The telecom industry is in the midst of a massive shift to new service offerings enabled by 5G and edge computing technologies. With this digital transformation, networks and network services are becoming increasingly complex: RAN, Core and Transport are only a few of the network’s many layers and integrated components. Today’s telecom engineers are expected to handle, manage, optimize, monitor and troubleshoot multi-technology and multi-vendor networks. The biggest challenge is balancing the innovation that pushes for new technologies, layers and nodes with the need to provide robust, high quality products and services 24/7, 365 days a year. For telecoms (CSPs) and other verticals employing extremely complex systems, fully autonomous monitoring technologies are the holy grail. As monitoring and alerting platforms mature, there is a growing expectation that they will go from anomaly detection to full remediation, without a human in the loop. This is not your run of the mill industry buzz. Over the last five years, monitoring telecom networks have evolved to the extent that autonomous remediation (aka “the action phase”) is the logical next step, likely to become a dominant feature for leading CSPs. But to get there, robust machine learning capabilities are key.  [CTA id="6deee8f2-9918-4475-bc47-87e93a96be07"][/CTA] Scale, accuracy, speed Machine learning is already making a difference in the network monitoring space. In order to ensure availability and reliability and deliver more business value, CSPs need to stay on top of hundreds of metrics. But with the ongoing growth in operational complexities, effectively managing and monitoring connections, devices, radio networks, current and legacy core networks, services, and transport and IT operations is becoming a radical challenge. Static network monitoring gives rise to billions of alarms with a very high rate of false positives, since it’s based on manual thresholding for a system that is too complex and volatile to adhere to predetermined states. What is worse - static monitoring leads to late detection of service degradation and incidents. Even after detection, which often occurs after the incident has already impacted customers, there is no context to go on for expedited resolution.  Compared to manual, dashboard-based monitoring systems, ML enables unprecedented scale, accuracy and speed. It enables today’s telecom engineers to handle, manage, optimize, monitor and troubleshoot multi-technology and multi-vendor networks. Machine learning enables CSPs to move from reactive problem solving to proactive monitoring and learn more about what is happening across their networks before any minor issues escalate into bigger problems.  In the network operations context, every network generates millions of time series data, measuring all aspects of the network. Anomalies can cause service degradations and system-wide outages/incidents. Therefore, discovering these anomalies and identifying the technical root cause to fix incidents is a key objective of network operations. Autonomous anomaly detection minimizes time spent looking for issues, leaving more time to focus on resolution.  From detection to remediation AI enables the transformation of traditional network and service operations towards automation and intelligent operations through three crucial steps that can only be achieved by applying cutting edge machine learning: anomaly detection, correlations and root cause analysis, and, finally - remediation.  Anomaly detection. In the first stage, ML enables real time monitoring of 100% of the network data from connections, devices, radio networks, current and legacy core networks, services, transport, IT operations and any other source. Leading monitoring platforms feature fully autonomous baselining that also accounts for different seasonalities and constantly and optimally adapts to change. By monitoring the full scope of data using adaptable algorithms that take seasonality, trends and other behavioral variabilities into account, anomalies are detected faster and false alarms are reduced to a minimum.  Correlations and root cause analysis. One of ML’s superpowers is its ability to correlate across billions of metrics. When such a technology is leashed on data that has been freed from its silos, it autonomously creates the correlation between different related events and glitches across multi-technology (3G/4G/5G) and multi-vendor networks. These correlations provide the full context of what is happening, enabling teams to swiftly get to the root cause of every issue for the fastest possible remediation.  Remediation. By autonomously pinpointing network anomalies and mapping the relations between them, ML-based monitoring is paving the way for autonomous remediation. These automated, closed-loop processes are referred to as ITSM or “self-driving ITOM”. Currently, they can be observed in low level tasks, such as automating “bounce the server” or an “open a ticket” type of script. This is done through automation scripts that still require a human in the loop. However, the technological roadmap is leading towards automation rule mapping and a fully automated ML remediation engine. In this scenario, the ML-based system will go through phases 1 and 2 - anomaly detection and root cause analysis - recommend an action based on previous incidents, execute the action through the remediation engine, and fine tune its operations through a closed feedback loop, increasingly improving its reactions.  Moving forward Only these three ML-based monitoring tiers can provide CSPs with robust anomaly detection and remediation that ensures reliability, availability and a seamless customer experience. Still in its infancy, the “action” phase of monitoring is still lacking in most solutions. However, since this is the direction this domain is going in, it’s a good idea to check with respective vendors where they stand on automated actions. Since autonomous remediation is predicted to become a dominant feature for leading platforms, in the meantime it’s crucial to verify that the platform is ML-based and can effectively communicate granular data and insights to both IT stakeholders and other IT systems that can be used in the remediation phase. 

