Cooling strategy

Cooling that supports heat reuse first, rejection second.

Rather than treating heat only as a waste stream, the design routes it through productive uses and uses rejection equipment primarily for surplus conditions.

Liquid cooling

Direct liquid cooling captures heat efficiently from dense compute hardware and makes it available for transfer.

Heat exchange

Heat exchangers separate loops while moving useful thermal energy into hot water or process loads.

Hybrid solar preheat

Solar thermal and PVT systems can reduce auxiliary heating needs and improve overall system efficiency.

Evaporative rejection

When useful thermal demand is saturated, the system can reject remaining heat through the final cooling stage.

Seasonal flexibility

Winter and shoulder-season demand patterns improve the value of recovered heat for laundries and wash facilities.

Controls & safety

Valves, pumps and bypasses allow the operator to route heat safely according to current demand and temperatures.

Heat-rejection equipment is only part of the story.

Cooling, water treatment and heat reuse operate as one combined system rather than separate, isolated subsystems. This thermal architecture is paired with a dedicated dark-fibre scale-across network so compute can be distributed according to useful heat sinks instead of being forced into a mega data centre simply to keep accelerators physically co-located.

Updated fanless heat-rejection figure

Corrected cooling summary: dry first, wet only when dispatch requires it.

Fanless heat rejection figure showing passive buoyant, radiative, evaporative and electrohydrodynamic pathways

44.2%Reduction in wetted states under dispatch in the updated fanless heat-rejection figure.

120 vs 67Water-eligible states versus wetted states under dispatch in the screening summary.

83 of 144States feasible in the overall screening summary.

77 of 144States feasible by free pathways alone in the current figure summary.

Array-wide electrohydrodynamic augmentation is not part of the preferred architecture: the corrected figure summarizes only 3 of 80 tested EHD cases as exceeding the conservative comparator, and the broader thermal strategy still prioritizes passive buoyancy, radiative rejection, and selective wetting when required.

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 PDF Model + 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 PDF DOCX Model + files

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.

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.