JC
J.Y.R. Cui
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
The rapid growth of mobile data traffic and the evolution towards 5G-Advanced and 6G networks have significantly increased the operational complexity of mobile networks, making fault localization a critical challenge for mobile network operators. Traditional fault management approaches rely on reactive, threshold-based alarms operating within individual network domains. This is increasingly ineffective for detecting and localizing faults in complex, multi-domain environments.
This thesis proposes a cross-domain fault localization framework that combines unsupervised anomaly detection with offline reinforcement learning, where the RL agent learns a policy for identifying the most likely fault origin based on observed anomaly patterns across domains. The proposed framework analyzes time-series Key Performance Indicators (KPIs) collected from the Radio Access Network (RAN), Core Network and end-to-end (E2E) domains to detect anomalous behaviour without requiring labeled data. Subsequently, the detected anomalies and cross-domain results are used by an offline reinforcement learning agent to track the most probable origin of faults across network domains.
The framework is evaluated using real-world KPI data collected over a 1 month period, consisting of 13 KPIs across the 3 domains. Unsupervised anomaly detection is applied to identify deviations from normal network behavior, while fault localization is performed using reinforcement learning based on the observed anomaly patterns. The results demonstrate that the proposed approach can identify anomalies and provide fault localization despite the lack of explicit fault labels.
This thesis highlights key challenges such as traffic dependent KPI behaviour, noise during low traffic periods and threshold selection. While the results indicate that combining unsupervised anomaly detection with reinforcement learning is a promising direction for predictive fault localization, further refinement is required to improve robustness, precision and operational consistency. Future work should focus on online deployment, calibration and improved learning strategies to support deployment in real world mobile network environments. ...
This thesis proposes a cross-domain fault localization framework that combines unsupervised anomaly detection with offline reinforcement learning, where the RL agent learns a policy for identifying the most likely fault origin based on observed anomaly patterns across domains. The proposed framework analyzes time-series Key Performance Indicators (KPIs) collected from the Radio Access Network (RAN), Core Network and end-to-end (E2E) domains to detect anomalous behaviour without requiring labeled data. Subsequently, the detected anomalies and cross-domain results are used by an offline reinforcement learning agent to track the most probable origin of faults across network domains.
The framework is evaluated using real-world KPI data collected over a 1 month period, consisting of 13 KPIs across the 3 domains. Unsupervised anomaly detection is applied to identify deviations from normal network behavior, while fault localization is performed using reinforcement learning based on the observed anomaly patterns. The results demonstrate that the proposed approach can identify anomalies and provide fault localization despite the lack of explicit fault labels.
This thesis highlights key challenges such as traffic dependent KPI behaviour, noise during low traffic periods and threshold selection. While the results indicate that combining unsupervised anomaly detection with reinforcement learning is a promising direction for predictive fault localization, further refinement is required to improve robustness, precision and operational consistency. Future work should focus on online deployment, calibration and improved learning strategies to support deployment in real world mobile network environments. ...
The rapid growth of mobile data traffic and the evolution towards 5G-Advanced and 6G networks have significantly increased the operational complexity of mobile networks, making fault localization a critical challenge for mobile network operators. Traditional fault management approaches rely on reactive, threshold-based alarms operating within individual network domains. This is increasingly ineffective for detecting and localizing faults in complex, multi-domain environments.
This thesis proposes a cross-domain fault localization framework that combines unsupervised anomaly detection with offline reinforcement learning, where the RL agent learns a policy for identifying the most likely fault origin based on observed anomaly patterns across domains. The proposed framework analyzes time-series Key Performance Indicators (KPIs) collected from the Radio Access Network (RAN), Core Network and end-to-end (E2E) domains to detect anomalous behaviour without requiring labeled data. Subsequently, the detected anomalies and cross-domain results are used by an offline reinforcement learning agent to track the most probable origin of faults across network domains.
