Data Center Equipment

Me today dealing with some EMC issues… 🧙♂️🪄🐉 EMC might feel like black magic sometimes, but it’s not all spells and wand-waving. Here’s the checklist I worked through today to troubleshoot: 1️⃣ 𝗕𝗲 𝘄𝗮𝗿𝘆 𝗼𝗳 𝘄𝗶𝗿𝗶𝗻𝗴 𝗮𝗰𝘁𝗶𝗻𝗴 𝗹𝗶𝗸𝗲 𝗮𝗻 𝗮𝗻𝘁𝗲𝗻𝗻𝗮. Anything with wiring can pick up noise and radiate it—even cables that seem unrelated to your core system. If the cable isn’t critical, remove it and retest to isolate the problem. If you can’t remove it, try adding a ferrite ring to the cable as close to the board as possible On the PCB, ferrite beads or chokes can also help suppress noise if you’ve got space to add them. 2️⃣ 𝗦𝗹𝗼𝘄 𝗱𝗼𝘄𝗻 𝘆𝗼𝘂𝗿 𝗠𝗢𝗦𝗙𝗘𝗧 𝗴𝗮𝘁𝗲 𝗱𝗿𝗶𝘃𝗲 𝘀𝗶𝗴𝗻𝗮𝗹𝘀. This is one of the top culprits for EMI on motor drive boards. Increasing both the turn-on and turn-off resistors for your MOSFET gate drive slows the rise and fall times of the signal, which directly cuts down on emissions. 3️⃣ 𝗥𝗲𝗱𝘂𝗰𝗲 𝗣𝗪𝗠 𝗳𝗿𝗲𝗾𝘂𝗲𝗻𝗰𝗶𝗲𝘀. We had a 250kHz PWM signal driving a battery charger boost converter. The lab results weren’t happy, so we made some changes: - Dropped the frequency to 75kHz. - Increased the inductor value to match the new frequency. - Slowed down the MOSFET rise time (see point 2). This got us under the threshold—barely (around 2dB). We’ll reduce the charge current by about 15% to get a little more breathing room. 4️⃣ 𝗖𝗵𝗲𝗰𝗸 𝘆𝗼𝘂𝗿 𝗿𝗲𝘁𝘂𝗿𝗻 𝗽𝗮𝘁𝗵𝘀. High-current or high-frequency signals need clean return paths—no exceptions. In our case, we were stuck with a 2-layer PCB (budget constraints, of course), and the ground return path for the low-side MOSFET gate drive signal ended up being pretty big. I spotted a way to reduce the loop area by adding a via. We drilled a quick hole in the board and connected it with a wire. Not pretty, but it worked! The layout will need redoing, but this hack let us verify the solution at the test lab. If you haven’t already, check out 𝗔 𝗛𝗮𝗻𝗱𝗯𝗼𝗼𝗸 𝗼𝗳 𝗕𝗹𝗮𝗰𝗸 𝗠𝗮𝗴𝗶𝗰 𝗯𝘆 𝗛𝗼𝘄𝗮𝗿𝗱 𝗝𝗼𝗵𝗻𝘀𝗼𝗻. It’s the go-to resource for high speed digital electronics theory, and will let you analyse EMC issues way more effectively. What are your favorite resources for EMC troubleshooting? Drop them below—I’m always on the lookout for more tools/knowledge to add to my wizarding arsenal! 🪄 ------------- 🔔 Follow Ryan Dunwoody for more hardware chat 🚀 ♻️ Repost if you're an EMC wizard (or would like to be) 🧙♂️

