Category: Network Analytics

As seen in Pipeline Publication

Fast, reliable, and low-latency data services are essential deliverables from telecom operators today. Realizing them is pushing operators to enhance infrastructure, expand network capacity and mitigate service degradation. Unlike other industries, though, telecom networks are vast monoliths comprising fiber optic cables, proprietary components, and legacy hardware. Because of this, there is less enhancing—and more shoring up the creaking infrastructure.

The evolution of RAN

Radio access networks (RAN) are the backbone of the telecommunications industry. However, the industry’s propensity to incubate and evolve newer, cost-effective, and energy-efficient technologies has been slow due to monopolization by RAN component manufacturers.

Throughout the history of mobile network evolution, innovation has been driven by the need to ensure a superior customer experience. This calls for an evolution from legacy systems to alleviate shortcomings and address rising demand. The same can be said for the need to evolve the RAN ecosystem to revolutionize the mobile communication industry, as we now move to a new technology like 5G.

Breaking the monolith

To truly appreciate the significance of Open Radio Access Network (O-RAN)—a RAN interface that supports interoperation between vendors’ equipment—one must first understand how RAN architecture has evolved through the years.

Traditional RAN architecture

A typical RAN consists of the baseband unit (BBU), the radio unit (RU), and antennas. Traditionally, all RAN hardware was housed on-site within a mobile tower. These sites were controlled by a base station controller (BSC) residing in the backhaul space and connected to the core network. This type of RAN architecture was more suited for a technology like 2G, the first technology designed for digital mobile communication.

Distributed RAN (D-RAN)

To overcome the coverage limitations of traditional RAN, radio units were split from the rest of the hardware (BBU) while maintaining a single wired connection between the two. The split part, known as the remote radio unit (RRU), was housed closer to the antenna to improve wireless coverage. Vendor monopoly persisted, and hardware design changes were always a vendor choice. This type of RAN architecture was used extensively for 2G, 3G, and 4G technology.

Single RAN

As network technology evolved, co-location of multiple technologies led to the need for new radio units for 2G, 3G, and 4G. At the same time, innovation to support multiple technologies in the same software stack led to the consolidation into a single RAN. This model helped operators modernize their older systems at a lower total cost of ownership (TCO).

Cloud RAN (C-RAN)

The next evolution came with the emergence of Cloud RAN, marking a redistribution of functionalities. The BBU and its software components were now hosted in a centralized cloud environment, while the RRUs remained on-site. Because these could be co-located, the evolution to C-RAN delivered resource efficiencies and minimized costs.

Virtualized RAN (vRAN)

Virtualized RAN represents a decisive shift in RAN innovation by disaggregating the BBU software from BBU hardware. This opened the possibilities of using any COTS hardware, making it vendor neutral. Through network function virtualization (NFV), operators can rapidly deploy new applications and services, scale resources, and improve reliability.

A New Era Unfolds: Open RAN

Historically, RAN vendors used proprietary equipment with tightly coupled hardware and software. Because they controlled the distribution, use, access, service, and maintenance of the RAN, operators were heavily dependent on their vendors for advances and upgrades. This hindered their ability to innovate as proprietary RAN cannot sync with other equipment, leading to vendor lock-in and higher TCO.

The good news is that today, radio access networks are on the cusp of change thanks to the Open RAN movement that brings together vendors, software developers, telcos, and more to develop new RAN prototypes based on open-source, open architecture, and open networks.

According to the Telecom Infra Project, “OpenRAN is a vendor-neutral disaggregation of RAN at both the hardware and software levels on general-purpose processor-based platforms.” It breaks all proprietary bonds between hardware, virtualized components, and even software, exposing all interfaces and connections. This deconstruction provides an open playground for true innovation.

Potential opportunities

Despite investing in network upgrades and greater data throughput, the revenue from data services has increased only marginally over the past few years. To remain profitable, operators must reduce operational and capital expenses (OPEX and CAPEX), an opportunity afforded by O-RAN in the following ways.

Enhance service agility

O-RAN provides a commonality among heterogeneous resources, allowing operators to take advantage of market trends and user behavior by deploying services quickly.

Elevate network management

O-RAN orchestration supports automation by allowing programmable creation and deployment of containerized resources to meet service-level requirements of ultra-reliable and low latency communications (URLLC) and enhanced mobile broadband (eMBB) slices. As deep intelligence penetrates RAN architecture, it will create AI-based closed-loop automation to support faster decision-making to enhance the overall network-management process.

