As analysts, we are increasingly asked to speculate on how Artificial Intelligence will impact various segments of enterprise and service provider networks. My colleague, Stefan Pongratz, began our collective responses to these requests with an excellent piece on how AI will impact mobile RAN investments.
For my piece on how AI will impact broadband networks, I thought I would start by posing the question to ChatGPT, the generative AI platform, to see what it would suggest as AI’s impact on broadband networks and services. My specific query was “How will artificial intelligence impact broadband networks and services?” Here are the verbatim results:
Artificial Intelligence (AI) is poised to have a significant impact on broadband networks and services in several ways. Some of the key impacts include:
- Network Optimization: AI can be used to optimize the performance of broadband networks by analyzing data in real-time and making adjustments to network configurations. This can lead to better utilization of network resources, reduced congestion, and improved overall network efficiency.
- Predictive Maintenance: AI-powered analytics can help predict potential network failures or issues before they happen. By analyzing data from various network components, AI can identify patterns that indicate impending problems, allowing for proactive maintenance and reducing downtime.
- Enhanced Customer Service: AI can be employed in customer service applications to provide personalized support, answer customer queries, and troubleshoot common issues. AI chatbots can handle a significant portion of customer interactions, improving response times and overall customer satisfaction.
- Quality of Service (QoS) Improvement: AI can monitor network performance and prioritize certain types of traffic based on user demands. This can ensure that critical services, such as video conferencing or online gaming receive higher priority and a better quality of service.
- Network Security: AI can play a crucial role in identifying and mitigating cybersecurity threats on broadband networks. By analyzing vast amounts of network data, AI can detect unusual patterns, potential attacks, and vulnerabilities, helping to enhance network security.
- Network Traffic Management: AI can optimize network traffic routing, especially in scenarios with dynamic traffic patterns. It can analyze real-time data to redirect traffic through the most efficient paths, reducing latency and improving user experience.
- Content Optimization: AI can analyze user behavior and preferences to personalize content delivery. By understanding individual preferences, AI can recommend content, advertisements, and services that are more likely to resonate with specific users.
- Network Planning and Expansion: AI can assist in planning and expanding broadband networks by analyzing demographic and usage data. This can help service providers determine where to invest in network infrastructure, ensuring that resources are allocated efficiently.
- Resource Allocation: AI can help allocate network resources based on demand and usage patterns, dynamically adjusting bandwidth to accommodate peak periods and preventing network congestion.
- Network Virtualization: AI can be utilized in software-defined networking (SDN) and network function virtualization (NFV) to optimize the allocation of virtual resources, making networks more flexible, scalable, and cost-effective.
While AI offers numerous benefits to broadband networks and services, it also presents challenges, such as ensuring data privacy, addressing ethical concerns, and maintaining transparency in decision-making algorithms. As AI continues to evolve, its impact on broadband networks and services is likely to become even more profound.
This might be dangerous to say, but I couldn’t have said it any better myself. All of the network impacts ChatGPT identified are definitely aligned with what we hear from broadband service providers around the world. This is especially true when it comes to proactive network and infrastructure management.
We are already seeing a small, but growing list of operators using machine learning tools as a first step in improving the overall reliability of their broadband access networks. Comprehensive, active monitoring of fiber broadband networks and optical assets has generally been reserved for long-haul and metro Ethernet networks. But for broadband access networks, fiber monitoring has generally been limited to identifying physical fiber cuts or bends and then rolling a truck so a technician can use a handheld OTDR or PON power meter to determine the location of the physical issues. Broadband network operators have always struggled with balancing cost and reliability, which is why they have typically relied on reactive toolsets as opposed to proactive ones.
But with the increased investment levels and long-term strategic significance of fiber broadband networks for both enterprise and residential applications, service providers are increasingly introducing machine learning and AI platforms to help them anticipate and correct network issues before they are impactful. Self-healing broadband networks are the goal.
Beyond ChatGPT’s fairly astute responses, there are also other impacts that AI will have on broadband network spending and services:
AI will Result in Additional Subsidies to Expand Broadband Accessibility and Affordability
COVID-19 was the first of a two-part wave of governments understanding the need for their citizens to have access to broadband and, in many cases, subsidizing the expansion of broadband networks to reach previously unserved locations as well as subsidizing the affordability of those services to learn, work, and engage in commerce from home.
AI—particularly generative AI—is the second part of that wave that will keep governments investing in the broadband networks and services of the future. Somewhat lost amidst all the speculation of how transformative generative AI will be to GDP, as well as how individuals even interact with the Internet and each other, is the fact that no government and no service provider, for that matter, wants to be known as the entity that left its citizens or its subscribers behind.
Therefore, we expect legislators in many countries will push for additional investments to be made to expand the availability and affordability of broadband services. Along those lines, AI tools will prove very useful in the critical task of mapping and identifying locations and communities that lack necessary broadband speeds. In the US, for example, AI tools are being used throughout the BEAD (Broadband Equity Access and Deployment) process to get the most accurate determination of broadband availability at the census block level to start. Ultimately, these datasets can be further parsed so that availability and performance can be determined at a per-street level. The goal, of course, is to ensure that the capital is used as efficiently as possible to eliminate broadband deserts. But AI tools will eventually help governments and service providers determine where their speeds and service levels might not be evolving quickly enough to support the needs of their communities and ensure that a broadband divide doesn’t become an AI divide.
The combination of AI and the Metaverse will Drive Increasing Traffic Requirements
The metaverse is often cited as a reason why service providers need to deploy fiber networks despite today’s applications and content generally not taxing those connections. Though the metaverse will ultimately have an impact on broadband service requirements in both enterprise and residential networks, it is the combination of generative AI and the metaverse that will really be a catalyst for speed growth and continued latency and reliability improvements.
In gaming, VR, and AR applications, the combination of generative AI and the metaverse will dramatically improve how users interact with their environments. The ability to use natural language to create new worlds or to navigate those worlds while also being able to request statistics about those environments in real-time will result in a whole new universe of content creators, and game and application designers. Their ability to successfully create and interact with their 3D and immersive environments will depend largely on their connectivity.
Obviously, the data centers running the real-time engines powering these immersive environments will experience the biggest demand. But there is expected to be some distribution of processing at the device level and at the edge of networks, which means that broadband capacity and throughput will also have to scale up based on users’ requirements.
The impact of using natural language to search, shop, and interact online, as well as to control in-home or in-building IoT sensors, for example, will have a significant impact on overall traffic growth. Where online searches used to be fairly-static requests for particular URLs, using natural language to make similar requests, while a convenience for users, requires significantly more language model processing and broadband connections that can support high downstream and upstream speeds.
And it goes without saying that securing these interactions will be critical, which will also introduce additional bandwidth requirements as well as SLAs and service tiers that match subscribers’ levels of risk tolerance.
