Application Of Complex Event Processing For Broadband Network Fault Prediction Using Random Forest
The customer satisfaction of the clients of broadband network mostly depend on robustness of the service offered by Internet Service Providers (ISP)s. Providing uninterrupted network service is essential in this communication era even though interruption in internet connection is unavoidable. Howeve...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2018
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The customer satisfaction of the clients of broadband network mostly depend on robustness of the service offered by Internet Service Providers (ISP)s. Providing uninterrupted network service is essential in this communication era even though interruption in internet connection is unavoidable. However, if it is predicted earlier, the consequences can be minimised. So, it is very essential to accurately forecast the faults in internet connection for telecommunication companies. However, currently the companies do not have real-time fault prediction system to solve the issue. This system may help to reduce future operational expenses to some extend and it may enable to perform preventive actions as far as possible. Hence, the objective of this thesis is to develop a suitable tool to predict the network fault. The proposed tool is a combination of Complex Event Processing (CEP) and Predictive Analytics (PA). The PA is used to predict network fault using Random Forest Classifier and CEP is used to perform the prediction in real-time on streaming events. |
|---|