Estimating the effect of network element events in a wireless network

Abstract

Abstract Network events, like outages, are costly events for communication service providers (CSPs) not only because they represent lost revenue but also because of adverse effects suffered by the CSP’s customers. Quantifying the effect of negative events on certain key performance indicators allows the CSP to measure the network resources impacted, to provide data for a more robust revenue assurance process, and to assign appropriate severity to the events. These additional insights may help optimize the resource allocation, ticketing, and troubleshooting response times. This paper presents a novel heuristic algorithm that takes advantage of the daily patterns observed in most key performance indicators of a wireless network and the stability observed in the differences between the original time series and the lagged version. The proposed algorithm uses those differences and the previous actual values to make accurate predictions of time-series traffic volume data that represent the estimated effect of a wireless network event. The performance of the algorithm is compared with that of the state-of-the-art autoregressive, integrated, moving average (ARIMA) model and the results are reported. The proposed algorithm has reduced standard deviation in error percentage by 4.8 percentage points, has no negative bias, and executes 97% faster than the ARIMA model. The algorithm provides an accurate methodology for online or batch network event impact estimation that could potentially be implemented in traditional relational database management systems (SQL) or Big Data environments.

Keywords

• Network event
• Forecasting
• Anomaly detection
• ARIMA
• Time series
• Self-Organizing Networks (SON)