Development of Cable Tunnel Monitoring System Based on ACO Optimization Neural Network in Smart Grid

• Published in: International Symposium on Autonomous Systems (Online) pp. 1 - 6
• Main Authors: Wang, Shuo, Dong, Liwen, Lang, Yaoming, Zhang, Mingde, Li, Zhihua, Guo, Fanghong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.05.2025
• Subjects: Ant Colony Optimization; cable tunnel; comprehensive environmental monitoring; Computational modeling; Data acquisition; Environmental monitoring; Geographic information systems; Neural networks; Power system stability; Safety; Smart grids; Stability analysis; Thermal stability
• ISSN: 2996-3850
• DOI: 10.1109/ICAISISAS64483.2025.11052186

With the accelerated urbanization process and escalating demand for electrical energy, the operational safety and stability of cable tunnels have emerged as critical components in modern power infrastructure systems. This study presents an innovative multi-modal monitoring system featuring a hierarchical distributed architecture that establishes a closed-loop framework integrating real-time data acquisition with intelligent analytical applications. The proposed system employs an array of advanced detection technologies, including high-precision sensor networks, distributed fiber-optic temperature sensing (DTS), and adaptive wireless transmission protocols, to achieve comprehensive environmental monitoring of tunnel structures. A novel hybrid algorithm combining Back Propagation (BP) neural networks with Ant Colony Optimization (ACO) metaheuristics has been developed to synergistically enhance fault prediction accuracy while optimizing computational efficiency. The integration of 3D/Building Information Modeling (BIM) visualization techniques with Geographic Information Systems (GIS) spatial analysis enables dynamic condition mapping and data-driven decision support through spatiotemporal modeling of tunnel parameters. This research advances intelligent monitoring methodologies for underground utilities and offers practical insights for next-generation smart grid development.