Cognitive Networking with Analytics ML/AI
Solving Real-world Problems with Solutions Powered by Advanced Analytics and Machine Learning/AI
Network automation continues to be a priority for most optical transport network operators. Whether the goal is to reduce operational costs, increase network efficiency, manage disaggregated networks, or accelerate service activation, automation is becoming increasingly critical.
The first step to efficient network operation is learning from network data. Advanced analytics and machine learning/AI techniques complement Infinera’s application-based approach to automation. Offering flexible and intuitive ways of visualizing multiple key network metrics and identifying patterns, trends, and correlations, Infinera’s network analytics solution helps operators improve network performance and reliability and respond proactively to avoid service degradation. The combined use of different Transcend applications, enabling closed-loop automation, opens the path to intent-based, self-healing networks.
Highlights
Modular app-based approach
Practical automation applications, including Auto-Lambda, Instant Bandwidth, ADAPT, CORE PCE, and vASON, are easy to deploy without massive infrastructure changes, solving real-world problems and adding value to the network.
Multi-layer, multi-vendor service automation
With real-time service visualization, you can accelerate service activation and improve network efficiency.
Streaming telemetry
Streaming telemetry is fast becoming the de facto approach in packet and optical networks, replacing or complementing polling-based monitoring with scalable fine granularity and real-time network visibility, enabling better troubleshooting and control, as well as more efficient resource utilization.
Network analytics
Collect a variety of network information and store and analyze the data to extract powerful insights in real time to maximize existing investments, plan more efficiently for growth, and improve customer experience. For example, Optical Performance Analytics can help make the best use of available optical budget and network capacity.
Machine learning/AI
Machine learning techniques allow the extraction of value from data far beyond what standard statistical analysis permits. Pattern finding and predictive power are taken to a new level.
The Infinera Experience
Infinera’s automation solutions are complemented by the know-how and proven expertise of Infinera Global Services, our wide array of professional services ranging from consulting to network integration services and network management services.
Testimonial
“Verizon has always been relentless when it comes to technology innovation. We are able to simplify network operations and reduce costs through virtualization and automation. This is one example.”
Director of Network Infrastructure Planning
VERIZON
Blog
Take Me to the Cloud!
There is much discussion on how cloud-native network functions can help service providers move beyond connectivity services. There is also debate on whether the use of multi-cloud and hybrid cloud architectures for distributed cloud computing are key to achieve the scale and agility imposed by 5G and IoT. In this blog, Teresa Monteiro focuses on cloud in network automation – but from another perspective, that of cloudifying embedded infrastructure.
Related Resources
Blog
Five Things You Should Know About Machine Learning
Blog
Is Your Optical Network Ready for Open and Disaggregated?
Blog
Transformation and Practical Automation on Display at MEF '19
White Paper
Cognitive Networking in the Access: Deploy DAA Faster than Ever
Video
MEF 3.0 PoC: AI/ML and Policy Driven Networks for the LSO-Based Architecture
Data Sheet
Dashboard Reporting and Analytics
White Paper
Intelligent Light: The Softwareization of Optical Networks
Technical Paper
Demonstration of Extensible Threshold-Based Streaming Telemetry for Open DWDM Analytics and Verification
Experience Infinera
Learn how the innovation and intelligence of Infinera networks can provide amazing experiences for your customers and your business.