...
| Table of Contents | ||||
|---|---|---|---|---|
|
Executive Summary - Overview and Key Takeaways
0.25 page – Beth Cohen will fill in when the paper is mostly complete.
...
The future of Intelligent Networking and AI is in the hands of the individuals and organizations who are willing and able to contribute to new and existing projects and initiatives. If you are involved in building and operating networks, developing network technology or consuming network services, consider getting involved. Engaging with the LFN projects and communities can be an educational and rewarding way to shape the future of Intelligent Networking.
Key Takeaways
- Intelligent networking is rapidly moving out of the lab and being deployed directly into production
- Operational maintenance, and service assurance are still a priority, but there is increasing interest in using AI/ML to drive network optimization and efficiency
- More research and development is needed to establish industry wide best practices and a shared understanding of intelligent networking to support interoperability.
- There has been some work on developing common or shared data sources and standards, but it remains a challenge
- LFN and the Open Source community are key contributors to furthering the development of intelligent networking now and in the future
Background and History
0.5 page
At their core, telecoms are technology companies driven by the need to scale their networks to service millions of users, reliably, transparently and efficiently. To achieve these ambitious goals, they need to optimize their networks by incorporating the latest technologies to feed the connected world's insatiable appetite for ever more bandwidth. To do this efficiently, the networks themselves need to become more intelligent. At the end of 2021, a bit over 2.5 years ago, LFN published its first white paper on the state of intelligent networking in the telecom industry. Based on a survey of over 70 of its telecom community members, the findings pointed to a still nascent field made up of mostly research projects and lab experiments, with a few operational deployments related to automation and faster ticket resolutions. The survey did highlight the keen interest its respondents had in intelligent networking, machine learning and its promise for the future of the telecom industry in general.
...
- How to create and maintain public Networking data sets for research and development of AI applications? (Ranked #1 in GB member survey)
- What are some feasible goals (short term) in creation of AI powered Network Operations technologies
- Evaluate the existing Networking AI assets coming from member company contributions
- Analyze generic base AI models and recommend the creation of Network specific base models (Ranked high in GB member survey)
- Recommended approaches and the potential for open source projects to contribute to the next generation of intelligent networking tools.
Challenges and Opportunities
1 page - Focus on Telco pain points only
Ironically, as generative AI and LLM adoption becomes more widespread in many industries, telecom has lagged somewhat due to a number of valid factors. As was covered in the previous white paper, the overall industry challenges remain the same, that is the constant pressure to increase the efficiency and capacity of operators’ infrastructures to deliver more services to customers for lower operational costs. The complexity and lack of a common standard understanding of network traffic data remains a barrier for the industry to speed the adoption of AI/ML to optimize network service delivery. Some of the challenges that are motivating continued research and adoption of intelligent networking in the industry include:
Common Telecom Pain Points
- Operational Efficiency: The continuing need to reduce costs and errors, potentially increase margins
- Network Automation: Right-sizing network hardware and software, optimizing location placement
- Availability: Identifying single points of failure in systems to improve equipment maintenance efficiency
- Capacity Planning: Avoid unnecessary upgrades or poor network performance from overloaded nodes.
Challenges to Achieving Full Autonomy
0.5 page Lingli Deng Andrei Agapi
...
- Need for High Quality Structured Data: Telecommunications networks are very different from other AI human-computer data sets, in that a large number of interactions between systems use structured data. However, due to the complexity of network systems and differences in vendor implementations, the degree of standardization of these structured data is currently very low, causing "information islands" that cannot be uniformly "interpreted" across the systems. There is a lack of "standard bridge" to establish correlation between them, and it cannot be used as effective input to incubate modern data-driven AI/ML applications.
- AI Trustworthiness: In order to meet carrier-level reliability requirements, network operation management needs to be strict, precise, and prudent. Although operators have introduced various automation methods in the process of building autonomous networks, organizations with real people are still responsible for ensuring the quality of communication and network services. In other words, AI is still assisting people and is not advanced enough to replace people. Not only because the loss caused by the AI algorithm itself cannot be defined as the responsible party (the developer or the user of the algorithm), but also because the deep learning models based on the AI/ML algorithms themselves are based on mathematical statistical characteristics, resulting in sometimes erratic behavior, meaning the credibility of the results can be difficult to determine.