Meta is building dozens of massive tents at campuses across the US, sticking billions of dollars of chips inside, and powering them with off-grid turbines. The AI race has officially entered its Mad Max phase. Over the last month, I reviewed hundreds of documents and satellite images for Cleanview's latest report on behind-the-meter data centers. Meta's data center strategy, which is very visible from space, was one of the weirder approaches I came across. Mark Zuckerberg recently ditched the data center designs that Meta had perfected over the last decade and told his team to stick tens of thousands of chips in tents outside their data center in New Albany, Ohio. Each of these chips costs about $60,000. Zuckerberg plans to stick billions of dollars worth of them in the tents. The strategy has helped cut the time to build compute in half. The first five buildings at Meta’s New Albany, Ohio data center took between two and three years to build. Meta started building five ~125,000 square foot tents between April and June of 2026, according to city permits. Satellite images show the structures have all been built. To power those "rapid deployment structures", as they are officially named, Meta signed a 10-year deal with Williams to build a pair of 200 MW off-grid power plants. Those power plants began construction about a year ago and are nearly complete. Meta is using the same strategy to build a data center in Tennessee, bringing the total count of tent data centers to three. Strategies like this are part of the reason behind-the-meter data center capacity is growing so quickly. In Cleanview's report, I found that there's currently about 2 GW of BTM capacity online today. By the end of the year, it will likely be 3 GW—equivalent to three nuclear power plants. By the end of 2027, it could be as high as 13 GW—more than the power demand of NYC. I've been talking to a lot of reporters about this research. When I told one reporter about these tents and other companies powering their data centers with jet engines, he said, "It's like a scene out of the movie Mad Max."

EnergyEvening: Northern Norway - where the largest European data centers get built. Our journey through Northern Norway also took us past the construction site of Europe’s largest datacenter. The location: Close to Narvik, in the middle of nowhere, but close to a high-voltage substation. Why here? First and foremost, there is plenty of power at attractive costs. NO4 (the name of the Northern Norway electricity zone) still exported up to 1 GW of power to Sweden and the rest of Norway during most of the last two weeks. And it should be noted that these were exceptional weeks with temperatures typically averaging below -5°C. Now consider that plenty of households are heating their homes with electric resistance heaters and heat pumps. So, these were high consumption weeks. Power prices were thus higher than usual during this period but still below 100 EUR/MWh even during peak hours. Secondly, the cold temperatures come with another side effect: Data center produce a lot of heat and the arctic temperatures provide highly efficient natural cooling. This reduces the power consumption and costs. It is hence not surprising that the developers of the Stargate Norway project have settled here. The datacenter will consume 230 MW electric power in the first stage and could see a later extension to 520MW, a size that outruns most - if not all - datacenters in the rest of Europe. Developed and built by Aker and Nscale, equipped with Nvidia technology and serving OpenAI and Microsoft as initial customer - this datacenter has the most important players involved. I am really excited to see this growth opportunity for such a remote region. I wish we could create similar projects in Switzerland. If we manage to find real estate and build power infrastructure, this might even be possible. It just needs a bit of pioneering spirit. Read more about the project here: https://lnkd.in/e_7wtTeR

Everyone's chasing data center land. Almost everyone is missing the real constraint. It's not fiber. It's not even land. It's power. U.S. Interior Secretary Doug Burgum said at the Prologis conference: "To win the AI arms race against China, we've got to figure out how to build these artificial intelligence factories close to where the power is produced, and just skip the years of trying to get permitting for pipelines and transmission lines." Translation: The next generation of data centers won't be built where the land is cheap. They'll be built where the power is available. Three implications for dirt investors: 1. Nuclear Proximity = New Premium: Amazon already signed deals with Dominion Energy near the North Anna nuclear power station in Virginia and expanded partnerships with Talen Energy at the Susquehanna nuclear plant. Sites within transmission distance of existing nuclear facilities just became exponentially more valuable. 2. Warehouse Conversions Accelerate: If Prologis is eyeing their 6,000 buildings for data center conversion, every industrial site with surplus power capacity needs re-evaluation. What looks like a struggling warehouse today might be a data center tomorrow. 3. Grid Capacity > Geographic Desirability: Constellation Energy CEO Joseph Dominguez noted that data economy customers "want to run their systems 24-7" with "firm pricing so that they know the price for energy for 20 years". Long-term power contracts are becoming the new land entitlements. But here's what nobody's talking about: The same power constraints driving this opportunity are also creating massive project risks. According to a recent CoStar analysis, data centers will account for up to 60% of total power load growth through 2030. But there's a timing mismatch: data centers take 2-3 years to build, while power system upgrades take 8 years. That gap is forcing developers to either wait or find sites with existing capacity. The Community Resistance Factor Data Center Watch estimates $64 billion in data center projects were blocked or delayed over a recent two-year period. There are now 142 activist groups across 24 states organizing against data center development. Northern Virginia alone-the nation's largest data center market-has 42 activist groups fighting projects. Reasons cited: water consumption, higher utility bills, noise, decreased property values, loss of open space. Translation for land investors: Sites with existing power capacity + community support just became exponentially more valuable than sites with just land and zoning. The power infrastructure thesis isn't just about finding available capacity. It's about finding that capacity in counties that actually want data centers. Not every market will roll out the welcome mat. Are you evaluating community sentiment alongside power infrastructure access?

