Leveraging AIOps for a holistic view of network performance and security

In this interview with Help Net Security, Terry Traina, CTO at Masergy, talks about the benefits of leveraging AIOps and how it can help thwart growing security threats.

Many organizations are already leveraging AIOps across their network and security. How does that help them stay ahead? What are the benefits?

With remote and hybrid business models demanding a new level of application performance and security measures to power and protect multi-cloud environments, organizations are embracing AIOps to gain a smarter, holistic view of network performance and security. AIOps enables them to better manage applications and data across environments with dynamic physical boundaries, providing insight and visibility from the cloud to every endpoint. When AI can alert IT of anomalies, recommend improvements, and ultimately act automatically to resolve issues, those are the next-level benefits.

According to a recent State of AIOps study, network operational efficiencies, faster security threat identification, and faster security threat response were noted as the top three reasons for AIOps adoption.

Does AIOps help and simplify IT teams’ work and how?

IT leaders can’t afford to trade WFH flexibility for heightened security risk and declines in business continuity, and AIOps helps to manage those tradeoffs. The complexity of IT management has grown beyond the capabilities of human-based analysis and manual evaluation. With multi-cloud environments and information exchange occurring outside the corporate data center, IT engineers are spending 49% of their time on monitoring application performance with 48% of that time troubleshooting the network. AIOps automates evaluation thereby increasing efficiency.

Does AIOps eliminate the human element completely?

It can, yes. AIOps has the power to create fully autonomous networks — systems that are self-managing and self-healing, without human intervention. But it doesn’t just happen overnight. Full autonomy is reached through a process called closed-loop automation. In the beginning AIOps makes only recommendations based on it’s evaluations, but when connected to control panels and given the right permissions, it can also act on its own recommendations. This is when AIOps evolves from being an advisor to a valuable automation tool. IT teams train AIOps engines on their operational playbooks, evolving through key stages of automation and learning to trust the machine to act alone.

These four progressive steps are part of the journey toward autonomous networking:

• AIOps insights: “Here’s the problem I found.”
• AIOps recommendations: “Here’s the problem and my recommended repair.”
• AIOps partial automation: “Here’s my recommendation. Approve and I will make the repair.”
• AIOps autonomous networks: “Here’s what I just fixed for you.”

Can you describe the working process of AIOps?

AIOps uses machine learning, behavioral analytics, and predictive analytics to observe and evaluate performance across the network, security, and cloud applications. Using historic patterns of behavior and past problem/solution analysis, it can detect anomalies, evaluate propensity, and generate real-time alerts, suggested reactive improvements, proactive recommendations, and predictions. In order to achieve this AIOps needs:

• Access to data feeds: SASE solutions that unite network and security analytics into one dashboard, offering a single source of truth, work well as an AIOps platform.
• Access to system controls: Without the ability to act, AIOps provides only insight. To automate, it must make changes to network configurations and security policies.
• Agile infrastructure: Modern IT architectures managed by software rather than hardware (SD-WAN) and defined by the cloud and virtualization are best suited for AIOps.

What are the use cases for AIOps?

According to the State of AIOps study, the top use cases include cloud application analytics, network performance improvement, network service optimization, and faster threat detection and response. Sixty-four percent of IT professionals surveyed measure AIOps success based on IT operational efficiencies, and another 54 percent on improved network or app performance. This shows there is real value in an AIOps investment, both making IT operations more efficient and improving business operations.

What does the future look like for AIOps?

Full automation is the end game, and the future is bright. That’s because everything IT teams need to build a fully autonomous network is available today. A resounding majority (84%) of IT leaders see AIOps as the path to a fully automated network environment, according to the State of AIOps study. Eighty-six percent predict that they will have a fully automated network within 5 years, and 97% already express a high level of trust in AIOps tools to act on their own recommendations and create fully automated systems.