Enterprise 5G - evolving bottom-up from small islands, not top-down from national networks

This post originally appeared on September 29 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

While the broad concept of #privatewireless seems to be getting a lot more awareness in the wider tech industry, some of the implications haven't quite fully landed yet.

I've had a couple of meetings recently where there was still a prevailing view that #5G evolution would continue to be "top-down", with major MNOs setting the agenda, especially for enterprise. The belief is that national "umbrella" networks would address all the various localised applications, such as #industry40 and #smartagriculture, or #v2x networks along roads.

Such a set-up would mean that the network "mothership" would need all sorts of cloud-native elements for orchestration, security and control systems, both at the telcos and their clients, which would be a boon for vendors expecting a direct correlation with the promised $xxx billions of 5G value, coming from URLLC capabilities, slicing and other features.

But what is happening is much more bottom-up. The most cutting-edge uses of 5G are happening at specific locations - whether that is standalone networks at factories, or new #neutralhost deployments in offices and hotels (more on NH's in my next post btw). We can expect Release 16/17/18 features to appear at a micro level, long before they're switched on for the macro domain.

And while these small local networks are sometimes being deployed by MNOs, they are often based on dedicated infrastructure, perhaps using different vendors to the main umbrella national networks. It's often the B2B units running the show, with a variety of partners, rather than the central core network team.

Other small islands are getting their networks built by integrators, towercos & infracos, inhouse teams, industrial solutions suppliers and assorted others. It's very heterogeneous.

And each island can be *small*. A port's 5G network might have huge value for the site's operator, but only have 100 SIMs in cameras and vehicles. There might be redundancy, but it won't need a datacentre full of kit. There's often going to be a lot of customisation, and unique combination of applications and integrations with other systems

So if you're a vendor pitching umbrella-grade solutions, you might need to rethink how to re-orient towards small islands instead.

 

Train connectivity - is passenger Wi-Fi too linked to rail portals' needs?

This post originally appeared on Oct 5 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

It's always interesting to attend non-telecom industry events. Too often, we breathe our own smoke. Visiting another sector's conferences gives better perspective. Often, networks are less important than we imagine for "verticals".

Yesterday I chaired the Connectivity stream of the World Passenger Festival conference in Vienna, an event primarily for the rail industry, plus other forms of transport mobility. The speakers in my breakout covered Wi-Fi access onboard trains and at stations, plus how to manage video traffic. 5G was covered for on-train network backhaul, neutral-host provision and possible use-cases like AR-enabled tourism & urban mobility V2X safety for buses and bikes.

The rest of the conference and show floor was about passenger experiences more generally. Ticketing, sleeper trains, coordination with other types of transport, train-based tourism and so on. Plenty of talk about apps and "transformation" more broadly, but the network wasn't a priority.

There was also a rather muddled main-stage keynote on #5G by Accenture, with 2018-era references to millisecond latencies, network slicing and autonomous vehicles. It conflated normal MNO 5G with the long-promised critical-comms rail variant #FRMCS and bizarrely suggested they would coexist on converged, virtualised networks. A later chat on their booth with a more knowledgeable colleague gave a lot more clarity & agreement on the realities & drivers of operational connectivity for future rail - especially enabling ECTS (European Train Control System) for higher capacity on rail networks.

The rail industry is at the apex of a trend I discussed in a recent newsletter article and post - the need for customers to have reliable access to smartphone apps for ticketing, journey-planning, at-seat entertainment and catering etc. Travellers need to download passes, make payments and use QR codes.

This explains why so much of the on-train #WiFi strategy is linked to apps and portals, and much less to general wireless infrastructure, whether MNO or dedicated trackside/FRMCS.

Some rail Wi-Fi teams view cellular as a cost (for backhaul) or a rival that stops passengers seeing the portal and info/monetisation offers, when they directly access the Internet from phones. They filter or cache video use to reduce cost and congestion. One even tries to dissuade passengers from using cellular, to save 4G/5G network capacity for the train!

In my view, there is both too much "joined-up" thinking and too little. It's either 5G maximalism ("we don't need Wi-Fi on trains") or it directly links connectivity to the rail operator's own priorities, rather than passengers' real Internet access needs and expectations.

What is needed is integration in the right places and layers. Shared trackside masts and fibre, plus hybrid connectivity to trains from public 5G, trackside dedicated networks (including #private5G) and satellite, delivering good, neutral, fast on-train Wi-Fi AND cellular for passengers.

 

Indoor wireless & the need for unlicensed 6GHz

This post originally appeared on October 2 on my LinkedIn newsletter, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please subscribe / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

 

Note: This article has been commissioned by the Dynamic Spectrum Alliance, based on my existing well-known analysis and positions, which I have been discussing for many years both publicly and privately. I believe that in-building wireless - irrespective of technology - receives far too little attention from policymakers and regulators. 6GHz should be indoor-primary spectrum.

---

Abstract & summary: The vast bulk of wireless data traffic today is for indoor applications. In future, in-building wireless will become even more important. It is ideally-suited to 6GHz spectrum, made available on an unlicensed basis. A licensed model for 5G mobile in 6GHz would be unable to deliver coverage consistently for more than a small number of sites.

Indoor wireless is already critical & often overlooked

Industry estimates suggest that 60-80% of cellular data is delivered to indoor users, predominantly on smartphones. Additional statistics shows that smartphones also typically consume another 2-5x the cellular data volume on Wi-Fi, almost all of which is indoors or in vehicles. In other words, 90%+ of total smartphone data is consumed inside buildings.

In addition, residential fixed broadband traffic volumes are roughly 10-20x that of mobile broadband, with final delivery mostly over Wi-Fi, often to non-smartphone devices such as smart TVs, laptops, game consoles and voice assistants.

Outside the consumer market, a great deal of non-residential wireless connectivity is also indoors – healthcare, education, manufacturing, conventions, hospitality and office environments are all increasingly dependent on wireless, especially with the rise of industrial automation systems, IoT, robots, connected cameras and displays. These map to the rise in cloud- and video-based business processes.

