Cloud Wash Laundry Corporation logoCloud Wash Laundry CorporationDistributed AI infrastructure
EDGE AI • HEAT RECOVERY • WATER EFFICIENCY • DISTRIBUTED RESILIENCE • MICRO DATA CENTERS • COMMUNITY INFRASTRUCTURE • DARK-FIBRE SCALE-ACROSS • NVIDIA SPECTRUM-XGS • CHALLENGING MEGA DATA CENTRESEDGE AI • HEAT RECOVERY • WATER EFFICIENCY • DISTRIBUTED RESILIENCE • MICRO DATA CENTERS • COMMUNITY INFRASTRUCTURE • DARK-FIBRE SCALE-ACROSS • NVIDIA SPECTRUM-XGS • CHALLENGING MEGA DATA CENTRES
Environmental benefits

Lower emissions, lower freshwater demand, better use of existing assets.

Environmental performance comes from a combination of heat reuse, solar assistance, reduced duplication of infrastructure and more efficient water handling.

Why conventional data centres face resistance

The public sees the water, power, land and waste-heat problem.

Large centralized data centres can concentrate electricity demand, cooling-water demand, land use and rejected heat in one place. Cloud Wash is designed around the opposite proposition: distribute compute into compatible existing businesses, recover useful heat first, and use water only where it materially improves rejection.

Water

The current Los Angeles screening model uses 74 m³/year of direct evaporative water in its central case. A dry-only captured-loop sensitivity uses zero direct cooling water, while a 0.6× rated-IT hybrid cooler rejects all captured heat with at most 217 m³/year of recycled host water in the screened cases.

Useful heat instead of waste heat

Under the optimistic fully temperature-compatible bound, 50.38 GWh/year becomes useful process heat: 79.4% of IT electricity and 93.4% of modeled host thermal demand. Lower temperature compatibility materially reduces that benefit.

Existing sites, not giant greenfield campuses

Car washes and laundromats already have recurring thermal demand. The current model treats that demand as the siting and capacity constraint rather than assuming arbitrary compute density can be accommodated. The network layer then uses dedicated dark fibre and NVIDIA Spectrum-XGS scale-across networking to test whether environmental benefits can be gained without sacrificing the workload-level function normally used to justify a mega data centre.

32B litresModeled freshwater savings per year at 10,000 sites.
3 MtModeled annual CO₂ avoidance at 10,000 sites.
17,500 sitesBull parent-company scenario used for the largest 20-year rollout case.
Retrofit firstUsing existing businesses can avoid part of the footprint of entirely new campuses.
Environmental mitigation slide
Environmental mitigationNetwork-scale water and emissions benefits.
Parent revenue sources page
Revenue sources & efficiencyOperating economics, energy efficiency and heat-reuse savings.

Environmental figures are modeled scenario outputs and require site-specific engineering and measurement before project-level verification.

Current fanless photovoltaic-thermal roof heat-rejection model
Water and rejection

Water is an adaptive resource, not the default operating mode.

The current Los Angeles heat-sink-siting model uses 74 m³/year of central direct evaporative water. A dry-only captured-loop sensitivity reduces modeled direct cooling water to zero, while a hybrid cooler sized at 0.6× rated IT rejects all captured heat with at most 217 m³/year of recycled host water in the screened cases.

The companion 170 m² PVT model rejects about 502 W/m² dry and 661 W/m² at the reference wet point. At wetting duty 0.35 it reaches about 1.32× dry-passive capacity while using roughly 38% less water than the reference evaporative cooler. An 85% water-reduction target is possible only at a lower capacity gain of about 1.06×, making the water/capacity trade-off explicit.

Open science downloads

Current papers, methods and model limits.

First page of the current heat-sink-constrained distributed AI infrastructure manuscript

Heat-sink-constrained siting of distributed AI infrastructure: energy, carbon and water impacts in Los Angeles

The current deterministic hourly study places 6,160 B300-equivalent accelerators across 120 representative car-wash and laundromat hosts and tests useful heat, carbon, water, climate and metropolitan-network constraints. Its network programme uses NVIDIA Spectrum-XGS as the scale-across layer over dedicated optical fibre and specifies fibre-spool and multi-site experiments to test whether distributed sites can match co-located clusters — the key experiment behind the project’s objective of proving that mega data centres can become obsolete as the default architecture for many workloads.

Current paper PDFModel + files
First page of the current mechanism-resolved fanless photovoltaic-thermal heat-rejection manuscript

Mechanism-resolved modeling and adaptive control of a fanless photovoltaic-thermal heat-rejection array

The current 170 m² roof-array study resolves passive and wetted mechanisms separately, quantifies the water-capacity trade-off, rejects array-wide ionic wind on energetic grounds and tests roof-area matching from micro facilities to hyperscale.

Current paper PDFDOCXModel + files
Central architecture challenge

The goal: prove the mega data centre is no longer necessary.

Cloud Wash Laundry is being designed around a direct technical challenge to the conventional mega-campus model: place compute where useful heat already exists, then connect those heat-sink-sited AI factories with dedicated dark fibre and NVIDIA Spectrum-XGS scale-across networking so the distributed sites can operate as one metropolitan compute fabric.

The dark fibre is the dedicated optical transport; Spectrum-XGS is NVIDIA’s scale-across networking layer. The project’s proposed fibre-spool testbed and multi-site field pilot are intended to determine whether distributed sites can match co-located clusters on workload-level measures such as time-to-result and energy per token.

Latest physical-model findings

Measured next. Modeled now. Heat-sink constrained.

Current design-stage results combine the 120-host Los Angeles heat-sink-siting model with the updated fanless heat-rejection screening figure. They are screening outputs, not field-certified performance. In parallel, the network programme tests whether NVIDIA Spectrum-XGS scale-across networking over dedicated dark fibre can make geographically separated AI factories behave as one compute system. The mega-data-centre conclusion remains an experimental objective, not an already validated result.

Distributed-AI paper PDFFanless-PVT paper PDF
79.4%IT electricity converted to useful process heat in the optimistic fully temperature-compatible heat-sink bound
77.6%same-supply operational emissions reduction at 43 gCO₂e/kWh in that upper-bound compatibility case
74 m³/yrcentral direct evaporative water in the current Los Angeles screening model
44.2%reduction in wetted states under dispatch in the current fanless heat-rejection screening figure
120 / 67 stateswater-eligible states versus wetted states under dispatch in the current screening summary
3-site dark-fibre pilotplanned workload-level validation of the NVIDIA Spectrum-XGS scale-across architecture against a co-located reference

The 79.4% and 77.6% values use the optimistic fT = 1.00 temperature-compatibility bound; lower compatible heat fractions materially reduce both benefits. The updated fanless heat-rejection figure also summarizes 83 of 144 states as feasible overall and 77 of 144 as feasible by free pathways alone, while array-wide EHD is not preferred because only 3 of 80 tested cases exceed the conservative comparator.