June 2025 – BGPTrace

Can AI Replace Network Engineers? A Real-World Perspective from the Trenches

Today, I watched the latest YouTube video by NetworkChuck.
He discussed how AI is affecting network engineers. It was really interesting — and it motivated me to continue my journey as a network engineer.

Of course, I’m facing some difficulties right now.
If you have any open positions for network engineers, please feel free to message me anytime. I’d really appreciate it.

I’m currently based in the UK.
Yes, I could join Amazon — I mean, Amazon Flex.
No joking. I’m serious.

Right now, I’m especially interested in data center networking and hyperscale networking for AI.
Regardless of the use case — whether it’s business, research, or something more creative like cryptocurrency — I find these areas fascinating.

Also, Internet route checking (RPKI again? Yes, definitely) is something I want to explore further.

On the topic of device deployment — automation, zero-touch provisioning, scripting, etc.:

Yes, scripting in Bash or Perl (SSH into the device, wait for a prompt, automate the commands) has been used for a long time. But today, there are many modern approaches: agents, tailored remote access methods, tunneling deployments, and more.

How do they compare? Which method is best?
Ansible? Python scripting? YAML? Network programming?

And… you prepare every configuration manually? (No way — maybe for 10,000+ devices?!)

OK, let’s step back. Here’s how it usually goes:

Gather and analyze all requirements
Define the needed solutions
Prepare configurations
Plan deployment and coordinate across multiple parties

So the question is: what can AI help with?

I asked ChatGPT about step 3 — configuration preparation and the best automation method.
It gave me this:

Use Case                  | Best Tool
--------------------------|--------------------------
First-time provisioning   | 🟠 ZTP
Day-2 config, updates     | 🟢 Ansible
Dynamic runtime scripting | 🔵 Python

You don’t have to choose just one — combining them leads to full end-to-end automation.

Great! But… what about the rest of the steps to complete a full solution?
Can AI help us with the entire plan?

I think this is how you should approach it:

Analyze the requirements in detail
Identify what the solution needs
Prepare the configurations
Design the deployment plan

You’d need to provide AI with a comprehensive scope of work, and then ask it to generate a plan.

But can you trust it?

YOU need to verify all outputs from AI.
YOU need to plan the project timeline and human resources.
YOU need to review the configurations generated by AI carefully.

If you don’t know networking, project planning, or resource management — how would you even do that?

That’s why:
YOU = Network Engineer, Network Project Manager

We’re always learning new things. AI is becoming a great assistant, but right now, we shouldn’t fully trust it without verification.

As I said before:
Can AI operate the Internet?
Well… that depends on how the AI is designed to manage networks, and which parts of the network it’s capable of operating.

Discussion continues…

TCP Congestion Control – again

This topic keeps coming up again and again:

Which TCP congestion control algorithm has the best performance?
Which handles high latency, delays, and bottlenecks better?
And some might ask, what does it mean when the congestion window becomes zero? AH…

Yes, it’s true — no matter how much technology improves, how fast chipsets and processors become, or how advanced fast-forwarding gets — congestion still happens.

Today’s topic isn’t about local datacenter LAN-side congestion (which may be caused by high network usage in clustered, fabric-based structures — AI workloads, maybe?).

We’re talking about long-haul network connections — like between two distant endpoints. Take Starlink, for example: a satellite-based system with unpredictable latency and environmental effects.

So, how are these “OLD” TCP congestion control algorithms still being used today?

Can monitoring TCP congestion control behavior — like how the congestion window changes — be used to detect potential congestion and trigger a BGP or transit path switch?
Maybe — but it depends on the access technology. If the last mile is wireless, measurements might not be reliable enough.

So, which one is best suited for the modern era?

Here’s a list of Linux-supported TCP congestion control algorithms (summarized by ChatGPT):

highspeed: Designed for networks with large bandwidth-delay products.

reno: The traditional TCP congestion control algorithm.

cubic: Default in Linux since kernel 2.6.19; optimized for high-speed networks.

bbr: Developed by Google (since kernel 4.9); focuses on bottleneck bandwidth and round-trip time.

bic: Binary Increase Congestion Control; predecessor to CUBIC.

htcp: Hamilton TCP; designed for high-speed, long-distance networks.

vegas: A delay-based algorithm that adjusts the sending rate based on RTT variations.

westwood: Optimized for lossy networks; adjusts congestion window based on bandwidth estimation.

