ALACA: A platform for dynamic alarm collection and alert notification in network management systems

Abstract

SummaryMobile network operators run Operations Support Systems that produce vast amounts of alarm events. These events can have different significance levels and domains and also can trigger other ones. Network operators face the challenge to identify the significance and root causes of these system problems in real time and to keep the number of remedial actions at an optimal level, so that customer satisfaction rates can be guaranteed at a reasonable cost. In this paper, we propose a scalable streaming alarm management system, referred to as Alarm Collector and Analyzer, that includes complex event processing and root cause analysis. We describe a rule mining and root cause analysis solution for alarm event correlation and analyses.The solution includes a dynamic index for matching active alarms, an algorithm for generating candidate alarm rules, a sliding window-based approach to save system resources, and a graph-based solution to identify root causes. Alarm Collector and Analyzer is used in the network operation center of a major mobile telecom provider. It helps operators to enhance the design of their alarm management systems by allowing continuous analysis of data and event streams and predict network behavior with respect to potential failures by using the results of root cause analysis. We present experimental results that provide insights on performance of real-time alarm data analytics systems.

Recent Advances in Data Engineering for Networking

“…Furthermore, in some scenarios, such as IoT networks, raw data (e.g., temperature, humidity) collected via the Data Connect module can be integrated with the Data Visualization component either via mobile applications or web user interfaces for direct visualization in a dashboard. In other scenarios, further data analysis and processing using recent advances in AI/ML algorithms may be required (e.g., in the case of high quality prediction, statistical analysis or root cause analysis [44]), which takes place between the Data Connection and Data Visualization modules.…”

“…https://hudi.apache.org/, accessed December-202142 https://github.com/ClickHouse/ClickHouse, accessed December-202143 https://www.timescale.com/, accessed December-202144 https://delta.io/, accessed December-202145 https://iceberg.apache.org/, accessed December-2021VOLUME 10, 2022 …”

Discovery of Frequent Patterns of Episodes Within a Time Window for Alarm Management Systems

“…After presenting the tests on the influence of system parameters, the proposed algorithm is compared with a traditional sequential data mining algorithm, RuleGrowth [14] and MineAlarmRulesForKind algorithm [31]. For this evaluation, the same prediction occurrence model with the alarm rules presented in [31] is implemented.…”

A system for profiling the IXPs in a region and monitoring their growth: Spotlight at the internet frontier

“…These motivate this work that aims at designing and implementing a tool, which can evaluate in real‐time key metrics that could help IXPs market their features, report on routing inefficiencies, and make everyone witness the interconnection growth and gaps, etc. Such a goal is in line with previous research such as the studies, which aimed to help improve networks performance or topologies using visualizations tools that relied on collected BGP data.…”