The International Energy Agency (IEA) has reported that DCs consumed about 220–320 TWh in 2020, which is 0.9–1.3 percent of the global electricity demand and accounted for 330 million metric tons (MT) of carbon dioxide equivalent emissions. This substantial energy and carbon footprint of DCs has been a concern for public authorities and policymakers worldwide.  

Moreover, the significant amounts of waste heat generated by DCs require energy-intensive cooling systems to manage the increased heat dissipation demands associated with average rack power densities increasing beyond 8 kW in 2020. It is, therefore, essential to develop new methods to dissipate power dense IT equipment while also recovering waste heat from the rack. 

The potential for waste heat recovery will continue to grow as the DC industry itself grows. Lawrence Berkeley National Lab in 2023 forecasted that the DC industry will grow from the 2023 value of roughly 180 TWh to a range of 320 to 580 TWh in 2028, with further growth beyond. This growth is largely due to the ever-increasing hardware needs for AI training systems. It is therefore vital that some heat reuse practices be standardized ahead of this industrial growth. 

DCs can consume up to hundreds of MW of power, and nearly all that electricity is converted into heat. That heat is available energy that could be put to beneficial use, potentially reducing operating costs and environmental burden. The industry realizes this and is increasingly focused on adopting waste heat recovery practices from DCs to benefit areas such as agriculture and HVAC systems. Examples also include heating swimming pools, using the waste heat for fermentation, and developing hydronic systems for melting ice on sidewalks. 

The paper presented a thermo-economic analysis (TEA) of a novel cooling and enhanced heat recovery (CEHR) system for DCs. We calculate three financial metrics (net present value—NPV, return on investment—ROI, and payback period—PP) for hot and chilled water generation. Hot water generation uses vapor recompression to produce water at approximately 75 °C. Chilled water generation builds upon the hot water generation scenario by feeding the hot water stream into an absorption chiller.
Without considering the additional costs for connecting the infrastructure with the customer, we found a payback period shorter than two years for a hot water generation system for a base case assuming a 10-MW DC in Philadelphia, where carbon credits are included. And the economies of scale enable favorable payback periods for integrating hot water generation for facilities beyond 7 MW. Hot water generation is especially favorable in Singapore, for example, when replacing natural gas-based heating or hot water heat pumps. 

Reusing waste heat should benefit the supplier and the consumer. The lowest hanging fruit lies in those applications that do not have a specific individual third party consumer such as in connecting to a large district heating network or in reusing the heat in the DC itself. The latter has compelled us to focus our research on novel methods to reuse waste heat in the DC such as in providing additional cooling. 

It should be noted that while this study focuses on the economic feasibility of the proposed system, other challenges exist such as configuring the control system to enable hot water generation for varying external applications and addressing long-term maintenance issues due to system strain under cyclical compressor operation. Floor space may also be limited for system equipment, and integration of a hot water loop into an external application may pose unique challenges.  

The biggest challenge, however, is to establish a partnership with a consumer that has a consistent need for the waste heat since the DC supplies a large amount, at a consistent temperature, all year long. This partnership needs to be financially viable for both the DC and the consumer, taking into account the additional infrastructure costs. 

While significant research exists in energy efficiency and heat recovery in DCs, there remains a distinct gap in the thorough economic examination of innovative combined cooling and waste heat recovery approaches like mechanical vapor recompression within a cooling and enhanced heat recovery (CEHR) system.  

Our study aims to fill this gap by presenting a comprehensive thermoeconomic analysis (TEA) of this novel system specifically designed for DCs. A critical step toward adopting the CEHR system is to estimate the conditions under which it is economically favorable. This study builds upon work that already exists by refining the analysis using more accurate equipment and installation costs and incorporating additional TEA elements such as electricity cost, natural gas cost, and carbon credits with their associated savings. 

Moving forward, we are looking into using waste heat recovery to address DC onsite needs such as in water recovery. Our focus is on making DCs as sustainable and environmentally benign as possible, and waste heat recovery is a critical element of this plan.