While hardware maintenance is extremely important for Communications Service Providers to ensure Quality of Experience (QoE) for their subscribers, maintaining the actual services used by subscribers is equally significant.
Typically, CSPs learn that a service has failed either from their monitoring systems or their subscribers after it has already happened. Therefore, learning that a service is likely to fail in advance allows CSPs to solve any problems proactively. Consequently, the reduced service downtime may provide CSPs a competitive edge, increasing the subscribers’ QoE and decreasing their churn rate.
Elitnet’s Service Degradation Detection solution addresses this issue by collecting data from numerous network sources and detecting anomalies using Artificial Intelligence (AI)/Machine Learning (ML) methods. The solution analyzes service data, measures quality of experience (QoE), and detects anomalies which indicate service degradation, allowing the CSP to predict service problems and prevent or even eliminate service downtime.
The solution is implemented as a collection of data processors/applications for Elitnet’s Data Analytics Platform, a high-performance data analysis platform which covers data collection from multiple sources, AI/ML enabled data processing, and powerful reporting and monitoring tools.
KEY FUNCTIONALITIES
SERVICE DATA ANALYSIS
The solution collects and analyzes data for each service and alerts the CSP in case any of tracked indicators goes beyond predefined margins.
SERVICE ANOMALY DETECTION
The solution uses Big Data and AI/ML methods to process data and detect anomalies related to service degradation detection tasks.
QoE MEASUREMENT
The solution measures the subscribers’ Quality of Experience for each service and alerts the CSP in case it falls below any predefined thresholds.
RELATED PRODUCTS
Big Data and AI-enabled network
security, fraud prevention, and
predictive maintenance