Over the past few years, the role of technology in the day-to-day lives of people has expanded. Key trends such as increased distribution and consu­mption of video and multimedia servi­ces, growth in digital payments, uptake of mo­bile gaming and other user engagement platforms have all contributed to­wards the generation of more complex and dynamic traffic patterns that impose new requirements on modern networks.

Given the context, the need to make networks more agile, scalable and adaptable has become more apparent now than ever. Therefore, operators are now inc­reasingly looking at solutions such as open RAN (O-RAN)  and cloud in an eff­ort to modernise their network infrastructure. Telecom operators all over the world are warming up to the idea of replacing their legacy radio access networks (RANs) with O-RAN as they look to lower their capex and opex amidst rising capital in­ten­sity and subdued subscriber and reve­nue growth. By disaggregating the software and hardware eleme­nts of networks, O-RAN has the pot­ential to reduce operators’ dependency on a single vendor and bring down network-re­lated costs. Fur­ther, by enabling operators to in­crease the number of their network infrastructure partners, O-RAN can help operators bu­ild better and more cost-effective 5G networks. Further, op­erators are ex­plo­ring the idea of tying up their O-RAN de­ploy­ments with new-age technologies such as AI, ML, big data, cloud and virtualisation to automate the software components of their O-RAN ar­chi­tecture. Besi­des en­han­­cing operational efficiency, the use of these technologies is helping operators make their networks more intelligent and scalable.

A look at some of the key technologies being deployed by operators across O-RAN architectures and their benefits…

Use of AI and ML

O-RAN solutions can apply data science leveraging AI/ML technologies to significantly improve performance, and operation automation, through algorithms that learn from experience and continuously im­­­prove the system. As such, operators have started harnessing advanced AI and ML applications to improve the network performance of O-RAN and enhance end-user experience. O-RAN gives much gr­eater flexibility to integrate AI and ML algorithms into RAN management. AI al­go­rithms help operators analyse vast amounts of traffic data and network load in real time, without impacting the capacity of the network. This makes it possible to obtain instant traffic predictions in the network, without the need for extra hardware or manual site visits. AI and ML are currently being used for forecasting quality parameters, detecting anomalies in the system and predicting failures. Further, with the help of AI and ML, operators are able to adjust network conditions, thereby ensuring proper load balancing and seamless transfer of an active call or data session from one cell in a cellular network or from one channel to another.

O-RAN provides flexibility in terms of disaggregation and interfaces and, therefore, it can optimally use AI/ML for optimisation and automation. O-RAN provides multiple touchpoints in terms of open interfaces to perform data collection and information enrichment. This  can be used for model training to enable intelligent feedback mechanisms for 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 selection of the best-suited solution for the use case.

Going forward, many RAN features, which traditionally have been manually programmed, will rely on AI capabilities to handle the increasing complexity of current and future networks.

Use of big data analytics

With the use of big data analytics in an O-RAN system, operators can obtain a visual representation of patterns and abnormalities in their networks and enable network intelligence across all the O-RAN network elements, including the O-RAN contr­o­ller, edge core and security gateway pr­oduct suites. The technology can be used to store, process and analyse a large am­ount of complex data, both structured as well as unstructured, and the insights from the same could then be used to enhance the service quality for retail end-users and enterprises. Several operators have already started using big data solutions to ensure fast visibility and analysis to accelerate network optimisation and fault resolution. By obtaining massive, dynamic network maps and multidimensional analytics that up­date in seconds, operators are able to ac­hieve in-depth multilayer troubleshooting from the core to the cell site and connected devices.

Use of virtualisation

A fully virtualised RAN (vRAN) can bring the advantage of harmonisation, which entails one single uniform hardware platform across the core network, RAN and edge. This can simplify the management of the complete network, reducing operations and maintenance costs. Further, in a full vRAN, the network functions are separated from the processing hardware. This means that RAN network functions provided by multiple vendors could run on the same hardware, increasing the flexibility for the service provider. In some cases, the hardware could even be shared between service providers.

In addition, vRAN offers an opportunity to embrace established solutions, available in public cloud technologies, for non-RAN-specific functions. By using industry-established components for common tasks, the need for costly adaptations of vendor-specific solutions can be remo­ved. If this is achieved, it would allow the RAN ecosystem to focus on business-critical components. Moreover, a vRAN off­ers increased flexibility as far as the dep­loyment of enhanced functionality and capacity is concerned. Cloud technologies could facilitate this type of flexibility. Fi­nally, a widely adopted open platform cou­ld reduce barriers for cross-domain innovation, facilitating the development of new use cases and services.

Use of cloud

A cloud-native O-RAN solution enables automation, which is required to simplify network management and ensure scalable and agile network operations. Moreover, it ensures automated orchestration and management, providing long-term benefits for mobile network operators. These benefits include zero-touch provisioning, continuous integration/continuous delivery (CI/ CD), AI, and ML-enabled network monitoring and optimisation.

In a cloud-native system, applications can be developed and operated in virtual cloud environments. Further, applications in such a system can be carved up into sm­aller units called microservices and a group of smaller and interconnected mi­cro­services can then be used to replace lar­ge applications of a traditional RAN. The cloud-native model enables workflow or­chestration and network automation that facilitates easy deployment of applications, scale-up of systems and repair of network faults. This is extremely beneficial for re­mote locations that are otherwise difficult to serve without manual intervention. Several major cloud vendors such as Ama­zon, Google and Microsoft have partnered with telecom operators globally to facilitate the migration to cloud-native O-RANs. Industry experts believe that the in­volvement of big public cloud providers is likely to provide a huge impetus to O-RAN adoption. In fact, telecom operators have started leveraging recent advancements in cloud technology such as edge computing to improve their O-RAN experience. Edge computing is a distributed computing framework that brings computation and data storage closer to the data sources. In an O-RAN framework, edge computing can help operators virtualise their networks and run internal operations more efficiently.

The way forward

The concept of building open networks seems to be gaining traction among global as well as Indian telecom operators. As per industry experts, the number of O-RAN-based radio units (RUs) deployed by operators and private networks will grow to more than 800,000 in 2025 from only 122,000 RUs in 2020. In the coming years, O-RAN is expected to help save money in multiple market segments, including both high capacity applications and coverage-limited applications. When this happens, telcos would look to apply the O-RAN business model to both rural as well as urban areas in many mainstream markets. However, this open network expansion would depend on the continued growth of a healthy ecosystem that would require adding new suppliers and innovations to this developing market.