Eliminate proprietary vendor monopolies

With vendors free to produce flexible future-proof hardware, operators can further exploit the spectrum. They may section spectrum for different industries or dense user hotspots and provision this dynamically for greater quality of service, quality of experience, and customer stickiness.

CAPEX reduction

Open RAN primarily involves disaggregating traditional fit-for-purpose solutions into off-the-shelf hardware and open-standards-driven software, thereby enabling a larger ecosystem of vendors and improving vendor diversity. The combination of commercial off-the-shelf (COTS) hardware and standards-driven solutions is expected to offer operators a significant gain in CAPEX reduction. Studies indicate that the traditional RAN domain is easily the most expensive part of a mobile network, representing 65 to 70 percent of its total cost. According to Deloitte, Open RAN can reduce CAPEX by 40 to 50 percent. The open standard promotes faster innovation cycles, improves supply chain diversity, and encourages automation of network operations to enable a lower overall network TCO.

However, it is important to note that the diversity and larger ecosystem afforded by O-RAN can create integration challenges if not well-orchestrated or limited by hardware choices. As the network becomes increasingly software-driven, it becomes imperative to look at integration challenges from a software-driven system view.

AI and ML in Open RAN RIC

Artificial intelligence and machine learning (AI/ML) will have a much more comprehensive and transformative impact on the end-to-end network in an O-RAN environment. The O-RAN Alliance specifications provide a framework to use AI and ML to optimize radio resources in LTE and 5G networks. The framework heavily relies on AI/ML technologies to improve performance and operation automation through intelligent algorithms that improve the system continuously. This is done through applications hosted on the RAN Intelligent Controller (RIC) platform, which can be implemented for near real-time control and non-real-time control. AI-enabled policies and ML-based models generate messages in non-RT RIC and are conveyed to the near-RT RIC.

RIC is evolving, and projects are ongoing

RIC is evolving, and a number of new initiatives have come to the fore. For example, at the end of August 2020, the Open Networking Foundation (ONF) introduced a software defined radio access network (SD-RAN) project to develop an open-source Near Real-Time RAN Intelligent Controller (nRT-RIC) that is compatible with the O-RAN architecture. In September 2020, Samsung and KDDI demonstrated a network slicing use case involving an RIC to manage radio resources to guarantee required service levels.

The TIP OpenRAN 5G NR Project Group is also active, with the launch of its RAN Intelligence and Automation (RIA) subgroup to develop and deploy AI/ML-based applications (as xApps) for a variety of RAN use cases, including radio resource management, massive MIMO, quality of experience, optimization, and more.

AI/ML-based closed-loop automation

Because Open RAN provides flexibility in terms of disaggregation and interfaces, it can optimally use AI/ML for optimization and automation in a way that these actions are not guided but are fully closed-loop automation. Open RAN provides multiple touchpoints in terms of open interfaces to perform data collection and enrichment information, which can be used for model training to enable intelligent feedback mechanisms to enable AI/ML-based closed-loop automation. Open RAN supports open APIs like xApps and rApps for real-time and non-real-time model implementation and decision-making, which allows the accommodation of multiple models and the selection of the best-suited solution for the use case.

The overall approach drift and AI/ML-enabled closed-loop automation would help in reducing OPEX through advanced and adaptive self-managing capabilities, which would help in accelerated time-to-value and reduced risk of human errors.

The O-RAN future

The RAN ecosystem has evolved significantly at each stage of mobile network technology transformation, from the days of 2G, to now, the inception of 5G. As 5G moves toward becoming mainstream, Open RAN at the network edge is expected to benefit applications, including autonomous vehicles and Internet of Things (IoT) solutions.

ABI Research has predicted that Open RAN CAPEX spending will overtake traditional RAN spending by 2028. Leading European telecommunications operators, including Deutsche Telekom, Orange, Telefónica and Vodafone, have already committed to deploying Open RAN as part of their 5G rollouts. The open standards promoted by the O-RAN Alliance will allow the development of open interfaces and faster deployment of radio access networks by leveraging technologies such as AI/ML and real-time analytics. Additionally, Open RAN brings considerable innovation potential to the telecommunications industry by creating an open ground for innovation, not just for traditional RAN vendors but also for new players and startups, ensuring revolution in network economics as we know it today.

See how our Subex Capacity Management can help your organization

Check out now!

Today for Communication Service Providers (CSPs), moving to 5G is quickly becoming a necessity. Consequentially, this has led to a need for CSPs to ensure that they are well equipped to cover both expectations and the customer needs that 5G promises.