Most wireless uses & devices are indoor-centric

This does not imply that outdoor wireless use is either trivial or unimportant. Most obviously, everyone uses their phones for calling, messaging, mapping and various transport and other apps while on-the-move. Vehicle connectivity is becoming essential, as well as wireless use for safety, utilities and smart-city infrastructure. Some sectors such as agriculture, logistics and construction are predominantly outdoor-oriented, albeit often at specific locations and sites.

But to a rough approximation, if 80%+ of wireless use is indoors, then 80%+ of economic and social benefit of wireless will accrue indoors as well. This applies irrespective of the technology involved – Wi-Fi, 4G/5G cellular, or even Bluetooth.

Future growth of indoor wireless

The demands for indoor connectivity are likely to grow in both scale and scope in coming years. There will be huge demand for high-throughput, low-latency access for both consumer and enterprise use-cases.

• Gigabit broadband, especially delivered with fibre, is becoming the default for both residential and business premises. In the medium term, we can expect 10Gig services to become more common as well. In many cases, the bottleneck is now inside the building, and local wireless systems need to keep pace with the access network.
• There is a growing array of demanding devices and applications connected inside homes and enterprises premises. 4K and 8K screens, automation systems, healthcare products, AR/VR systems, cameras for security and industrial purposes, robots and much more.
• Wireless devices will increasingly be located in any room or space inside a building, including bedrooms, garages, basements, meeting rooms, factory-floors and hospital operating theatres.
• The density of devices per-building or per-room will increase exponentially. While some will be low-traffic products such as sensors, ever more appliances and systems will feature screens, cameras and cloud/AI capabilities demanding greater network performance.
• There will be growing emphasis on the efficiency of networks, in terms of both energy and spectrum usage. “Blasting through walls” with wireless signals will be viewed negatively on both counts.

Yet only some policymakers and regulators have explicit focus on indoor wireless in their broadband and spectrum policies. There has been some positive movement recently, with regulators in markets such as the UK, Germany, Canada and Saudi  Arabia addressing the requirements. But it is now time for all governments and regulators to specifically address indoor wireless needs – and acknowledge the need for more spectrum, especially if they eventually want to achieve “gigabit to each room” as a policy goal.

Wi-Fi can satisfy indoor requirements, but needs 6GHz

Almost all indoor devices discussed here have Wi-Fi capabilities. A subset have 5G cellular radios as well. Very few are 5G-only. This situation is unlikely to change much, especially with a 5-10 year view.

Yet Wi-Fi faces a significant limit to its performance, if it just has access to traditional 2.4GHz and 5GHz bands. Not only are these limited in frequency range, but they also have a wide variety of legacy devices, using multiple technologies, that must coexist with any new systems.

While mesh systems have helped extend the reach to all rooms in a home, and Wi-Fi 6 brings new techniques to improve performance and device density in consumer and enterprise settings, much more will be required in future.

Now, Wi-Fi 6E and 7 generations are able to use the 6GHz band. This adds up to 1.2GHz of extra spectrum, with almost no sources of interference indoors, and almost no risk of indoor use creating extra interference to incumbent outdoor users, especially at lower power levels.

6GHz Wi-Fi would be able to address all the future requirements discussed in the previous section, as well as reducing system latency, improving indoor mobility and providing greater guarantees of QoS / reliability.

6GHz 5G is unsuitable for indoor use, and of limited use outdoors

By contrast, 6GHz is a poor fit for indoor 5G. Most buildings will be unable to use outdoor-to-indoor propagation reliably, given huge propagation challenges through walls. This would be hugely wasteful of both energy and spectrum resource anyway. This situation will worsen in future as well, with greater use of insulated construction materials and glass.

That leaves dedicated indoor systems such as small cells or distributed antenna or radio systems. Current DAS systems cannot support 6GHz radios – most struggle even with 3.5GHz. It may be possible to upgrade some of the more advanced systems with new radio heads, but few building owners would be willing to pay, and almost no MNOs would. In any case, only a fraction of buildings have indoor cellular systems, especially beyond the top tier of shopping malls, airports and other large venues.

The industry lacks the human and financial resources to implement new 6GHz-capble indoor systems in more than a tiny proportion of the millions of buildings worldwide, especially residential homes and small businesses.

Enabling public 5G services to work reliably indoors with 6GHz is therefore a decade-long project, at least. It would likely be the mid-2030s before 5G (or 6G) devices could routinely use 6GHz inside buildings. Lobbyist estimations of the notional GDP uplift from IMT use of the band ignore both the timing and the practical challenges for indoor applications. A very heavy discount % should be applied to any such calculations, even if the baseline assumptions are seen as credible.

Private 5G systems in factories or warehouses could theoretically use 6GHz licensed cellular, but most developed countries now have alternative bands being made available on a localised basis, such as CBRS, 3.8-4.2GHz or 4.9GHz. Many countries also have (unused) mmWave options for indoor private 5G networks. In theory, 5G systems could also use an unlicensed 6GHz band for private networks, although previous unlicensed 4G variants in 5GHz never gained much market traction.

It is worth noting that there are also very few obvious use-cases for outdoor, exclusive-licensed 6GHz for 5G either, beyond a generic increment in capacity, which could also be provided by network densification or other alternative bands. Most markets still have significant headroom in midband 3-5GHz spectrum for 5G, especially if small cells are deployed. The most-dense environments in urban areas could also exploit the large amount of mmWave spectrum made available for cellular use, typically in the 24-28GHz range, which is already in some handsets and is still mostly unused.

Conclusions

Regulators and policymakers need to specifically analyse the use and supply/demand for indoor wireless, and consider the best spectrum and technology options for such applications and devices. Analysis will show that in-building wireless accounts for the vast bulk of economic and social benefits from connectivity.