- Uneconomic Uneconomical Margin Costs: According to the analysis and research in the Intelligent Networking, AI and Machine Learning While Paper , there are a large number of potential network AI technology application scenarios, but to independently build a customized data-driven AI/ML model for each specific scenario, is uneconomical and hence unsustainable, both for research and operations. Determining how to build an effective business model between basic computing power providers, general AI/ML capability providers and algorithm application consumers is an essential prerequisite for its effective application in the field.
- Unsupportable Research Models: Compared with traditional data-driven dedicated AI/ML models in specific scenarios, the research and operation of large language models have higher requirements for pre-training data scales, training computing power cluster scale, fine-tuning engineering and other resource requirements, energy consumption, management and maintenance, etc. It is difficult to determine if it is possible to build a shared research and development application, operation and maintenance model for the telecommunications industry so that it can become a stepping stone for operators to realize useful autonomous networks.
- Contextual data setsData Sets: Another hurtle that is often overlooked is the need for the networking data sets to be understood in context. What that means is that networks need to work with all the layers of the IT stack, including but not limited to:
- Applications: Making sure that customer applications perform as expected withe underlying network
- Security: More important than ever as attack vector expand and customers expect the networks to be protected
- Interoperability: The data sets must support transparent interoperability with other operators, cloud providers and other systems in the telecom ecosystem
- OSS/BSS Systems: The operational and business applications that support network services
- Community Unity and Standards: Although equipment manufacturers can provide many domain AI solutions for professional networks/single-point equipment, these solutions are limited in "field of view" and cannot solve problems that require a "global view" such as end-to-end service quality assurance and rapid response to faults. . Operators need to aggregate management and maintenance data in various network domains by building a unified data sharing platform, and based on this, further provide a unified computing resource pool, basic AI algorithms and inference platform (i.e. cross-domain AI platform) for scenario-specific AI, end-to-end scenarios, and intra-domain scenarios using an applied reasoning platform.
Emerging Opportunities
The Telecoms have been working on converged infrastructure for a while. Voice over IP has long been an industry standard, but there is far more than can be done to drive even more efficiencies with network and infrastructure convergence.
Converged infrastructure is needed to support the growth and sustainability of AI. This is particularly important in the need for a single solution designed to integrate compute, storage, networking, and virtualization. Data volumes are trending to grow beyond hyperscale data, and with such massive data processing requirements the ability to execute is critical. The demands on existing infrastructure are already heavy., so bringing everything together to work in concert will be key, to maintain and grow support the growth in demand for resources. In order to do that the components will need to work together efficiently and the network will play an important role in linking specialized hardware accelerators like GPUs (Graphics Processing Units) or TPUs (Tensor Processing Units) to accelerate AI workloads beyond current capability. Converged infrastructure solutions will lead to the ability to deploy AI models faster, iterate them more efficiently, and extract insights faster. This can will pave the way for the next generation of AI.
Converged Service and integrated solutions that combine AI with traditional services has have the potential to deliver enhanced services to end customers, but more importantly these services need to leverage AI-driven insights, automation, and personalization to optimize user experience, improve efficiency, and drive innovation across industries. There are many existing industry use cases for this already, which include healthcare, legal, retail, telecommunications, networking, and incidence incident tracking. The analytics delivered by a converged service provide automated insights and tools that can provide real-time analysis, tracking, response and remediation/response–either with or without human intervention.
Business Innovation - New Revenue Streams: Data monetization encompasses various strategies, including selling the raw data, offering data analytics services, and developing data-driven products or solutions to customers. Organizations can monetize their data by identifying valuable insights, patterns, or trends hidden within their datasets that no group of human resources can possibly identify quickly. These insights can then be used to create new products and services that will better serve customers and organizations. This is a new strategic business opportunity for organizations looking to monetize anonymous data and leverage it for increased business efficiency and to determine product direction and determine new go to market strategies.
Data Privacy and Security: The ability to monetize the data comes with a big caveat, which is that the use of customer data must be handled with care to ensure data privacy, security and regulatory compliance. This requires clear policies and security procedures to ensure anonymity, safety and privacy at all times. The good news is that AI can be used to address the growing threat of network vulnerabilities, zero day exploits and other security related issues with predictive analytics and threat analysis.
Complex Data Model Simplification: Large language models can be used to understand large amounts of unstructured operation and maintenance data (for example, system logs, operation and maintenance work orders, operation guides, company documents, etc., which are traditionally used in human-computer interaction or human-to-human collaboration scenarios), from which effective knowledge is extracted to provide guidance for guide further automatic/intelligent operation and maintenance, thereby effectively expanding the scope of the application of autonomous mechanism.