5G comes with a host of new services and business models. For CSPs to capitalize on the 5G opportunity and ensure a more significant market share, it would be important to understand how their networks will need to evolve to meet the rise in demand and traffic. At the same time, CSPs continue to amortize their 4G deployments, and this has made it paramount that customer experience on 4G is not affected as CSPs move closer to a 5G deployment.

The above elements represent a significant challenge for all different departments involved in the 5G deployment. The Radio Optimization team is probably the most impacted one, as they need to address several aspects, such as:

• Accelerating the learning phase with respect to 5G technology
• Maintaining QoE and QoS during the new technology integration, while switching off frequency carriers from legacy technologies, or even switching off a specific legacy technology (2G or 3G) in order to make most of the new spectrum scenario that comes with 5G
• Releasing new services to support new business needs: Fixed Wireless Access, Massive IoT, LTE Advanced, Massive MIMO, Network Slicing, Private Networks, etc.

Today, most of the optimization processes implemented consider data from PM Counters, Call Traces, Probes, Crowdsourcing solutions, Drive tests, etc. Hence, network KPIs built on data for network performance, CX, and network quality are generally used to provide insights to organize and prioritize actions, such as geolocation data, VIP Subscribers, Roamers, etc. However, these earlier methodologies, which were used to perform radio optimization for legacy technologies, are no longer sufficient to cater to all the needs indicated above and the new use cases that come with 5G.

To explain why we need to take a step back.

One of the main advantages 5G offers comes from introducing the possibility to create several tailored use cases that will open doors for newer revenue streams. However, managing the capacity to control the multiple performance indicators inherent to these new services will be significantly complex, as each particular use case will need very specific KPIs and SLAs to be monitored to maintain the high performance; KPIs which are not covered as part of the above-mentioned network KPIs.

Moreover, 5G will also facilitate network slices for different services or use cases, which will call for adding new analytics techniques and leveraging new data sources to assure a seamless customer experience, enhance profitability, and gain a competitive advantage.

For these reasons, it will be necessary for CSPs to maximize automation as much as possible to ensure RAN optimization for 5G. Here is where it will be important for CSPs to couple network KPIs with business data to prioritize and enhance the necessary optimization actions to meet the business needs as well as forecast and address the demand for new services built on 5G.

Generating holistic, actionable insights for improved decision making is only possible by correlating and enriching data from the different areas (Network, Finance, and Customer Experience), applying advanced machine learning techniques, defining the rules engine, and leveraging ML/DL models under the expertise of both data-scientists and domain experts.

Business data-driven optimization will ensure that radio teams focus their efforts towards maintaining high levels of QoE, QoS and CX for the most relevant revenue streams. Adopting an intelligent approach to RAN optimization can ensure that the ROI from different network elements can be easily tracked, managed and augmented. This can help CSPs ensure that their network Capex is optimized while bringing in a significant reduction in operational costs for RAN Optimization.

Learn About the 3 Strategic Pillars to Service-based Network Analytics

Read this Whitepaper

Each day, as every skier knows, can present new conditions and a fresh set of challenges. The weather can be sunny, blustery or confront you with a whiteout due to heavy snow and wind. The slopes might be icy and hard-packed (recalling learning to ski in Eastern Pennsylvania), or you may be blessed with “champagne powder” (which we live for here in the Rocky Mountain West). Poor coverage can expose rocks, bare patches, and other obstacles.

I took the above photo at one of my favorite Colorado resorts. The “EX” at the top of the sign means this is an extreme expert slope.

Skier beware — know your limits.

Right about now you’re probably thinking “Andy, I see where this is going… metaphor ahead!”

I could get a bit heavy-handed and compare the challenging alpine environment to your network—and chair lifts to your need to manage traffic and capacity constraints. But I’ll keep it simple.

Recognizing and overcoming obstacles is crucial to the success of any network transformation program.

I’ve been part of numerous network transformations over a 30+ year career. I recall when ISDN was going to change our world. What I find most interesting now is the confluence of multiple trends and technology shifts.

We used to have the luxury to handle one major shift at a time – think PDH to SDH/SONET and then to MPLS and IP networks. On the mobile side, we’ve had the stepwise progression of ‘G’s. Of course, it’s not generally this clean. Each generation doesn’t readily give way to the next, rather there is often an awkward, inefficient, and expensive co-existence among technologies.

Consider the present era, and the transformational forces underway in the telecom industry.

Here is a sampling.