This is best delivered by using Wi-Fi, which is already supported by almost all relevant device types. With the addition of 6GHz, it can address the future expected growth delivered by FTTX broadband, as well as video, cloud and AR/VR applications.

The ultra-demanding uses that specifically require cellular indoors can use existing bands with enhanced small cells and distributed radios, neutral-host networks, or private 5G networks in the 3-5GHz range. There is also the ample mmWave allocations for 5G.

A final fundamental element here is timing. 6 GHz Wi-Fi chipsets and user devices are already shipping in their 100s of millions. Access points are widely available today and becoming more sophisticated with Wi-Fi 7 and future 8+ versions. By contrast, 5G/6G use of the band for indoor use is unlikely until well into the next decade, if at all.

Indoor wireless is critically important, growing, and needs Wi-Fi.

And Wi-Fi needs 6GHz.

 

5G data traffic growth - the devil (FWA) is in the detail

This blog combines two separate, linked LinkedIn articles published in June 2023 on consecutive days. The original posts and comment threads are here and here.

Measuring #mobile data traffic is important for operators, vendors, and policymakers.

As I've said before, we should use *good* #metrics to measure the #telecoms industry, rather than just *easy* metrics. This post is an example of what I mean.

Yesterday, Ericsson released its latest Mobility Report. It's always an interesting trove of statistics on mobile subscribers, networks and usage, with extra topical articles, sometimes written by customers or guests.

While obviously it's very oriented to cellular technologies and has an optimistic pro-3GPP stance, it has a long pedigree and a lot of work goes into it. It's partly informed by private stats from Ericsson's real-world, in-service networks run by MNO customers.

This edition includes extra detail, such as breaking out fixed-wireless access & separating video traffic into VoD #streaming (eg Netflix) vs. social media like TikTok and YouTube.

It had plenty of golden "information nuggets". For instance, traffic density can be 500-1000x higher in dense urban locations than sparse rural areas. I'll come back to that another time.

Global mobile data grew 36% from Q1'22 to Q1'23. The full model online predicts 31% growth in CY2023, falling to just 15% in 2028, despite adding in AR/VR applications towards the end of the decade. That's a fairly rapid s-curve flattening.

For Europe, MBB data growth is predicted at 29% in 2023, falling to only 12% in 2028. That's a *really* important one for all sorts of reasons, and is considerably lower than many other forecasts.

But what really caught my eye was this "#FWA data traffic represented 21% of global mobile data traffic at the end of 2022". Further, it is projected to grow much faster than mobile broadband (MBB) and account for *30%* of total traffic in 2028, mostly #5G. When the famous "5G triangle" of use-cases was developed by ITU, it didn't even mention FWA.

However, the report didn't break out this split by region. So I decided to estimate it myself based on the regional split of FWA subscribers, which was shown in a graphic. I also extended the forecasts out to 2030.

I then added an additional segmentation of my own - an indoor vs outdoor split of MBB data. I've pegged this at 75% indoors, aligning with previous comments from Ericsson and others. Some indoor MBB is served by dedicated in-building wireless systems, and some is outdoor-to-indoor from macro RAN or outdoor small cells.

The result is fascinating. By the 2030, it is possible that over 40% of European 5G data traffic will be from FWA. Just 14% of cellular data will be for outdoor mobile broadband. So what's generating the alleged 5G GDP uplift?

That has massive implications for spectrum policy (eg on #6GHz) and proposed #fairshare traffic fees. It also highlights the broad lack of attention paid to indoor cellular and FWA.

Note: This is a quick, rough estimate, but it's the type of data we need for better decisionmaking. I hope to catalyse others to do similar analysis.

 

A separate second post then looked at the policy aspects of this:

Yesterday's post on mobile data traffic - and contribution from 5G FWA and indoor use - seems to have struck a chord. Some online and offline comments have asked about the policy implications.

There are several conclusions for regulators and telecoms/infrastructure ministries:

- Collect more granular data, or make reasoned estimates, of breakdowns of data traffic in your country & trends over time. As well as #FWA vs #MBB & indoor vs outdoor, there should be a split between rural / urban / dense & ideally between macro #RAN vs outdoor #smallcell vs dedicated indoor system. Break out rail / road transport usage.
- Develop a specific policy (or at least gather data and policy drivers) for FWA & indoor #wireless. That feeds through to many areas including spectrum, competition, consumer protection, #wholesale, rights-of-way / access, #cybersecurity, inclusion, industrial policy, R&D, testbeds and trials etc. Don't treat #mobile as mostly about outdoor or in-vehicle connectivity.
- View demand forecasts of mobile #datatraffic and implied costs for MNO investment / capacity-upgrade through the lens of detailed stats, not headline aggregates. FWA is "discretionary"; operators know it creates 10-20x more traffic per user. In areas with poor fixed #broadband (typically rural) that's potentially good news - but those areas may have spare mobile capacity rather than needing upgrades. Remember 4G-to-5G upgrade CAPEX is needed irrespective of traffic levels. FWA in urban areas likely competes with fibre and is a commercial choice, so complaints about traffic growth are self-serving.
- Indoor & FWA wireless can be more "tech neutral" & "business model neutral" than outdoor mobile access. #WiFi, #satellite and other technologies play more important roles - and may be lower-energy too. Shared / #neutralhost infrastructure is very relevant.
- Think through the impact of detailed data on #spectrum requirements and bands. In particular, the FWA/MBB & indoor splits are yet more evidence that the need for #6GHz for #5G has been hugely overstated. In particular, because FWA is "deterministic" (ie it doesn't move around or cluster in crowds) it's much more tolerant of using different bands - or unlicensed spectrum. Meanwhile indoor MBB can be delivered with low-band macro 5G, dedicated in-building systems (perhaps mmWave), or offloaded to WiFi. Using midband 5G and MIMO to "blast through walls" is not ideal use of either spectrum or energy.
- View 5G traffic data/forecasts used in so-called #fairshare or #costrecovery debates with skepticism. Check if discretionary FWA is inflating the figures. Question any GDP impact claims. Consider how much RAN investment is actually serving indoor users, maybe inefficiently. And be aware that home FWA traffic skews towards TVs and VoD #streaming (Netflix, Prime etc) rather than smartphone- or upload-centric social #video like TikTok & FB/IG.

