Networked computing systems for bio-diversity and environmental preservation

Abstract

AbstractComputing platforms have a high water footprint that poses threat to biodiversity preservation. The high water footprint reduces water availability for habitat preservation. Hence, approaches that reduce the water footprint are needful. The presented research proposes an approach that reduces the need for water in future computing platforms. It proposes a hybrid computing platform that comprises terrestrial and non-terrestrial computing platforms. The performance benefit of using hybrid computing platforms is evaluated using the novel water potential metric. The water potential (WP) quantifies the need for water (for cooling) by computing platforms. A low WP shows that computing platforms have reduced the need for water and indicates better performance than a high WP from the perspective of reducing water footprint. Evaluation is done via performance formulation and stochastic simulation of the WP metric. Analysis shows that using the hybrid computing platform instead of the existing approach that utilizes only water-cooled terrestrial data centres reduces the WP by (4.9–93) % on average.