5G is in the process of transforming communications technology, enabling never-before-seen data transfer speeds and high-performance remote computing capabilities. As a cloud-native application, 5G provides advantages in terms of speed (the 5G network’s software-based functionality can be developed, upgraded and replaced several times a day); agility (the network can be deployed within minutes rather than months); efficiency (CSPs are aiming for a 10-fold improvement in the efficiency with which the 5G network can be scaled and migrated to take advantage of cloud economics); and robustness (zero downtime resilience results from the 5G network’s design and built-in automation). The Challenges of Transforming to 5G But in order to reap the rewards inherent in 5G technology, CSPs need to dramatically transform their key capabilities in terms of mobility, low latency, high data rates, extreme reliability and vast scale. The 5G network engineering, operations and scaling have to be vastly different from all the previous generation of mobile technologies, across all its layers. The underlying network technologies required for 5G include: Spectrally efficient, dense and ultra-reliable low-latency radio networks Strong security and authentication framework Network Function Virtualization – Cloud computing-based networks where network functions share resources dynamically and independently of geographical location Software-Defined Networking to separate user plane and control plane functions and to support network slicing to enable creation of multiple virtual networks to cater for specific characteristics of the services being offered Orchestration and management to fully automate fulfillment and assurance of services Multi-access edge computing to bring services closer to the network edge Edge computing and Kubernetes Edge software and computing bring computers and the data they need closer to each other to increase availability and speed and protect against latency and performance issues. Edge computing enables the reduction of data processing time to accommodate the growing need for speedier processing across various Internet devices. To fulfill this potential, the 5G network-as-application will need a different execution environment from first-generation virtual network functions (VNFs) that execute in virtual machine (VM)-based clouds. Ultra-reliable, low-latency communications, network slicing, edge services, and converged access hinges on CSP’s adoption of cloud-native technology and containers. Modern, cloud-native applications execute in lightweight container technology controlled by an orchestrator. In this ecosystem, Kubernetes is rapidly becoming the de facto standard for container orchestration. Nokia, for example, adopted Kubernetes as early as 2018 and attributes to it a large part in the success of its foray into 5G.  Kubernetes is, essentially, an engine for container management orchestration, tasked with managing the container-based infrastructure that will be needed to support 5G networks and related services.  Kuberenetes enables CSPs to self-remediate, scale on demand, and automate the microservices lifecycle. From a business perspective, Kubernetes can help reduce operational costs and increase the efficiency of engineering teams.  By enabling the separation of the infrastructure and the application layers, Kubernetes supports a system with less dependencies, that can easily sustain the implementation of features in the application layer. Telecoms are opting for Kubernetes for the resilient, flexible, scalable, and automated capabilities inherent to its architecture. But as Kubernetes integrates into 5G, CSPs need to develop their container networking expertise. [CTA id="e752365e-683e-44de-9472-be8e05efd62b"][/CTA] Staying on top of a new network Kubernetes and cloud native computing represent a big step forward in terms of 5G’s potential. In combination, this is the kind of advancement that spells digital transformation. But this transition also depends on the confidence telcos can build towards these new technologies by creating the monitoring environment that provides the transparency needed to seamlessly identify and mitigate any issues as soon as possible.  Monitoring distributed environments has never been easy. While solving some of the key challenges involved in running distributed microservices at large, Kubernetes has also introduced some new ones. The growing adoption of microservices makes logging and monitoring more trying since it involves a large number of distributed and diversified applications constantly communicating with each other. On one hand, a single glitch can kill the entire process. On the other hand, identifying failures is becoming increasingly difficult. It’s not surprising that engineers list monitoring as a major obstacle for adopting Kubernetes.  Manual alerts and thresholds are a non-starter when it comes to Kubernetes. CSPs run multiple clusters, each with a large number of services, making static alerts completely impractical. Values fluctuate for every region, data center, cluster, etc. Manual or even semi-autonomous monitoring platforms will inevitably produce alert storms (too many false-positives)—or you could miss key events (false negatives). By adopting an AI monitoring system, your organization can use machine learning to constantly track millions of your Kubernetes events in real time and to alert you when needed. Anodot’s Autonomous Monitoring solution creates a comprehensive view by monitoring the Kubernetes environment and the applications themselves, to bulletproof your operations. It is vertical-agnostic, and ideal for various end user applications such as IoT, e-commerce, manufacturing, retail, digital entertainment, fintech and more. Anodot automatically illuminates critical blind spots for the shortest time to detection and resolution, so even when transitioning to new technologies, CSPs never miss another incident—and can rely on a system where every alert counts.  

Automated root cause analysis is the missing link between autonomous detection and autonomous remediation. Bridging the gap holds, on the face of it, the true realization of AIOps. Alas, in reality, uncovering a root cause is conceptually complex and still impossible without a man in the loop, even using today’s bleeding-edge AI technology.

The promise is exciting but the reality is complicated. These eight essential components are what automated remediation will depend on to (hopefully) operate successfully.

Real-time service experience monitoring ensures lightning-fast detection of the incidents that impact your customers and revenue so that you can scale quickly and deliver great customer experience at the same time.

Our list of the 15 best analytics tools of 2021. With the right mix of software you’ll be in a much better position to optimize user experience and increase the bottom line.

When it comes to staying current on big data and analytics, you'll want to bookmark these leading blogs and sites.

These two incidents from the gaming and eCommerce industry that showcase the limitations of static thresholds and the impact that has on customer experience.

Now there’s an easy way to measure the business impact of every incident. Anodot lets you set a monetary value for each measure you monitor. Once you set the Impact Value, future alerts will include the business impact of the anomaly.