New Heavy Reading report highlights the growing role of AI in telco operational use cases

Data from Heavy Reading's Intelligent Data-Driven Operations with AIOps report indicates that CSPs recognize AIOps as a solution for dealing with network expansion.

Jennifer Clark, Principal Analyst – Cloud Infrastructure & Edge Computing

January 11, 2024

4 Min Read
Abstract image of geometric shapes and connected lines
(Source: Kiyoshi Takahase Segundo/Alamy Stock Photo)

At the end of 2022, Heavy Reading published Simplifying Operations with Multi-Layer Network Control, a white paper that examines how communications service providers (CSPs) can simplify network management by automating multi-layer operations. Then, at the end of 2023, we revisited the subject in a report sponsored by Ciena, Intelligent Data-Driven Operations with AIOps, with a special focus on artificial intelligence for IT operations (AIOps). The analysis in this report supports the theory that CSPs are looking to use AI for IT operations (AIOps) to broaden the scope, ease of use and effectiveness of network management in all stages of the network lifecycle.

CSPs are leveraging a combination of AI/machine learning (ML), multi-layer management and the cloud to underpin their AIOps strategies. Heavy Reading sees specific current use cases benefiting the most from AIOps over the next two years, providing the best ROI for the telcos. These use cases are in network operations and management, as supported by data from Omdia's recently published Service Provider Digital Transformation & Cloud Strategies Survey Report – 2023 (see figure below). More specifically, most are performance optimization use cases that improve routes, channels and bandwidth/spectrum utilization while supporting SLA parameters and route diversity requirements.

CSPs are looking to improve efficiency and cut hardware costs with a shift to cloud

Ciena_graphic.png

(Source: Omdia, Service Provider Digital Transformation & Cloud Strategies Survey Report – 2023)

Key AIOps use cases are described below. Multi-layer management capability is essential to all these use cases for merged Layer 0–3 visibility and control across optical and IP layers.

  • Proactive maintenance: AI/ML is used to predict maintenance issues, identify the root cause and ultimately resolve the issue without operator intervention. Verifying fiber health is an example of proactive maintenance. It usually relies on an optical time domain reflectometer (OTDR), a device that tests the integrity of a fiber cable and is used for the building, certifying, maintaining and troubleshooting of fiber optic systems. Current OTDR capability is embedded into photonic line cards, making frequent measurement possible. AI/ML modules leverage historical and current OTDR data to enable proactive maintenance apps.

  • Multi-layer capacity forecasting: By analyzing historical and trend data from Layers 0–3, AI can be used to predict future demand. In delivering a prediction of future capacity, such forecasting also considers the impact of changes to the individual layers (IP, Ethernet or optical) and the cost impact of the capacity recommendations.

  • Congestion alleviation: This function uses ML to identify patterns and relationships in traffic data to route traffic to avoid congestion or to identify DDoS attack traffic and drop it.

  • Signal-to-noise ratio optimization: AI/ML, in combination with analytics, can be used to monitor and control the signal-to-noise ratio (SNR) margin. Today's coherent modems generate a massive amount of data, but without AI/ML, it is difficult to leverage the data in a timely and holistic manner. If CSPs can increase the SNR on their optical infrastructure, they can optimize costly fiber transport and significantly lower the overall cost per bit.

  • Spectrum defragmentation: Spectrum becomes fragmented when isolated, non-aligned and non-contiguous frequency slots accumulate, and it cannot be allocated to new connections. Defragmentation of the spectrum results in better use of the fiber and the freeing up of stranded capacity. This use case is computationally intensive and relies on AI/ML to determine the optimal channel assignments to free up the most spectrum.

  • Digital twins: Digital twinning creates a virtual representation of a physical entity, operational process or set of data to simulate, capture real-time performance data and then predict and optimize. This gives CSPs the tools they need to answer such questions as, "Can I complete a network modification in a maintenance window?" Digital twinning also enables CSPs to test software upgrades (e.g., to routers) by first providing scripts that can be validated before installing the upgrade on the production network. For CSPs, a digital twin provides a replica of the physical network that exists in the digital space throughout the network lifecycle. A digital twin continuously learns and updates itself from multiple sources to show its near real-time status and features, working conditions or position. It also integrates historical data from past machine usage into its digital model.

CSPs consistently cite AIOps and the technologies that make up an AIOps solution — AL, ML, multicloud, cloud native migration, etc. — as critical parts of their digital transformation strategy. They emphasize that the transition to AIOps cannot take place overnight. However, they recognize AIOps as a solution for dealing with relentless network expansion and see it as imperative for managing the network going forward.  

This blog is sponsored by Ciena.

Read more about:

Heavy Reading

About the Author

Jennifer Clark

Principal Analyst – Cloud Infrastructure & Edge Computing

Jennifer Pigg Clark is Principal Analyst with Heavy Reading covering Cloud Infrastructure and Edge Computing. Clark provides actionable insight into service provider evolution, examining the challenges and opportunities facing network operators as they move towards 5G and IoT with an increasingly virtualized and cloud native infrastructure. Clark examines the solutions and technology reshaping the telco data center, technologies such as Edge Computing, Open Source, OpenStack, container networking, Network Orchestration, Software Defined Networks (SDN), Network Functions Virtualization (NFV), and SD-WAN. Clark started her industry research career with the Yankee Group, which was acquired by 451 Research in 2013. She held the role of Sr. Vice President at Yankee Group. Prior to joining Yankee Group, Clark was Manager of Network Planning and Strategy for Wang Laboratories'corporate data network. She began her career at Wang with responsibility for the domestic and international roll-out of Wang's packet network, connecting more than 250 locations in 14 countries. Before joining Wang, she was a member of the IT research and development division of Commercial Union Insurance Companies. Clark is a highly regarded speaker at industry seminars and conferences and is frequently cited by the commercial and trade press. She has been a guest lecturer at the MIT Sloan School of Management and is a member of the IEEE. She holds a B.A. degree from Mount Holyoke College.

Subscribe and receive the latest news from the industry.
Join 62,000+ members. Yes it's completely free.

You May Also Like