Brief Overview of AI Research in Context
Lingli DengAndrei Agapi Sandeep Panesar
...
This breakthrough in AI research is characterized by vast amounts of easily accessible data, extensive training models, and the ability to quickly generate human-like text, in almost an instant. These models are trained on enormous datasets from sources particular to a given area of research. LLMs have changed the way natural language processing tasks are interpreted. Some of the areas that have been particularly fruitful includeincluding: text generation, language translation, summarization, and automated chatbots, image and video generation, and routine query responses/search results.
Generative AI (Gen AI)
Gen AI is a much broader category of artificial intelligence systems capable of generating new content, ideas, or solutions autonomously based on a human text, video, image or sound-based input. This includes LLMs as resource data for content generation. As such, Gen AI seems to be able to produce human-like creative content in a fraction of the time. Content creation for web siteswebsites, images, videos, and music are a few of the capabilities of Gen AI. The rise of Gen AI has inspired numerous opportunities for business cases, from creating corporate logos , to corporate videos , to saleable products to end-consumers and businesses , to creating visual network maps based on the basis of the datasets being accessed. Further, even being able to provide optimized maps for implementation to improve networking either autonomous or with human intervention are useful areas for further exploration.
The two combined open the question as to what should Gen AI be used for, and more importantly how is it distinguishable from human work. There are many Many regulatory bodies are looking at solutions around the identification of decisions and what content has been generated to solve a particular problem and solution. The foundation of this combination is to ensure security , and safety, mitigate biases, and identify which behaviors were illustrated and acted upon by Gen AI, and which were not.
The advent of transformer models and attention mechanisms [1][2] and the sudden popularity of ChatGPT and other LLMs, transfer learning, and foundation models in the NLP domain have all sparked vivid discussions and efforts to apply generative models in many other domains. Interestingly, let us not forget that word embeddings [3][4][5], sequence models such as LSTMs [6] and GRUs [7], sequence models such as LSTMs and GRUs, attention mechanisms [8], transformer models [1] and pretrained pre trained LLMs [2] have been around long before the launch of the ChatGPT tool in late 2022. Pretrained transformers like BERT [2] in particular (especially transformer-encoder models) were widely used in NLP for tasks like sentiment analysis, text classification [9], extractive question answering [10] etc. long before ChatGPT made chatbots and decoder-based generative models go viral. That said, there has clearly been a spectacular explosion of academic research, commercial activity, and ecosystems that have emerged since ChatGPT was launched to the public, in the area of both open [11][12] and closed source [13][14][15] LLM foundation models, related software, services and training datasets.
Beyond typical chatbot-style applications, LLMs have been extended to generate code [16][17][18][19], solve math problems (stated either formally or informally) [20], pass science exams [21], or act as incipient "AGI"-style agents for different tasks, including advising on investment strategies, or setting up a small business [22]. Recent advancements to the basic LLM text generation model include instruction finetuning [23], retrieval augmented generation using external vector stores [24][25], using external tools such as web search [26], external knowledge databases or other APIs for grounding models, code interpreters [27], calculators and formal reasoning tools [28]. Beyond LLMs and NLP, transformers have also been used to handle non-textual data, such as images, sound, and arbitrary sequence data.
Intelligent Networking Differences
A natural question arises on how the power of LLMs can be harnessed for problems and applications related to Intelligent Networking, network automation and for operating and optimizing telecommunication networks in general, at any level of the network stack. Datasets in telco-related applications have a few particularities unique to the industry. For one, the data one might encounter ranges from fully structured (e.g. code, scripts, configuration, or time series KPIs), to semi-structured (syslogs, design templates etc.), to unstructured data (design documents and specifications, Wikis, Github issues, emails, chatbot conversations).
...