Telecoms regulation needs good input data, not convenient or dramatic headline stats.

 

Connectivity on trains is hard - but both Wi-Fi and cellular need to be provided for passengers

This post originally appeared on May 24 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

 There have been recent headlines about the possible ending of on-train passenger #WiFi services in the UK. It is deeply controversial.

Apparently the Department for Transport (DfT), United Kingdom has insisted rail WiFi must be "justified financially". It's unclear if that means by extra ticket sales, higher customer satisfaction, or the use of WiFi for #train operational functions like cameras and wireless payment terminals.

I hope it's not referring to so-called "monetisation" by customers paying for WiFi, or being served adverts. On trains, WiFi is a basic amenity, like toilets or power sockets.

That said, train WiFi in the UK is often problematic. It uses clunky captive portals, and often old access points & slow/patchy 4G backhaul. It often fails to work well, or at all. It sometimes blocks video or VPNs. By contrast, in-station WiFi is run separately - and often much better.

Public cellular coverage on the rail network is also poor. Many rail lines run through cuttings and tunnels with limited room for trackside infrastructure & poor lines-of-sight to cell towers. The recent Department for Science, Innovation and Technology Wireless Infrastructure Strategy highlighted poor #railway #wireless coverage & pushed for regular monitoring and access to trackside fibre.
 
What should DfT, DSIT, Network Rail, Train Operating Companies and the future restructured Great British Railways Transition Team (GBRTT) do?
 
- Recognise both cellular & WiFi are essential for passengers, especially on long-distance trains where laptops are common
- Understand that cellular - especially #5G - has problems with signals reaching inside train carriages
- Don't underestimate forecasts for future data use. Add in uplink as well as downlink, and think about latency. Trains may need 1-5 Gbps in the medium term, via a mix of cellular & WiFi.
- Ensure on-train WiFi is easy to use & easily-upgraded. No captive portals, no “monetisation” with ads/data capture & a clear roadmap for regular upgrades. No blocking of any apps, especially VPNs and video. Apply Net Neutrality rules.
- Federation or roaming between on-train & station WiFi systems, extending to smart cities & metro bus/train/tram WiFi over time
- Easier access for MNOs / #neutralhosts to build trackside or near-track infrastructure & use gantries & fibre assets
- Decouple passenger connectivity needs from future critical #FRMCS deployment. They have different timing/cadence & investment cases
- Look at trackside 5G neutral host networks delivered with “excess” spectrum from any future 4-3 merger of MNOs
- Insist on-train gateways are modular & can use a dynamic mix of public 5G, trackside wireless & eventually satellite in remote areas. Ensure they are easily upgradeable without trains being taken out of service
- Upgrade on-train signal repeaters & look at window-etching for better outdoor-to-indoor performance

Note: I wrote this on WiFi on a train back to London from this week’s Wi-Fi NOW conference.

 

Data traffic growth forecasts - AD Little's new report has a lot better methodology than most

This post originally appeared on June 5 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

When I saw that Arthur D. Little had published a report on “The evolution of data growth in Europe”, on behalf of ETNO Association & GSMA, I rolled my eyes.
 
Both organisations have previously published terrible studies by consultants, riddled with flawed assumptions and dodgy multiplier "fiddle factors". I’ve loudly criticised Axon and Coleago reports related to the (un)#fairshare and #6GHz #spectrum debates respectively.
 
So I started the ADL report with trepidation, not helped by a strange typo / editing error in the first paragraph.
 
But actually, the report is pretty good, and I broadly agree with both methodology and conclusions, albeit with one major caveat.
 
It estimates usage of home and mobile broadband on the basis of hours-per-day of active use of heavy applications such as video streaming, gaming and possible metaverse-type experiences.
 
I’ve used GB-per-hour myself, to model passenger data-traffic demand on trains. It makes more sense than the usual Gbps, as most applications are “bursty”. It also fits the typical heuristics of human behaviour. How many seconds a day do you spend on social media?
 
The central prediction of 20% growth in fixed traffic and 25% for mobile usage seems reasonable. I could argue for 25/20 rather than 20/25, but it's fine as a rough estimate.

Importantly these rates for the next few years are well within the bounds of both fixed broadband (moving to #FTTP) and mobile (on #5G) without incremental investments in extra capacity, beyond the main "generational" shift & CAPEX. And that is driven by government policy and competition, not traffic load and congestion. The report convincingly shows that nobody really needs/values more than 100Mbps for current apps, so #gigabit networks have plenty of headroom.

My main criticism is there is no analysis of mobile device traffic carried over fixed networks and #WiFi. Smartphones used at home for video, gaming or social media will be c80% on Wi-Fi, and indoor usage is c80% of the total.

The report also talks about AI pre-emptively downloading content for “infinite scrolling”, but doesn't suggest it could be smart enough to do so mostly over cheap / low-energy fixed connections. (IMO, by 2030, governments may *mandate* cellular offload via neutral-host or Wi-Fi for indoor use).

I agree with the report's assertions that VR is in an indoor/fixed application, that most #IoT traffic is a rounding-error and that #Web3 is probably irrelevant. The #metaverse scenarios seem mostly plausible.
 
One area I think ADL underestimates is fixed broadband for video streaming. While Netflix and YouTube are “active” viewing, historically, many people just leave broadcast TV switched on, even if nobody is in the room except the cat.

If TV really goes online-only, then that becomes a genuine “waste” of capacity, unless you can advertise to pets.

Overall - really quite good analysis, which (ironically, given the sponsors) fatally undermines the #InternetTrafficTax rhetoric.

 

Spectrum: The shifting tone of the satellite industry

This post originally appeared on June 7 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

I'm in Brussels this week at the Forum Europe European Spectrum Management Conference.