Land acquisition and securing utilities and permitting for data centers in Africa can be a harrowing experience. Somebody needs to write up a digest of all the crazy stories 😅 I enjoyed sharing Agility Logistics Parks’ experiences in land acquisition and securing utilities and permitting for our pan-African logistics parks platform, at ITW Africa in Nairobi - it’s given us invaluable experience and land bank that we hope to leverage to help data center operators grow faster in Africa. At ITW Africa, I heard two data center operators talk about how they discovered the land plots they bought actually belonged to different owners. A CEO of an African data center operator shared his fascinating story. He wanted to build his data center close to the cable landing station and identified land in a village close to the CLS. The problem was that many villagers claimed to own the same land parcels and there would be many sales / transactions of the same land plots. So when he eventually bought a land plot, he ensured the village chief and four other senior elders from the village were witnesses. The CEO went himself to the land registry to ensure it was registered properly. Imagine a data center CEO having to do that in any developed market. There was no road to the site so he built a road to the site. There was no grid connection to the site so he built his own independent power plant. It was a journey of over a decade. It was a first mover advantage with such high barriers to entry. And sure enough, demand came from global hyperscalers and his business became a very attractive one. Good things do happen in Africa to those who are patient and persistent - and who can figure out land acquisition, utilities and permitting in a timely way 😅 #africa #datacenters #datacentres #digitalinfrastructure

Increasing both the capacity and number of data centers is fundamental to the growth of AI, but they have become a lightning rod for criticism from local residents and politicians alike as they are causing higher energy prices and using scarce water resources in a growing number of regions globally. On a recent episode of the Bloomberg Switched on Podcast, Tom Rowlands-Rees and Lloyd Arnold, BloombergNEF's Global Power Analyst and Data Center Analyst, respectively, discussed “What Really Determines Where Data Centers Get Built”. The decision about where to site data centers is becoming more complex, with decision makers having to factor in energy & water availability and cost, as well as land permitting. However, other criteria are becoming more important, including taxes, fiber connectivity, and existing ecosystems, which are impacting competitiveness, given that tech companies remain focused on sustainability and net zero initiatives. Key takeaways from the podcast include: · Power constraints are now the biggest bottleneck - Many regions face grid congestion, long interconnection queues, and rising competition for electricity from AI, electrification, and industrial loads. Access to reliable, low‑carbon power is becoming a decisive factor in site selection. · Regional competitiveness is diverging - Markets with streamlined permitting, strong renewable‑energy pipelines, and supportive policy frameworks are pulling ahead. Others are struggling with regulatory complexity, land scarcity, or slow infrastructure build‑out. · Construction timelines are lengthening - Supply‑chain pressures, skilled‑labor shortages, and stricter environmental reviews are extending development cycles. Speed to market is becoming a differentiator — and a challenge. · Geopolitics and resilience matter more than ever - Operators are diversifying locations to reduce exposure to geopolitical risk, extreme weather, and single‑grid dependency. Redundancy is becoming a strategic asset. · Permitting and land availability remain major hurdles in dense metros, pushing operators toward secondary markets. · AI workloads are reshaping design, driving higher rack densities[JB1] , new cooling strategies, and unprecedented energy demand forecasts. · Sustainability pressures are rising, with operators expected to prove real emissions reductions, not just offsets. Data center growth will continue, although some regions will be slower due to the challenges mentioned above. However, with so much capital being invested into the AI sector, we should expect that data center hyperscalers will be willing to overpay for the power and water needed to start the permitting and building process.      Listen on Apple Podcasts: https://lnkd.in/gSw5GwKM #ai; #datacenters; #hyperscalers; #renewableenergy; EcoTech Capital Cy Obert Jeffrey Lipton

