Self-Organizing Swarm Intelligence for Real-Time Network Fault Localization

DOI

10.2991/978-94-6239-713-2_34How to use a DOI?

Keywords

network communications; multiagent framework; network fault maintenance; swarm intelligence

Abstract

Large-scale networks are expanding and becoming increasingly heterogeneous and dynamic. Localizing faults quickly and accurately is of the highest importance for network operators. While centralized monitoring systems have been effective in many deployments, they face scalability and latency challenges in highly dynamic and large-scale environments and require human intervention for reconfiguration when network conditions change. This paper proposes a decentralized swarm-intelligence based system that can improves fault localization accuracy by 12.3% while decreasing detection latency by 35–50% over traditional centralized rule-based and machine learning approaches. In this work, we target fault localization accuracy >90% and detection latency <5 seconds in networks up to 300 nodes. The approach is modeled after collective behavior observed in natural swarms. Here, autonomous agents monitor local network telemetry, communicate their states to nearby agents, and collectively reason about fault locations using swarm intelligence. The system operates in a fully decentralized manner, enabling autonomous self-configuration through adaptive belief updates driven by local observations and neighbor interactions, thereby dynamically adapting to network topology changes, evolving traffic patterns, and limited global state observability. Simulation results indicate that our proposed method obtains an accuracy of 91.7% for networks consisting of 300 nodes. This perfomance is superior to both 82.4% from centralized ML and 72.8% from the rule-based approach, while reducing detection latency.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Praveen Kumar Pal
PY  - 2026
DA  - 2026/06/25
TI  - Self-Organizing Swarm Intelligence for Real-Time Network Fault Localization
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 453
EP  - 467
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_34
DO  - 10.2991/978-94-6239-713-2_34
ID  - Pal2026
ER  -