TL;DR · 30-second read
The Short Version
Big data centers keep diesel generators on standby so websites and apps stay up when the power grid fails. Those generators burn fossil fuel.
Sabey Data Centers is testing a substitute at its site in Austin, Texas: a diesel made from vegetable oil and waste fats such as used cooking oil. It runs in the existing engines with no changes.
The catch is that government lab research finds it cuts planet-warming gases by as little as 40% or as much as 86%, depending on what it is made from. Where the oil comes from matters more than the engine.
Sabey Data Centers announced on Oct. 30, 2026, that it is piloting hydrotreated vegetable oil (HVO), a renewable diesel, as the primary fuel for backup generators at its Sabey Data Center Austin (SDC Austin) campus. The company says HVO can be used in existing diesel generators without engine modifications, and that the pilot will test whether the fuel is feasible for broader use across its portfolio.
Sabey cited a 2022 peer-reviewed study by the U.S. Department of Energy’s Argonne National Laboratory finding that renewable diesel made from waste-based feedstocks cuts lifecycle greenhouse gas emissions by 79% to 86% compared with petroleum diesel, while crop-based feedstocks deliver reductions of 40% to 69%. The company says it will track the feedstock behind the fuel it burns and, if results support a transition, expand testing to additional sites.
Executive Summary
Backup generators are a small but stubborn part of a data center’s carbon footprint. They run rarely, but because the operator owns them and burns fuel on site, their emissions count as Scope 1, the category a company cannot address simply by buying renewable electricity. Sabey’s Austin pilot targets that line item with a fuel swap rather than an equipment swap.
The practical appeal is that renewable diesel is a drop-in fuel: the same generators, tanks and maintenance routines stay in place, so there is no stranded hardware and no redesign of a facility’s resilience plan. The harder question is what the swap actually achieves. By the Argonne figures Sabey itself cites, the climate benefit roughly doubles depending on whether the fuel is made from waste fats or from crops.
That makes Sabey’s commitment to track feedstock the most consequential detail in the announcement. A drop-in fuel moves the decarbonization problem out of the engine room and into the fuel supply chain, and the pilot’s value to the wider industry will depend on how rigorously that supply chain is verified and reported.
The Engine Is Settled; the Supply Chain Is the Variable
The phrase “drop-in replacement” answers an engineering question: can a generator burn this fuel without modification? Sabey says it can. It does not answer the climate question, because lifecycle emissions are determined upstream, in how the feedstock was grown or collected and how it was processed into fuel. The Argonne study Sabey cites puts numbers on that spread. Renewable diesel from waste-based feedstocks such as used cooking oil cut lifecycle emissions by 79% to 86% versus petroleum diesel. Crop-based versions came in at 40% to 69%.
Put plainly, two tanks of fuel that look and perform identically at the generator can differ in climate impact by a factor of two at the extremes. For a data center operator, this means the decarbonization decision is effectively a procurement decision: which supplier, which feedstock, what certification, and at what price. Sabey acknowledges this directly, saying fuel origin determines the climate benefit and that it will track the feedstock behind the HVO it burns.
The people affected are not only Sabey’s facilities teams. Tenants in technology, finance and healthcare that report their own supply-chain emissions will want to know which end of the range their provider’s backup fuel falls on. Fuel suppliers, in turn, face buyers who will ask for traceability, not just a renewable label. Under widely used greenhouse gas accounting conventions, carbon released from burning biologically derived fuel is often reported separately from fossil emissions, which is another reason the method behind any eventual emissions claim will matter.
Why Backup Power Is a Hard Emissions Line to Move
Most of a data center’s carbon footprint comes from the electricity it buys, which operators can address through renewable power contracts. Backup generators are different. They sit on site, the operator owns them, and the fuel is combusted directly, so the emissions are Scope 1. Sabey notes that overall fuel consumption from backup generation is limited, since generators mainly run during outages, emergencies and testing, but it calls this one of the more challenging emissions sources to reduce.
The difficulty is that the alternatives to diesel generators typically involve replacing or supplementing the equipment itself, a capital-intensive change to systems designed around proven reliability. A fuel substitution sidesteps that. If it works, operators can lower the carbon intensity of an installed fleet without retiring generators early or re-engineering how a facility rides through a grid failure.
That framing also sets realistic expectations. Because backup generators run infrequently, the absolute emissions reduction at any single site may be modest relative to the facility’s electricity footprint. The significance lies in addressing a category that renewable electricity purchasing cannot touch, rather than in the size of the tonnage.
Reliability Is What the Pilot Is Really Testing
Sabey frames the pilot as evaluating HVO “under real-world operating conditions” while maintaining mission-critical reliability. For data centers, that is the gating criterion. Backup fuel has to be available, stored and ready to perform at the moment the grid fails, and any fuel change will be judged first on whether it compromises that readiness.
The company’s language is notably conditional. It describes exploring lower-carbon fuels across its portfolio “where fuel availability and operating conditions allow,” and says it intends to expand testing only if pilot results support a transition. That is a measured position: it signals that regional fuel supply, not just performance, could limit how far the approach travels beyond Austin.
What the Announcement Establishes, and What It Does Not
The release substantiates a few things clearly: the pilot exists, it is at SDC Austin, HVO is being used as the primary generator fuel, and Sabey has committed to tracking feedstock. It also cites a specific, named study for the potential emissions benefit, which is more than many sustainability announcements offer.
What it does not establish is scale or outcome. The 40% to 86% range describes renewable diesel generally, not results Sabey has measured. The release does not state how many generators are involved, how much fuel is being used, which feedstock the current supply comes from, or when results will be reported. Those details will determine whether this becomes a portfolio-wide practice or remains a single-site trial.
Background
Sabey Data Centers is one of the largest privately owned data center developers and operators in the United States, serving technology, financial and healthcare customers. It builds on the more than 50-year history of Sabey Corporation, and its Austin, Texas campus, SDC Austin, is the site of the renewable diesel pilot.
Data centers typically rely on diesel generators as a safeguard against grid outages, keeping servers running until utility power returns. Because these generators are owned and fueled on site, their emissions are classed as Scope 1. Renewable diesels such as HVO have emerged as a way to cut those emissions using existing engines, with the climate benefit varying by the raw material used to make the fuel. Source: Could Vegetable Oil Power a Cleaner Digital Future? Sabey Data Centers is Finding Out, Sabey Data Centers’ announcement of its HVO renewable diesel backup generator pilot at SDC Austin.Sources