• Dedicated network elements to White boxes and virtualized functions
• Proprietary code to Open source driven by communities of interest
• SDH/SONET to IP networks (sometimes with CEM as a stop gap)
• 2G/3G to 4G (many developing markets)
• Network performance focus (3G/4G) to Enterprise use case focus (5G)
• Central offices to Web scale data centers
• On-premise computing to Cloud & edge computing
• Manual processes to Closed loop automation enabled by AI
• Internet for cat videos and Instagram influencers to Internet of Things & smart cities

I’m sure I’ve missed a few. What would you add to this list?

Here’s the scary news… the pace at which transformational forces will compete for our attention is only going to accelerate.

It’s inevitable. Wheels are in motion.

AI and automation are accelerating the pace of innovation. Companies must embrace innovation to compete and, indeed, survive. Historical transformational cycles of 5-15 years (depending on the technology) will soon appear to be almost continuous.

Ray Kurzweil, noted author and futurist, addresses this pace of change in his book The Singularity is Near. He argues that the rate of paradigm change is doubling every decade. In 2030, the paradigm shift rate will be 2x what it was in 2020. In 2040, the rate will be 4x, and so on.

This means if you are stuck in a planning cycle for your next network transformation or moving forward with acknowledged (or unknown) blind spots—a bad situation now could become insurmountable in the future.

So, let’s get back to those obstacles (moguls?) for transformational network change. What might get in your way? How can you ski smoothly over them without turning into a yard sale? (Sorry, a little ski humor.)

Falling prey to inertia

Consider legacy TDM networks. Many large, incumbent operators continue to run these networks despite aging equipment (with difficult to find spare parts), high energy and real estate costs, and a dearth of qualified technicians due to a retiring work force.

These problems will only be exacerbated with time.

Better to proactively retire old networks, reap the cost savings, and enable the operational benefits of IP networks and SDNs.

Not knowing your cost structures

Every significant move made by a telco requires a business case. One might know in principle that a certain project makes sense, but show me the numbers. Network transformation projects are generally not going to be exempted from such fiscal scrutiny.

I expect you already have access to certain costs—e.g., real estate, power, field force, Capex for network assets, etc. A best practice is to know your cost structure at a product and services level.

You’re not in business to build a network. You exist to delight customers with products they need and with competitive rate plans.  If you know what it costs to deliver a service now and after a network transformation, your business case becomes easier.

The trick is to understand all your cost components. Most of your competitors only take educated guesses (trust me).

If you get this right, you will have a business insights edge that may be more valuable than your technology edge.

Examples of things you should know:

• What granular costs (Opex and Capex) should be assigned to each product and service?
• What are the margins for each product and service (including network costs)?
• What is the ROI of each of my sites?
• What is my return on assets?
• Which assets are underperforming?
• If I virtualize certain functions (e.g., onboard VNFs) will I trade Opex pain for Capex savings? This is really a separate discussion but thought I would fold it in. There’s no free lunch. While virtualization is certainly a growing trend, make sure you understand the costs of any operational complexities that arise when you replace the convenience of purpose-built OEM platforms.

Not knowing your network

You should have the data to know:

• What assets do I have in the network (what, where, when, and why)?
• What is each asset doing? What are the numbers? — Capacity, utilization, history/trends, contribution to revenue, etc.
• What is my network topology?
• How are services carried on my network and how do they map to my infrastructure?

There are many operational parameters you should know about your network which tilt more toward planning, optimization, and fault management. I haven’t listed them here since my context is on preparing for transformation but there is certainly room to consider many other types of data.

Migrating boxes, not services

There is a tendency to think about network transformations in terms of technology. For example, you will be replacing SDH/SONET network elements such as DACS and ADMs with routers and IP switches. In fact, many fixed line transformations have taken this approach—one box at a time.

This is inefficient and can show a lack of empathy for the customer.

Any transformation carries risk of disrupting customer services. Let’s consider the migration of a TDM network to IP. The recommended best practice for a TDM migration is to swing end-end services. This minimizes the risk of outages since each circuit is touched once during the migration, and the customer is taken into consideration during every phase of planning, execution and testing. This approach can also reduce cost and schedule by executing with an end-to-end view of the network.

As I write this, much of Colorado is settling in for an epic 2-day snow storm. I’m hoping for another ski day in my near future. But that will mean dealing with heavy skier traffic since everyone here will have the same idea. Alas, I-70 (the highway between Denver and ski areas to the West) is one “network connection” in serious need of transformation!

Are you prepared for your next transformation program?

Talk to an expert now!