In addition to general domain adaptation, many telcos will have the issue of multilingual datasets, where a mix of languages (typically English + something else) will exist in the data (syslogs, wikis, tickets, chat conversations etc.). While many options exist for both generative LLMs [11] and text embedding models [12], not many foundation models have seen enough non-English data in training, thus options in foundation model choice are somewhat restricted for operators working on non-English data. A solution to work around this issue is to use automated translation and language detection models on the data as a preprocessing step.<sorry for the late addition, feel free to edit or delete Andrei Agapi Beth Cohen - added by Jason Hunt >
Beyond these approaches, an emerging technique of for pre-training foundation models on network data holds potential promise. In With this technique, network data is essentially turned into a language via pre-processing and tokenization, which can then be used for pre-training a new "network foundation model." [34] Initial research has successfully demonstrated this technique approach on Domain Name Service (DNS) data [35] and geospatial data [36]. As this area of research matures, it could allow for general purpose network foundation foundational models that can be fine-tuned to answer a variety of questions around network data or configurations without having to train individual models for bespoke network management tasks. <end addition>
In conclusion, while foundation models and transfer learning have been shown to work very well on general human language when pre-training is done on large corpuses of human text (such as Wikipedia, or the Pile [29]), it remains an open question to be answered whether domain adaptation and downstream task adaptation work equally well on the kinds of domain-specific, semi-structured, mixed modality datasets we find in the telecom industry. To enable this, telecoms should focus on standardization and data governance efforts, such as standardized and unified data collection policies and developing high quality structured data across a common definition and understanding.
Projects and Research
1.5 page
3GPP Intelligent Radio Access Network (RAN)
The intelligent evolution of wireless access networks is in a phase of rapid evolution and continuous innovation. In June 2022, 3GPP announced the freezing of R17 and described the process diagram of an intelligent RAN in TR37.817, including data collection, model training, model inference, and execution modules, which together form the infrastructure of an intelligent RAN. This promotes the rapid implementation and deployment of 5G RAN intelligence and provides support for intelligent scenarios such as energy saving, load balancing, and mobility optimization.
...
However, despite the remarkable progress made in the 5G wireless access network intelligence industry, some challenges and issues remain to be addressed. For example, network security and data privacy protection are pressing issues that require effective measures to be implemented. The energy consumption issue of 5G networks also needs attention, necessitating technological innovations and energy-saving measures to reduce energy consumption. In the future, continuous efforts should be made in technological innovation, market application, and other aspects to promote the sustainable and healthy development of the 5G wireless access network intelligence industry.
Mobile Core Network Transformation
Mobile core networks can be thought of as the brains of mobile communication. In recent years, these networks have experienced a huge transformation from legacy proprietary hardware to telecom cloud native systems. Today, the majority of mobile core networks are deployed based on telco cloud architectures supported by NFV technologies. Intelligent networking most benefits the packet core networks such as 5GC and UPF which are responsible for packet forwarding, IMS which support delivery of multimedia communications such as voice, message and video, and operational functions that manage the core network itself including telco cloud infrastructure and 5G network applications. There have been three areas where intelligent networking have shown benefits:
Network Intelligence Enables Experience Monetization and Differentiated Operations
For a long time, operators have strived to realize traffic monetization on MBB(Mobile Broadband) networks. However, there are three technical gaps: non-assessable user experience, limited or no dynamic optimization, and no-closed-loop operations. To bridge these gaps, there is a need for an Intelligent Personalized Experience solution, designed to help operators add experience privileges to service packages and better monetize differentiated experiences. Typically in the industry, the user plane on the mobile core network processes and forwards one service flow using one vCPU. As heavy-traffic services increase, such as 2K or 4K HD video and live streaming, microbursts and extremely large network flows become the norm, it becomes more likely that a vCPU will become overloaded, causing packet loss. To address this issue, Intelligent AI supported 5G core networks need to be able to deliver ubiquitous 10 Gbps superior experiences.
Service Intelligence Expands the Profitability of Calling Services
In 2023, New Calling was put into commercial use, based on a 3GPP specification, it can enhance intelligence and data channel (3GPP specification)-based interaction capabilities; it enables users to use multi-modal communications, and helps operators construct more efficient service layouts. In addition, the 3GPP architecture allows users to control digital avatars through voice during calls, delivering a more personalized calling experience. One example where this can be seen as a business opportunity might be an enterprise using the framework to customize their own enterprise ambassador avatar to promote their brand.
O&M Intelligence Achieves High Network Stability and Efficiency
Empowered by the multi-modal large model, the Digital Assistant & Digital Expert (DAE) based AI technology could reduce O&M workload and improve O&M efficiency. It can reshape cloud-based O&M from "experts+tools" to intelligence-centric "DAE+manual assistance". Using the DAE, it is possible that up to 80% of telecommunication operator trouble tickets can be automatically processed, which is far more efficient than the manual processing it is for the most part today. DAE also enables intent-driven O&M, avoiding manual decision-making. Before, it commonly took over five years to train experts in a single domain, with the multi-modal large model it is now possible for it to be trained and updated in mere weeks.