yeah: Yet Another Highspeed TCP; combines delay and loss-based congestion detection.

hybla: Improves performance over high-latency networks by compensating for RTT.

illinois: Dynamically adjusts the congestion window for high-speed, long-distance links.

lp: Low Priority; designed for background traffic to yield to more important flows.

veno: Hybrid of Reno and Vegas; optimized for wireless networks.

scalable: Increases congestion window more rapidly than traditional TCP.

nv: New Vegas; an improvement over TCP Vegas.

cdg: Congestion Distance; uses delay gradients to detect congestion.

dctcp: Data Center TCP; optimized for data center networks using ECN.

www.pingnetbox.com project

PingNetBox – https://www.pingnetbox.com is developed using Python and PHP, and it runs on a Raspberry Pi to act as a probe for network measurement.

The source code is available at: https://github.com/royleung01

It’s easy for me to share this small-scale measurement tool with a web interface and reporting features. Of course, compared to RIPE Atlas, this is a much smaller project—on a completely different scale.

The Raspberry Pi operates with low power consumption while delivering high performance. It fulfills basic network testing needs and can also function as an iPerf probe. Since it’s Linux-based, tools like Speedtest-CLI can also be used for measurements.

It seems promising! I’m thinking of developing PingNetBox version 2 with more embedded features for the Raspberry Pi.

Rasp-SDWAN, perhaps? IPSEC?

#raspberryPI #speedtest #RIPE #atlas #IP #network #measurement #Internet #github #IPSEC

Can AI Operate the Internet?

Skynet? No, no Terminator, please.

Just joking—don’t jump to the movie scene right away. Let’s consider the idea of AI operating a network, similar to how automation handles network device configuration and zero-touch provisioning. Is it possible?

Let’s start with automation. A device comes with an initial configuration that includes an IP address and gateway. Once it’s network-accessible, the central server recognizes the device and pushes the final configuration. That’s a simple flow, right?

But what happens next—who operates the device?
Today, it’s still a human network operator.

Could AI replace the network operator? It depends on how the AI model is trained, how it handles fault tolerance, and how it avoids operational errors. There’s no such thing as 100% guarantee.

However, using AI to operate parts of the network—such as traffic tuning, AS path changes, or metric modifications—seems realistic.

AI can assist with tasks like network measurements, route and traffic tuning, DDoS detection and auto-mitigation (which already exists), device fault detection and traffic redirection, and DNS updates. That all seems feasible. You could train an AI module specifically for this purpose.

But then again—do we need AI if existing technologies already meet these requirements?

Let’s consider a scenario and see what AI (specifically, ChatGPT) can do.

Scenario:

An Internet provider has 2 transit links:
- Link A: 1 Gbps
- Link B: 10 Gbps
The subnets 10.0.0.0/24 and 11.0.0.0/24 (AS 65000) are advertised to Link A.
The same subnets, but with AS path prepending (65000, 65000), plus 12.0.0.0/24 (65000), are advertised to Link B.
Link A is congested—11.0.0.0/24 is using nearly 900 Mbps.
Link B’s total usage is just 5 Gbps.
A customer on 10.0.0.0/24 complains they cannot access the Internet.

ChatGPT’s Suggested Operation:

Summary:

Remove or reduce AS path prepend on Link B.
Optionally add prepends on Link A.
Let traffic shift to Link B (10 Gbps).
This will relieve congestion on Link A.
It should also restore Internet access for users on 10.0.0.0/24.

Business Follow-Up:

“From a technical perspective, that works. But from a business point of view, Link A is now underutilized. If Link B has a higher cost per bps, this is inefficient.”

ChatGPT’s Response:

Aspect	Strategy
Technical QoS	Offload heavy prefixes like 11.0.0.0/24 to Link B
Cost Control	Keep lighter prefixes like 10.0.0.0/24 on Link A to avoid overusing B
Business Fit	Avoid paying premium for B unless capacity is needed
Scalable Option	Automate prepend adjustments using monitoring-based thresholds

Yes, that’s a great example of how AI can analyze your needs if you provide enough detail and criteria.

The remaining concern is AI’s operational cost and power consumption.

This topic definitely deserves more discussion—SD-WAN + AI?

#BGP #bgptrace #AI #chatGPT #AS #ASPrepend #path #link #transit #INTERNET #SDWAN