putilov_denis - stock.adobe.com
New technologies, as well as the complex distributed nature of most network environments, have complicated network management. Ironically, to overcome this complexity, some enterprises are incorporating even more technologies -- including AI and machine learning, or ML -- within their network architectures.
Enterprises aren't the only ones facing this quandary with network management. Mobile network operators (MNOs) also experience complexity within their networks, including with 5G network deployment. But MNOs are evaluating newer technologies to simplify operations.
One way in which operators are attempting to reduce complexity is through open radio access network (Open RAN). With Open RAN architecture, operators use non-proprietary equipment to improve interoperability, reduce costs and increase programmability.
In a recent webinar, "How to Automate Operations Predictive AI/ML and Open RAN," Brian Walsh -- product marketing manager at Parallel Wireless -- discussed how MNOs can benefit from using AI and ML in Open RAN, with cellular to address complex operations.
"Open RAN and new approaches in AI and ML can help mobile operators optimize operations in their networks, while reducing costs and complexity," Walsh said.
According to Walsh, MNOs face pressure to evolve business operations to increase profits and differentiate themselves from competitors. On top of these challenges, new technologies like 5G have given end users higher expectations for the quality of service they can expect from providers.
Some of those expectations include the following:
- high throughput
- low latency
- network modernization
- quality and consistency
"Mobile operators must find new ways to increase their margin and improve network operational efficiencies with a more flexible and agile service delivery environment, while reducing both Capex and Opex," Walsh said.
But providing these network services increases both costs and complexity, Walsh said. For example, using 5G and previous generations of cellular connectivity -- such as 3G and 4G -- to support access networks requires higher RAN capacity and denser networks.
Network densification -- the process of adding more cell towers to increase the capacity of a network -- can improve connectivity and reliability, among other benefits. However, the challenge of densification is it's difficult for operators to receive permission to set up new cell sites. But 5G networks are predicted to be 100 times denser than 3G networks, and densification is critical to deploy 5G and achieve its benefits, Walsh said.
AI and ML in Open RAN can enable self-optimization
Open RAN architectures enable operators to provide network self-optimization capabilities, which use automation to manage a network more efficiently. Walsh outlined the following four components that help boost network efficiency:
- AI and ML
Automating network tasks and zero-touch provisioning can simplify network operations and management, Walsh said. Operators use automation to increase the scale of their operations without employing more staff.
One advancement with Open RAN architecture is the incorporation of ML frameworks. For example, the RAN intelligent controller enables operators to control the RAN programmatically both in and out of real time.
Open RAN applications support ML models, which automate the network and make data-driven decisions. According to Walsh, either third-party organizations or MNOs can develop the Open RAN applications.
4. AI and ML
Predictive AI and ML models use algorithms to process data by analyzing previous and current data events and finding patterns. Implementing these tools and automation within Open RAN architectures helps eliminate human error and serves as a significant advancement in the networking industry, Walsh said.
Open RAN deployment challenges
Ideally, according to Walsh, combining the four components above results in the creation of intelligent, self-optimizing networks.
But skepticism over Open RAN remains, despite the use cases. Similar to AI and ML, Open RAN is a recent development in the networking world, and MNOs are hesitant to implement it. A study from Mobile World Live, together with Aspire Technology, surveyed 370 operators from various industries and found that operators are split on deploying Open RAN.
Much of that reluctance stems from the fact that operators are uninformed about the technology. An estimated 57% of respondents said they need to learn more about Open RAN or aren't familiar with the technology at all. Research from Eightfold AI reaffirms this; according to a study taken from a dataset of 500,000 telecom employee profiles, 33% of network engineer and operations roles aren't equipped to deliver innovative offerings. Some of those offerings include emerging networking technology trends, such as 5G and Open RAN.
Future of AI and ML in Open RAN 5G
Experts predict the Open RAN market will boom as the technology develops, and the skills and knowledge gaps will likely shrink within that timeframe. The majority of respondents told Mobile World Live they believe Open RAN requires two to five more years of maturation before large-scale deployments can occur. More vendors may also have services to integrate Open RAN 5G with AI and ML by that time.
Parallel Wireless, for example, currently offers Open RAN cloud architecture that supports 5G and previous cellular generations, coupled with AI and ML frameworks, to help operators modernize their networks. Parallel Wireless isn't the only vendor to progress in this area, however. Other players in the industry are starting to make headway in automating Open RAN-enabled 5G networks.
In February 2022, Anuta Networks revealed ATOM, its standalone 5G network configured with Open RAN as a service. According to Anuta, ATOM incorporates AI and ML predictive analytic tools, among other features. In late 2021, Ericsson announced its Intelligent Automation Platform, a service that adds automation capabilities to both traditional and RAN 4G and 5G networks -- Open RAN included.