Thoth project - Telco Data Anonymizer
The Thoth project, which is a sub project under the Anuket infrastructure project, has recently focused on a major challenge to the adoption of intelligent networks, the lack of a common data set or an agreement on a common understanding of the data set that is needed. AI has the potential for creating value in terms of enhanced workload availability and improved performance and efficiency for NFV use cases. Thoth's work aims to build machine-Learning models and Tools that can be used by Telecom operators (typically by the operations team). Each of these models is designed to solve a single problem within a particular category. For example, the first category we have chosen is Failure prediction, and the project plans to create 6 models - failure prediction of VMs. Containers, Nodes, Network-Links, Applications, and middleware services. This project also will work on defining a set of data models for each of the decision-making problems, that will help both providers and consumers of the data to collaborate.
How could Open Source Help?
2-3 pages
It is important to understand the current landscape of Open Source Software (OSS) projects and initiatives and how they came into existence to see how OSS is well positioned to address the challenges of Intelligent Networking. Several such initiatives have already laid down the groundwork for building Network AI solutions, or are actively in the process of creating them. Building on these foundations, it is easy to envision the critical role open source software can play in unleashing the power of AI for the future generations of networking. Some of the required technologies are unique to the Networking industry, and will have to be addressed by existing OSS projects on the landscape, or by the creation of additional ones. Some pieces of the technologies are more generic, and will need to come from the broader community of AI OSS. Here is a rough outline of the different layers of Networking AI and the sources for the required technology:
...
In addition, successful development of AI models for use in Networking relies on the availability of data that could be shared under a common license. The Linux Foundation created the Community Data License Agreement (CDLA) for this purpose. Using this license, end users can share data and make it available for researchers, who in turn can further develop the necessary models and applications that benefit the telecom ecosystems and ultimately the end users.
Related Open Source Landscape
1-2 pages
The legal and technical framework for sharing research is important, but what is really essential for driving innovations is the ability for Open Source to provide a forum for creating communities with shared purpose. These communities by allowing people from various companies, diverse skill levels and different cultural perspectives to collaborate, have the potential to spark real innovation in ways that are not really possible in any other context.
...
Experience with OSS in other domains shows that whenever there is an OSS technology that powers commercial products or offerings, there is a need to validate the products to make sure they are properly using the OSS technology and are ready to use in a predictable manner. Such validation/verification programs have existed as part of OSS ecosystems for a while. The Cloud Native Computing Foundation (CNCF) has a successful "Certified Kubernetes" program that helps vendors and end users ensure that Kubernetes distributions provide all the necessary APIs and functionality. A similar approach needs to be applied to any OSS Networking AI projects. Users should have a certain level of confidence, knowing that the OSS based AI Networking solution they use will behave as expected.
Common Vision: Intelligence plane for XG Networks
...
Drawing from the IMT-2030 vision, the integration of AI into mobile networks unlocks transformative capabilities. Advanced human-machine interfaces, such as extended reality (XR) displays and haptic sensors, offer immersive experiences, blurring the boundaries between physical and virtual realms. Intelligent machines, equipped with machine perception and autonomous capabilities, facilitate seamless interactions and drive digital economic growth and societal changes.
Call for Action
0.25 page
The Linux Foundation's role in joining the AI revolution underscores the importance of open-source collaboration in advancing network capabilities. By harnessing open-source technologies, network operators can leverage the collective expertise of the community to accelerate innovation and adoption of AI-driven solutions. This collaborative approach not only democratizes access to advanced AI capabilities but also fosters interoperability and scalability across diverse companies and network environments.
...
- Collaborate on Network Super Blueprints or develop new ones: https://wiki.lfnetworking.org/x/ArAZB
- Work on the Thoth project - Telco Data Anonymizer Project
- Join LFN AI mailing list: https://lists.lfnetworking.org/g/lfn-ai-taskforce
Final Thoughts
In conclusion, the future of networks in the era of 6G and beyond hinges on the transformative power of AI, fueled by open-source collaboration. By embracing AI-driven intelligence, networks can enhance situational awareness, performance, and capacity management, while enabling quick responses to address undesired states. As we navigate this AI-powered future, the convergence of technological innovation and open collaboration holds the key to unlocking boundless opportunities for progress and prosperity in the telecommunications landscape.
References
[1] Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems 30 (2017).
...