There's a lot to discuss, especially around #6GHz and 3.8-4.2GHz and the role of unlicensed and local/shared bands, as well as the upcoming World Radio Conference WRC-23.

I'll have more to say, but here I just want to highlight one particular theme that has been evident over the last couple of days: the tone of the satellite sector, which is here in force, especially with GSOA and Intelsat.

In the past at these #spectrum events, the #satellite industry has turned up with a familiar script:

"Hi, we're from the satellite industry. Please don't take our spectrum. We help with defence, aviation & connecting the unconnected. Please don't take our spectrum. We work tightly with the mobile industry, doing backhaul & IoT and timing sync. They're our friends & vice versa. Oh, and did we mention our spectrum? Please don't take any more of it"

But this time, it's different. The message is now closer to:

"We're doing all ths cool new stuff, including for wireless broadband, direct to device and defence. So actually, we want to keep all our spectrum. And maybe give back the old #mmWave spectrum you took years ago, that the mobile industry hasn't even used. Seriously, you want *more* spectrum to be taken from us and pre-allocated to 6G now? Are you having a laugh?"

There was a whole panel on direct-to-device, and satellite has fought its corner on the upper 6GHz (it can coexist with low/medium power WiFi, but not high power 5G) and fixed satellite links in 4GHz band. The future-looking 6G panel started a fierce debate on 7-24GHz, which covers various of the satellite incumbent bands.

There's been a few references to South Korea's regulator reclaiming unused 28GHz licenses from MNOs that haven't used the band. And there's a broad opinion that mobile/IMT is not a friendly partner for spectrum-sharing, at least for national MNO macro networks at full power. (Local private networks are OK-ish, it seems).

"An IMT identification is an eviction notice - the incumbents must leave".

"It's disingenuous to discuss coexistence studies - we've been here before and know how it ends. It's not our first rodeo with the mobile industry"

Now clearly this year, in the last few months before WRC23, is when arguments get more vigorous. But some of the stuff at the #EUspectrum event has been seriously punchy - Intelsat asked whether Europe should be focused on primacy in an amorphous "race to 6G" or a more geopolitically-crucial "space race".

My view is that the #5G industry is seeing some chickens coming home to roost at the moment. It overpromised Release 18 features with Release 15 timelines, got mmWave spectrum years before it could be exploited, and have left politicians and regulators with egg on their faces.

Meanwhile, the satellite sector is positioning itself as super-cool and important. It has a swagger that is being noticed by policymakers, and for good reason.

 

Private 5G: Two different approaches at the Coronation

This post originally appeared on June 9 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

 A month ago, the UK and much of the world watched King Charles' #Coronation in London.

They were able to watch it partly because of the immense efforts of the various #broadcasters involved. Since then, two separate stories have emerged about the role of dedicated #5G connectivity in the TV coverage:

1) A dedicated private 5G network supplied by Neutral Wireless and BBC R&D, used by several broadcasters
2) A slice of the Vodafone public 5G network, enabled for ITN, based on Ericsson gear

In the comments I've linked to various articles and a great interview on Ericsson's Voice of 5G podcast show. They have details of the other partners involved too. In the BBC blog post they also mention a 3rd network on a separate cell, working alongside Sony, for low-latency (I think) remote-controlled cameras.

The #Private 5G network used 8 radios along The Mall (the tree-lined road between Buckingham Palace to Trafalgar Sq). It used 2x 40MHz channels in the UK's shared-licence band between 3.8-4.2GHz, with 1Gbps capacity (mostly for uplink). It was used by around 60 devices - I guess mostly cameras and test equipment via gateways, plus the BBC's onsite radio studio. They also used LiveU bonding systems to add capacity from public MNO networks. I'm not sure about the vendors of the radios or standalone core.

The 5G SA #networkslicing solution was apparently used for a single sector at a 3.5GHz temporary base station aimed at the Palace balcony. It also worked with LiveU. On the podcast, Andrea Donà (VF's head of network in the UK) talks about "dedicating bandwidth to one sector for the slice" and carving out some of the uplink capacity.

One thing that is unclear to me is how many other users were sharing the VF standalone 5G network hosting the slice - SA hasn't been fully launched commercially in the UK, although in January VF said it had invited selected users to trial it. I also don't know whether the 5G NSA and SA networks were sharing the radio resource, or if they use separate channels.

The public 4G / 5G networks (and also Wi-Fi bands) in the area were pretty overloaded, despite additional mobile towers adding capacity. The Vodafone / Ericsson podcast notes that VF uses "all the bands" at major events (although there's no #mmWave 5G in the UK yet) - so including 4G at 2.1GHz and 2.6GHz, and some lower bands for 2G/3G.

My take from this is that #private5G is considerably more mature than #5Gslicing, but that both are interesting for broadcasters. Both need quite a lot of specialist engineering, but TV is a sector with lots of very clever specialists and great ability to set up temporary networks. Of course, both networks were *outdoors* which meant that the thick stonework of the palace and Westminster Abbey weren't relevant.

One last note - the huge bulk of broadcast audiovisual output at the coronation would have used dedicated #PMSE wireless for cameras and microphones. But the #UHF spectrum debate is for another post.

 

CAPEX in telecoms - beware of headline numbers

This post originally appeared on June 12 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / connect to me on LinkedIn, to receive regular updates (about 1-3 / week)

CAPEX numbers are important in #telecoms. But they're also often collected and analysed in a haphazard fashion, or sometimes twisted and misinterpreted. There are examples that wrongly imply casual links or are carefully selected to drive specific policy choices.