They built submarines for the navy. Now they're building data centers. Viral clips show fish gliding past glowing server racks underwater. Pretty. Sci-fi. Also fake. Real underwater data centers are sealed steel pods. No windows. No fish. Just racks running about 35 meters down. In 2020, engineers at China's Highlander Group—people who worked on naval submarine systems—asked a simple question: what if the ocean did the cooling? Off the coast of Hainan, they lowered 1,300-ton capsules to the seafloor. They've run commercially since 2023, with zero reported server failures. That matters because regular data centers waste a lot of power on cooling—often 30–40% of their electricity. They also compete with farms and cities for freshwater. A hyperscale site can use as much water as a small town. Underwater pods change the math: ↳ Seawater moves through radiators behind the racks ↳ No freshwater ↳ Power use drops 30% or more ↳ PUE as low as 1.07 (industry average: ~1.5) ↳ A sealed box means less dust, less corrosion, fewer breakdowns Tencent, Alibaba, and China Telecom are already customers. Plans call for 100 pods, which would save 122 million kWh of electricity and 105,000 tons of freshwater each year. Near Shanghai, another project pushes further: 198 server cabinets powered by 97% offshore wind, with a goal of scaling to 500 MW clusters. Microsoft tested the idea with Project Natick. It worked. Then they stopped. China didn't. Scale changes what this is: 1 pod proves it can run. 10 pods support a region. 100 pods build national compute without draining aquifers. For decades we've built data centers that fight their surroundings. What if the ocean is the cooling system? Sources: You Xiaoying (2025) , Scientific American, Merics, Data Center Dynamics, Wired Video: @heyshrutimishra. Not real fictional representation.

Purpose of a Signal Reference Grid (SRG) for a Data Center Raised Floor A Signal Reference Grid (SRG) — also called an equipotential grounding grid — is a key part of a data center’s grounding and bonding system. It provides a low-impedance path for electrical noise and transient currents, ensuring stable reference voltages for sensitive IT equipment. Main Purposes: 1. Reduce Electrical Noise (EMI/RFI): The SRG minimizes electromagnetic interference and radio frequency interference by providing a consistent reference potential for all electronic equipment. 2. Ensure Equipotential Bonding: All metallic structures — such as racks, cabinets, cable trays, and raised floor pedestals — are bonded to the SRG. This ensures that no potential difference exists between equipment, preventing ground loops and signal disturbances. 3. Improve System Reliability: By maintaining a stable electrical reference, the SRG reduces data transmission errors, equipment malfunctions, and downtime caused by electrical noise or static discharge. 4. Enhance Safety: The SRG helps dissipate fault currents safely to the main grounding system, reducing shock hazards for personnel and protecting equipment from damage. 5. Support High-Frequency Performance: Modern data centers run high-speed digital signals. The SRG provides a low-impedance path for high-frequency return currents, ensuring signal integrity and optimal equipment performance. Typical Implementation: 👉 A copper mesh (e.g., 2 ft × 2 ft or 600 mm × 600 mm) is installed beneath the raised floor. 👉 All floor pedestals, equipment racks, and metallic pathways are bonded to the grid. 👉 The grid is connected to the main building grounding system at multiple points. #DataCenter, #SRG

