoration capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-identifying and categorizing all potential restoration switches into different layers before actual restoration execution. The chromosome architecture pre-defines action options for each tie switch (remain open, close, or swap with a normally closed switch). By preparing this structured framework in advance, the system eliminates the need for real-time complex calculations during actual restoration events, significantly reducing computational processing time while ensuring reliable power restoration.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the number of normally open tie switches and normally closed switches is increased to provide more restoration options, then restoration flexibility is improved, but the complexity of determining optimal switching sequences increases

Engineering Contradiction:
Improverestoration flexibilityVSAvoidswitching sequence determination complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system employs a dynamic genetic algorithm that adaptively evolves switching sequences through generations. Chromosomes represent candidate solutions with genes corresponding to tie switches and their actions. Through selection, crossover, and mutation operations, the algorithm dynamically searches the solution space, adapting to the specific network configuration and fault scenario. This dynamic approach handles the complexity of multiple switches and restoration options more efficiently than static optimization methods.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The fitness function evaluates candidate solutions using multiple parameters including the number of switching operations, radiality constraint satisfaction, and load restoration effectiveness. By changing and optimizing these parameters through the genetic algorithm, the system finds optimal switching sequences that balance restoration flexibility with operational constraints. The chromosome architecture encodes different parameter combinations, allowing systematic exploration of the solution space despite the large number of switches involved.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If comprehensive validation criteria are applied to ensure network configuration validity, then network violation avoidance is improved, but computational overhead increases

Engineering Contradiction:
Improvenetwork violation avoidanceVSAvoidcomputational overhead
Core Design Contradiction:
ReliabilityVSUse of energy by stationary object

Solution Approach 1:

The system performs preliminary validation by incorporating radiality constraints directly into the chromosome architecture and fitness function evaluation. Network configuration validity is checked against pre-defined criteria (radiality, current violations, switching operation limits) during the genetic algorithm's selection and evaluation phases. By establishing these validation rules in advance and integrating them into the optimization framework, the system ensures network violation avoidance without requiring separate, computationally intensive validation steps after solution generation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2507750B1Restoration switching analysis with genetic algorithm
Publication Date: 2020.04.29 ABB POWER GRIDS SWITZERLAND AG
  • EP2507750B1 patent drawingFigure 1
  • EP2507750B1 patent drawingFigure 2
  • EP2507750B1 patent drawingFigure 3

AI summary

A method for generating switching plans to restore power to out-of-service areas after fault isolation through back feeding. A chromosome architecture is defined to create chromosomes representing candidate post-restoration systems. The chromosomes are evaluated are repeatedly genetically altered until an acceptable solution is identified. The solution identifies a plurality of switching operations that back feed power to the out-of-service areas in the most optimal manner.