- Telco execs watch CAPEX stats as they're important elements of cashflow & also signify key strategies and technology transitions
- Vendors watch #CAPEX stats to understand demand for new products
- Investors watch CAPEX as inputs to their valuation models, and as a barometer for company/industry health and prospects
- Policymakers watch CAPEX as it gets captured in "investment" statistics, and as an indicator for potential regulatory changes (or as a metric of success of previous policies)

Various ratios are commonplace, for both companies and the industry:
- CAPEX vs. revenues
- CAPEX vs. EBITDA
- CAPEX of telecoms vs. tech/hyperscalers
- CAPEX vs. R&D spending
- Fixed vs. Mobile CAPEX
... and so on

The problem is that "telco CAPEX" is also a very vague and malleable concept. Digging into it reveals many more questions - and problems with the methodologies and conclusions drawn, especially where headline numbers are concerned.

Some of the questions I'm currently looking at include:

- What counts as a "telco"? Are you including towercos, subsea fibre operators, municipalities building networks, MVNOs and many others?
- Are historic CAPEX numbers restated when telcos sell or acquire other businesses, especially tower spin-outs?
- Is it meaningful to compare CAPEX for 10 / 30 / 50 year assets such as #FTTP, which will generate decades of new revenue, with last year's figures?
- How do you separate CAPEX for basic coverage vs. incremental capacity vs. "generational" upgrades to fibre or #5G? A lot of CAPEX occurs even if usage is low
- How do you deal with leasing or other financing models? If CAPEX shifts to OPEX, how is it captured in the stats?
- What happens with "cloudified" networks? Firstly they rely on shared (often 3rd-party) assets, and secondly they are *supposed* to lower costs / investments. But will the lower CAPEX be viewed as a sign of distress, not modernisation?
- Is non-network CAPEX broken out (eg retail sites, central offices, datacentres etc)?
- Is "adjacent capex" included and if so, how?, eg in-building #wireless, #spectrum licenses, software development

I hear many commentators and lobbyists claim "#NetNeutrality led to lower CAPEX!" or "Streaming traffic leads to higher CAPEX!" or "There's an investment gap!". Without detailed data - and an analysis of causality - you have to question the veracity & meaningfulness of such rhetoric.

In summary - CAPEX is indeed important. But in fact it's so important, that headline numbers are often useless or misleading.

Ask for details on segmentation, methodology and definitions - if they aren't available, treat the numbers with deep skepticism.

#FTTX #telcos #regulations #networks #fairshare

A new view on Neutral Host - the role of cities and municipalities

This post originally appeared on Apr 17 on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / subscribe to receive regular updates (about 1-3 / week)

I'm at the #ConnectedNorth event in Manchester today and tomorrow. There's a lot about gigabit fibre rollouts and uptake, as well as a big emphasis on connected communities and cities - but this post is about mobile densification and small cells.

A key theme here is the fast-evolving model for #neutralhost mobile for small cells and network capacity in-fill in cities. An NH is a 3rd party wholesale provider which enables multiple tenant 4G/5G mobile providers - generally MNOs, but also potentially including private networks as well.

A few years ago when I was running NH workshops with Peter Curnow-Ford we identified this area of metro infill as one with potential, but limited actual deployments.

There are numerous challenges - MNOs ideally don't want separate deals with each city authority, while cities don't want multiple MNOs independently requesting 100s of sites with associated street clutter, road closures and soon. Authorities also want to both make money from access to assets such as lampposts, and to improve connectivity for citizens and businesses as fast as possible.

One option floated was for authorities to build out their own private 4G/5G networks, then allow MNOs to roam onto them, or use some sort of MOCN network-sharing arrangement. But MNOs each have different coverage / capacity holes, different spectrum bands, different customer groups - and also worry about security, ability to manage radio units, do carrier aggregation and so on. The idea of a single cell network in its own spectrum, with multiple MNO tenants is appealing, but sometimes unworkable. (It might work OK in villages or indoors, though).

What's happening is that another model is evolving. Local authorities like city councils are contracting with several infrastrucure specialists - companies like Cellnex UK , Freshwave, Ontix, BAI Communications and Shared Access to run (essentially) small-cell as a service offers. These act as intermediaries, allowing local authorities to create standard contracts, and for MNOs to have standardised processes for getting access at each site.

It reduces the frictions and costs of the paperwork - and also allows for infrastructure-sharing to evolve over time where it makes sense. Coupled with vRAN or open RAN it can put some of the electronics into central facilities, reducing street-side box numbers. And it means MNOs can get coverage in their preferred locations, with backhaul/fronthaul and power supplies simplified.

The competitive infraco/towerco angle, rather than exclusive area concessions, allows MNOs to choose the provider that is the best fit - and without needing different processes in each city.

It's not quite what I expected NH models to look like - and they may differ in the US or across Europe - but it seems to make good sense here in the UK.

 

6G must be indoor-primary and have a Wi-Fi candidate technology

This post originally appeared on my LinkedIn feed, which is now my main platform for both short posts and longer-form articles. It can be found here, along with the comment stream. Please follow / subscribe to receive regular updates (about 1-3 / week)

I'm giving a lot of thought to #6G design goals, priorities & technology / policy choices. Important decisions are coming up. I'll be exploring them in coming weeks and months. Two important ones I see:

- 6G / #IMT2030 must be "indoor-primary"
- There must be a IEEE / Wi-Fi Alliance candidate tech for 6G

The first one is self-evident. The vast bulk of mobile use - and an even-larger % of total wireless use - is indoors. It's inside homes, offices schools, factories, warehouses, public spaces like malls and stadia - as well as inside vehicles like trains. Even outdoors, a large % of usage is on private sites like industrial complexes or hospital campuses.

Roughly 80% of mobile use is indoors - more if you include wireless streaming to smart TVs and laptops/tablets. By the 2030s 6G era, there will be more indoor wireless use for #industrialautomation, #gaming, education, healthcare, #robotics and #AR / #VR / #metaverse and so on.

This implies that economic, social, welfare and cultural upsides will be indoor-primary. 80%+ of any GDP uplift will be indoor-generated. This suggests 6G tech design & standards - and associated business models and regulation - should be indoor-oriented too.

