Artificial Intelligence-Based Predictive Network Congestion Control for Mission-Critical Industrial Communication Systems
One of the biggest problems currently hindering reliable and consistent performance for any type of industrial communication system, such as time-sensitive control subsystems seen in the oil & gas industry, is network congestion. This study aims to create an artificial intelligence (AI) predictive model to detect congestion events in the Oil Company (OC) network. To investigate the performance of the Random Forest, XGBoost, and LSTM models for network congestion detection, this study uses a quantitative comparative experimental design involving 1,000 operational network records from a network of an oil company. They experimented with three models based on machine learning as shown below: Random Forest, XGBoost and LSTM. The results revealed that all the models were performing with a very high level of accuracy ( Accuracy>96%). Indeed, XGBoost performed best among all the models evaluated in terms of all the measures we used, with Recall = 0.978 and F1-Score = 0.966, a good match for mission-critical environments that may encounter misdiagnosed traffic congestion and disrupt industrial processes. The results indicate that when AI is used to predict congestion in high-quality digital infrastructures, it can be beneficial in several areas, such as QoS (Quality of Service) improvement, packet loss mitigation, and predictive maintenance. The main value of this study is the suggested actionable framework specifically for oil-sector networks and highlighting new trends integrating AI with Digital Twin & Edge Technologies. The results could be used to guide the choice of congestion-detection models to track the performance of communication in SCADA-enabled industrial networks
Authors
- Taha Abdulwahid Mahmood (ORCID: https://orcid.org/0009-0005-2599-1335)
- Layla Mahdi Salih (ORCID: https://orcid.org/0000-0001-6142-5430)
- Afnan waleed Abdulsattar (ORCID: https://orcid.org/0000-0003-0740-5986)
Institutions
- University of Kirkuk (IQ)
Publication Details
- Journal
- Scientific journal of engineering and technology.
- Published
- 2026-11-14
- DOI
- https://doi.org/10.69739/sjet.v3i2.2520
- Primary Topic
- Network Traffic and Congestion Control
- Type
- article
- Field-Weighted Citation Impact
- 0.00