Peter Thiel just led a $140 million Series B for Panthalassa — an Oregon-based startup building autonomous wave-powered compute nodes that float in open ocean — at a reported valuation of nearly $1 billion. The technical design is worth understanding in full because it is more sophisticated than the headline suggests. Each node is an 85-meter steel structure that converts wave motion into electricity to power onboard AI chips. Cooling is handled entirely by seawater — eliminating one of the most significant cost and infrastructure challenges in conventional data center design. Once deployed, nodes navigate to remote waters autonomously using passive hull geometry rather than engines. AI outputs are transmitted back via SpaceX Starlink. No land acquisition. No grid connection. No cooling towers. No local opposition. The funding will complete a pilot manufacturing facility near Portland and deploy the first commercial nodes in the Pacific Ocean, with broader rollout targeted for 2027. The strategic context makes this raise particularly timely. AI data center construction has become one of the most contested infrastructure conversations in the United States. Local opposition is intensifying. Grid capacity constraints are real and worsening. The energy demand projections from frontier AI training are running ahead of what conventional land-based infrastructure can absorb at the required pace. Elon Musk and Google have both explored space-based compute as a long-term solution. Both remain years from practical deployment at any meaningful scale. Ocean-based infrastructure is a nearer-term alternative that sidesteps the land, energy, and political constraints that are slowing conventional data center buildout simultaneously. Thiel's framing to the Financial Times — that extraterrestrial compute solutions are no longer science fiction and that Panthalassa has opened the ocean frontier — is characteristically bold. But the underlying infrastructure problem it is responding to is entirely real and growing more acute each quarter. The ocean covers 71% of the planet's surface. The AI industry is running out of viable land. The direction of travel here is not difficult to read.

We're Building Africa's Internet on Diesel Fumes 🔌 Look at that map. Fiber everywhere. Submarine cables wrapping the continent. Population clusters glowing with digital potential. Now look at what's missing: reliable power. The Paradox Africa's data centre market will double by 2030—fastest growth globally. Lagos. Nairobi. Accra. Cairo. Tier III facilities rising. Hyperscale investment flowing. The problem? We're running the future on backup generators. The Numbers Are Brutal <1% of global data centre capacity Most African data still hosted in Europe/North America Facilities run 60-80% on diesel (global average: 10-15%) Translation: Higher costs. Massive carbon emissions. Hard growth ceiling. You can't scale cloud on a broken grid. You can't run AI on generators. Why This Actually Matters This isn't just about tech infrastructure: Economic sovereignty: Every app interaction routing through foreign servers = value exported AI economy: Can't participate when you're renting compute power abroad Jobs: Data centres need engineers, technicians, cybersecurity experts—all exported when we host elsewhere User experience: Try running fintech or telemedicine with 200ms lag to European servers What Needs to Happen Co-locate energy + data: Build facilities with dedicated renewable plants (solar + battery storage), not grid-dependent Smart siting: Build near existing power—hydro (Ethiopia, DRC), geothermal (Kenya), gas hubs (Nigeria) Regulatory push: Tax breaks for renewables. Data localization mandates for sensitive sectors Examples working now: 🇰🇪 Kenya: Geothermal-powered facilities 🇿🇦 South Africa: Multi-source energy strategy 🇪🇬 Egypt: Leveraging gas reserves The Real Opportunity Africa has: ✅ Abundant renewable potential ✅ 1.4 billion people increasingly online ✅ Young, data-hungry population ✅ Growing tech ecosystems The blueprint: Don't just build data centres. Build energy-independent digital infrastructure hubs. Bottom Line Fiber without power is like highways without fuel stations. You've got the roads—but nobody's driving. Africa's digital future doesn't start with code or cloud credits. It starts with kilowatts. 🗣 Your take: What's the smartest energy + digital play you've seen in Africa? Which country is getting this right? Drop your thoughts. 👇 Follow for real talk on Africa's infrastructure, digital economy, and the hard truths nobody publishes in glossy reports. #Africa #DataCentres #DigitalInfrastructure #RenewableEnergy #CloudComputing #EmergingMarkets #EnergyTransition #AfricanTech #Infrastructure