The IEEE / #WiFi idea follows on from this. The default indoor wireless tech today is Wi-Fi. There is a lot of indoor cellular use, but currently 5G is supported poorly - and certainly not everywhere.

While 5G and future 6G indoor #smallcells, #neutralhost and repeaters / DAS are evolving fast, *nobody* expects true ubiquity. Indoor cellular will remain patchy, especially multi-operator. And many devices (eg TVs) don't have cellular radios anyway.

This means that WiFi - likely future #WiFi8 and #WiFi9 - will remain central to in-building connectivity in the 6G era, no matter how good the tech for reconfigurable surfaces or other cellular innovations become.

IEEE decided not to pitch WiFi6 formally for 5G / IMT2020, but instead just show it surpassed all the metrics. But "we could have done it if we wanted" isn't good enough. There are no government-funded "WiFi Testbed Programs" or "WiFi Innovation Centres of Excellence" because of this lower visibility.

Governments are ITU members and listen to it. If policymakers want the benefits of full connectivity, they need to support it with spectrum, targets and funding, across *all* indoor options.

And if the WiFi industry wants full / easy access to new resources, it needs to be an official 6G / IMT2030 technology. It needs access to IMT licensed spectrum, especially for local licenses with AFC.

This idea will be very unpopular among both cellular industry (3GPP pretends it is the "keeper of the G's") and the WiFi sector, which sees it as a lot of extra work & politics.

But I think it's essential for IMT2030 to embrace network diversity, plus ownership- & business-model diversity as central elements of 6G.

 

What does an AI think about Net Neutrality?

Originally published on my LinkedIn Newsletter, 9th Feb 2023. See here for comment thread

Two very important trends are occurring in tech I'm following at the moment, so I thought it might be fun to combine them:

• The emergence of #GenerativeAI, for answering questions, generating images and sounds, and potentially a whole lot more. OpenAI #ChatGPT is the current best-known, but there are dozens of others using language models, transformers & other techniques. Some people are suggesting it will redefine web search - and potentially an awful lot more than that. Some even see it as a pivotal shift in technology, society and "skilled" employment.
• The re-emergence of discussions around #NetNeutrality and associated regulation relating to technology platforms, telcos and networks, like the ridiculous (un)#fairshare & #InternetTrafficTax concept being pitched in Europe by lobbyists. In the UK, Ofcom recently concluded a consultation on whether changes to NN rules should be made (I sent in a reply myself - I'll discuss it another time).

So, I asked ChatGPT what it thought about NN, over a series of questions. I specifically focused on whether it helps or hinders innovation.

The transcript is below, but some thoughts from me first:

• The text is good. Almost alarmingly good. I found myself saying "good point" a few times. This is probably because it gives reasons in fairly long lists, not just "3 bulletpoints for a slide".
• It seems pretty even-handed, with "proponents say this, others say that"
• You can sense that its training base tends to give it "common" responses and frequently-cited arguments. That doesn't mean they're wrong, but it can lack nuance, or repeat some common *fallacies* as well.
• The long-list approach and comments is quite good at highlighting the need for multiple approaches & reconciling them. A single statistical approach isn't enough - there are also qualitative questions to ask, surveys to undertake and multiple angles to absorb. ChatGPT understands the issue is complex, even if it cannot resolve the complexity itself. Simple answers are wrong.
• I was particularly impressed with the response to my question on cross-border effects, and to separating NN vs. funding effects.
• It struggled with the last question, about Internet and non-Internet innovation. EDIT: I just realised that it ignored my typo, and understood that I meant "directly" when I wrote "direct" in my question
• I'd be very worried if I did bog-standard "content generation" for clickbait blogs, "bucketshop" market research, or corporate social posts. This is all perfectly-usable general blurb if you need slabs of text nobody is going to really delve into too deeply.

All that said, I don't think this is (yet) a gamechanger in terms of analysis and argument. It's good for collating a lot of "food for thought", but as others have pointed out, it can also be "confidently wrong", sometimes in amusing ways.

In a separate chat, I asked it for a contrarian's view of #5G use-cases. While it was right on some things ("Some argue that the vast majority of #IoT devices do not require the high speed and low latency that 5G provides and that the hype around IoT is overblown.") others were less convincing: ("Some argue that 5G may not provide the low latency and high reliability that is being promised, and that there are other technologies, such as wired connections, that are better suited for applications such as autonomous vehicles"). If there's one thing less relevant to self-driving cars than 5G, it's fixed broadband!

Anyway - enjoy the debate treanscribed in full, below.

(Note: the image for this article came from Stable Diffusion, when I asked for a picture showing "An advanced AI debating Net Neutrality")

Me: Does net neutrality help innovation?

ChatGPT: Net neutrality has been a topic of much debate, with proponents arguing that it promotes innovation and others arguing that it stifles it.

Proponents of net neutrality argue that it helps to level the playing field for new entrants and small businesses by preventing Internet Service Providers (ISPs) from discriminating against certain types of traffic or services. This, in turn, encourages innovation, as entrepreneurs and startups are free to bring new products and services to market without fear of being blocked or slowed down by ISPs.

On the other hand, opponents of net neutrality argue that it creates a regulatory burden that stifles innovation and investment in the broadband industry. They argue that without the ability to prioritize different types of traffic, ISPs will be unable to effectively manage their networks and may be forced to limit investment in new infrastructure and technologies.

Ultimately, the impact of net neutrality on innovation is a complex and highly debated issue, and there is no clear consensus on whether it helps or hurts innovation. However, proponents of net neutrality generally believe that it promotes a free and open internet that supports innovation and competition, while opponents believe that it imposes unnecessary regulation that stifles growth and investment.

Me: What research is necessary to reach a better conclusion?

