Automatic Region-Based Layout Optimization of Substation Wiring Diagrams Via Improved Genetic Algorithms

This paper proposes an automatic region-based layout optimization method for substation main wiring diagrams using a improved genetic algorithm. The method addresses the problems of low space utilization and rigid region division caused by template-based layouts. A two-segment chromosome structure i...

Full description

Saved in:
Bibliographic Details
Published in:2025 8th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) pp. 237 - 241
Main Authors: Fan, Qing, Liu, Junyi, Ren, Hao, Qin, Jun, Xu, Xiaofeng, Shen, Zeliang, Peng, Cong
Format: Conference Proceeding
Language:English
Published: IEEE 09.05.2025
Subjects:
Biological cells
Genetic algorithms
graph-structured constraints
improved genetic algorithm
Layout
layout optimization
Software engineering
Stability analysis
substation main wiring diagrams
Substations
Transformers
two-segment chromosome
Voltage
Wiring
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an automatic region-based layout optimization method for substation main wiring diagrams using a improved genetic algorithm. The method addresses the problems of low space utilization and rigid region division caused by template-based layouts. A two-segment chromosome structure is designed to encode both region assignment and interval ordering. The algorithm includes repair mechanisms and enhanced crossover and mutation operations to improve search efficiency and solution stability. In the layout modeling phase, interval units are abstracted as rectangular blocks to enable unified spatial representation. A set of graph-structured constraints, including voltage isolation, region boundary rules, and transformer area merging logic, are incorporated into the objective function as penalty terms. A case study on a 220kV substation shows that the proposed method results in better-balanced occupancy across regions and a more compact and readable layout. Experimental results demonstrate improvements of 11.6 percent in optimal performance and 24.2 percent in average performance compared to the standard genetic algorithm. The method proves effective for handling constrained and dynamically changing layout tasks in intelligent substation design.
DOI:10.1109/AEMCSE65292.2025.11042402