The framework is evaluated using real-world KPI data collected over a 1 month period, consisting of 13 KPIs across the 3 domains. Unsupervised anomaly detection is applied to identify deviations from normal network behavior, while fault localization is performed using reinforcement learning based on the observed anomaly patterns. The results demonstrate that the proposed approach can identify anomalies and provide fault localization despite the lack of explicit fault labels.
This thesis highlights key challenges such as traffic dependent KPI behaviour, noise during low traffic periods and threshold selection. While the results indicate that combining unsupervised anomaly detection with reinforcement learning is a promising direction for predictive fault localization, further refinement is required to improve robustness, precision and operational consistency. Future work should focus on online deployment, calibration and improved learning strategies to support deployment in real world mobile network environments.
This thesis proposes a cross-domain fault localization framework that combines unsupervised anomaly detection with offline reinforcement learning, where the RL agent learns a policy for identifying the most likely fault origin based on observed anomaly patterns across domains. The proposed framework analyzes time-series Key Performance Indicators (KPIs) collected from the Radio Access Network (RAN), Core Network and end-to-end (E2E) domains to detect anomalous behaviour without requiring labeled data. Subsequently, the detected anomalies and cross-domain results are used by an offline reinforcement learning agent to track the most probable origin of faults across network domains.
The framework is evaluated using real-world KPI data collected over a 1 month period, consisting of 13 KPIs across the 3 domains. Unsupervised anomaly detection is applied to identify deviations from normal network behavior, while fault localization is performed using reinforcement learning based on the observed anomaly patterns. The results demonstrate that the proposed approach can identify anomalies and provide fault localization despite the lack of explicit fault labels.
This thesis highlights key challenges such as traffic dependent KPI behaviour, noise during low traffic periods and threshold selection. While the results indicate that combining unsupervised anomaly detection with reinforcement learning is a promising direction for predictive fault localization, further refinement is required to improve robustness, precision and operational consistency. Future work should focus on online deployment, calibration and improved learning strategies to support deployment in real world mobile network environments.
Practicing fire scenarios in emergency response training is very hard due to various obstacles. An example is when holding a training, real fire will preferably not be used as it can become threatening. Real fire will only be used in a surrounding where safety is ensured, which is probably outdoors. An emergency responder hardly knows that it has entered an area or room with imaginary fire nor does he know the extent of the fire due to the absence of smoke. This makes it exceedingly difficult to make right decisions during the training on the spot and this might lead to failure to help employees or clients to escape the fire area or building. This project focuses on developing glasses that can darken the view of the user, when entering an area with simulated fire and smoke. In order for the emergency responder to be able to practice in the most real possible scenario. The gain of using the glasses, is that it provides a common understanding between the instructor and trainee about the smoke situation in a training exercise. This enhances the quality of training, decreasing the possibility of making an incorrect decision when a real fire breaks out. This is done by constructing a set of darkening glasses that can darken the view, on the command of an infrared beacon that mimic the source of smoke in an area.
...
Practicing fire scenarios in emergency response training is very hard due to various obstacles. An example is when holding a training, real fire will preferably not be used as it can become threatening. Real fire will only be used in a surrounding where safety is ensured, which is probably outdoors. An emergency responder hardly knows that it has entered an area or room with imaginary fire nor does he know the extent of the fire due to the absence of smoke. This makes it exceedingly difficult to make right decisions during the training on the spot and this might lead to failure to help employees or clients to escape the fire area or building. This project focuses on developing glasses that can darken the view of the user, when entering an area with simulated fire and smoke. In order for the emergency responder to be able to practice in the most real possible scenario. The gain of using the glasses, is that it provides a common understanding between the instructor and trainee about the smoke situation in a training exercise. This enhances the quality of training, decreasing the possibility of making an incorrect decision when a real fire breaks out. This is done by constructing a set of darkening glasses that can darken the view, on the command of an infrared beacon that mimic the source of smoke in an area.