ChatGPT: To reach a more definitive conclusion on the impact of net neutrality on innovation, several types of research would be necessary, including:

1. Economic studies: Economic studies could analyze the impact of net neutrality regulations on investment and innovation in the broadband industry, as well as the impact on consumer prices and access to broadband services.
2. Case studies: Case studies of countries or regions with and without net neutrality regulations could provide valuable insights into the real-world effects of these regulations on innovation and investment in the broadband industry.
3. Surveys and interviews: Surveys and interviews with entrepreneurs, startups, and industry experts could provide insights into the impact of net neutrality on the ability of new entrants to bring new products and services to market.
4. Technical studies: Technical studies could examine the impact of net neutrality regulations on network management and traffic prioritization, and assess the potential impact on network performance, reliability, and security.
5. Long-term data analysis: Long-term data analysis could track changes in investment, innovation, and consumer prices over time in regions with and without net neutrality regulations, providing valuable insights into the long-term impact of these regulations.

Overall, a comprehensive and multi-disciplinary approach to research, combining economic, case study, survey, technical, and data analysis methods, would be necessary to reach a more definitive conclusion on the impact of net neutrality on innovation.

Me: How would you measure innovation in this context?

ChatGPT: Measuring the impact of net neutrality on innovation is a complex task, as innovation can take many forms and can be difficult to quantify. However, several metrics could be used to measure innovation in this context, including:

1. Investment in research and development (R&D): This could be measured by tracking the amount of investment in R&D by broadband companies and startups, as well as the number of patents filed in relevant areas.
2. New product and service launches: This could be measured by tracking the number of new products and services introduced by broadband companies and startups, as well as the market adoption and success of these offerings.
3. Entrepreneurial activity: This could be measured by tracking the number of new startups founded in the broadband industry, as well as the success of these startups in attracting investment and bringing new products and services to market.
4. Consumer benefits: This could be measured by tracking changes in consumer prices, access to broadband services, and the availability of new and innovative online services and applications.
5. Network performance and reliability: This could be measured by tracking changes in network speed, latency, and uptime, as well as the ability of networks to handle new and innovative applications and services.

While these metrics are not exhaustive, they provide a good starting point for measuring the impact of net neutrality on innovation in the broadband industry. By tracking changes in these metrics over time in regions with and without net neutrality regulations, researchers could gain valuable insights into the impact of these regulations on innovation.

Me: A lot of those metrics are international. More regions with net neutrality might increase innovation globally, not locally. How do you account for that?

ChatGPT: You are correct, some of the metrics mentioned could be influenced by factors beyond the borders of a single region. To account for this, it would be important to consider both the local and global impact of net neutrality on innovation.

For example, to measure the local impact of net neutrality, researchers could compare the metrics mentioned in regions with and without net neutrality regulations, taking into account factors such as the local economy, cultural and regulatory environment, and the state of the broadband industry in each region. This would provide valuable insights into the specific impact of net neutrality on innovation within those regions.

To measure the global impact of net neutrality, researchers could compare these metrics on a global scale, taking into account factors such as the state of the global economy, the state of the broadband industry globally, and the regulatory environment in different regions. This would provide a broader perspective on the impact of net neutrality on innovation globally, and could help to identify any trends or patterns that may not be apparent from a regional analysis alone.

Overall, it is important to consider both the local and global impact of net neutrality on innovation to gain a complete and accurate understanding of the impact of these regulations on the broadband industry and innovation more broadly.

Me: How would we know if net neutrality had a larger effect on innovation than availability of financing for startups?

ChatGPT: Determining the relative impact of net neutrality versus the availability of financing on innovation can be challenging, as these factors are often interrelated and can have complex and interconnected effects. However, several approaches could be used to isolate the impact of each factor, including:

1. Comparative studies: Researchers could compare regions with and without net neutrality regulations, but with similar levels of financing available for startups. By controlling for the availability of financing, researchers could isolate the impact of net neutrality on innovation.
2. Historical analysis: Researchers could analyze data from periods of time when net neutrality regulations were in place or not in place, and compare this data with changes in the availability of financing for startups. This would help to identify any correlations between net neutrality and innovation, independent of changes in financing.
3. Causal inference methods: Researchers could use causal inference methods, such as regression analysis, to model the relationship between net neutrality, financing, and innovation, while controlling for other factors that could influence these relationships.
4. Survey and interview-based research: Researchers could survey and interview startups, entrepreneurs, and industry experts to gain insights into the relative importance of net neutrality and financing for innovation. This would provide valuable qualitative data to complement the quantitative data obtained from other research methods.

Overall, a multi-disciplinary and multi-method approach, incorporating comparative studies, historical analysis, causal inference methods, and survey and interview-based research, would be necessary to determine the relative impact of net neutrality and financing on innovation in a robust and comprehensive manner.

Me: How do you distinguish innovations that direct relate to Internet access, compared to those which involve non-Internet applications and technologies?

ChatGPT: Distinguishing innovations that directly relate to Internet access versus those that involve non-Internet applications and technologies can be challenging, as many innovations are influenced by both Internet access and non-Internet technologies. However, several approaches could be used to differentiate these types of innovations, including:

1. Technical classification: Innovations could be classified based on their underlying technologies, with innovations that rely primarily on Internet access being classified as Internet-related innovations and innovations that rely primarily on non-Internet technologies being classified as non-Internet-related innovations.
2. Market classification: Innovations could be classified based on the markets they serve, with innovations that serve primarily Internet-based markets, such as online commerce or online communication, being classified as Internet-related innovations and innovations that serve primarily non-Internet-based markets, such as manufacturing or agriculture, being classified as non-Internet-related innovations.
3. End-user classification: Innovations could be classified based on their end-users, with innovations that are primarily designed for use by individuals accessing the Internet being classified as Internet-related innovations and innovations that are primarily designed for use by individuals not accessing the Internet being classified as non-Internet-related innovations.

It is important to note that these classifications are not mutually exclusive, and that many innovations may have elements of both Internet-related and non-Internet-related technologies, markets, and end-users. Nevertheless, using these classifications can provide valuable insights into the extent to which innovations are influenced by Internet access, and can help to distinguish Internet-related innovations from non-Internet-related innovations.