Ciena uses cookies to ensure that we give you the best experience when visiting our website, as well as to enhance the overall quality of our site. By continuing, we assume that you consent to receive all cookies on all Ciena websites. To consent to receive all cookies on all Ciena websites, click I acknowledge. To learn more, view our privacy policy.

There was a problem with your video. Another version is available.

Machine Learning and Big Data Analytics

A technique used for network analytics

Machine learning with big data analytics extracts hidden network insights

The proliferation of connected devices along with an exponential growth in traffic has added to the complexity of network management. With new technologies such as 5G and Edge Cloud set to bring even more devices and services into the network, service providers, enterprises and other network operators are looking to looking implement innovative new technologies and tools to modernize their service and network operations. AIOps, which utilizes the combination of big data and machine learning to enable automation of operations processes, plays a key role in this approach.

Machine Learning: A field of study that gives computers the ability to learn without
being explicitly programmed —Arthur Samuel (1959).

Machine learning is a branch of artificial intelligence (AI) that uses algorithms and analytics to recognize data patterns or trends. These insights can then be used to make predictions or AI-enabled decisions, while gradually improving accuracy through continuous learning. Machine learning thrives on growing data sets.

AIOps diagramBig data analytics refers to the use of various methods, including machine learning, to extract meaningful insights and correlations from large data sets, including structured and unstructured data. The more data fed into a machine learning system, the more it can learn and apply to deliver higher quality insights. In large networks, big data is generated by network elements, connected devices, traffic data, event logs, performance and fault metrics, ticketing systems, and more.

AIOps platforms can leverage big data from the diverse network, analyze using machine learning models, and initiate actions based on the result. Unlike traditional monitoring tools that analyze data and reports the event for human interpretation, AIOps enables predictive analytics, actionable insights, and service lifecycle automation for network operations.

For network operators, machine learning and big data analytics can address a wide range of business and operational needs. For example, AIOps-based continuous learning can help ensure service and network reliability by keeping the network’s health at its optimum state. Big data analytics can learn from historical performance metrics and trouble   ticketing data to understand normal behavior and then predict future network failures. Machine learning models on big data can correlate events, suppress noise, and emphasize high impact events. Collectively, AIOps, machine learning and big data analytics can recommend remediate actions or enable self-optimization, self-healing actions.

AIOps with Blue Planet

The Blue Planet® software utilizes big data analytics on historical and real-time data to learn and understand changing network conditions, ultimately to ensure network resiliency and service Quality of Experience (QoE).  This holistic approach leverages machine learning models that enable capabilities such as anomaly detection, alarm suppression, and root-cause analysis for continuous learning to meet service performance requirements. This AIOps-driven application of new actions on the network is often referred to as ‘closed-loop automation.’ It’s a continuous process—and it’s the focal point of Blue Planet’s service lifecycle automation vision.

Blue Planet is based on an open framework and allows for quick and easy integration of multiple data sources, whether physical or virtual. Integration with cluster-based storage systems allows for scalable datasets and efficient machine learning. Its microservices-based architecture provides modularity and scale to enable rapid adoption of data-driven automation.

Get started now