The digital carbon footprint makes a significant contribution to the CO2 issue society has today.
The pioneer datacube engine, rasdaman, now has been enhanced with the GreenCube innovation which minimizes energy consumption in Big Data Analytics while retaining full flexibility.
Computers today generate a non-negligible contribution to the overall CO2 release on the planet, known as the "digital carbon footprint". Business transactions, gaming, analytics, AI, etc. all have made computer energy consumption skyrocket. IEEE, like other institutions, has published several articles on this challenge.
One angle to attack the problem is the algorithmic efficiency. Python, for example, is what computer scientists call an "interpreted language" meaning the code has to be translated into executable machine language every time again. "Compiled languages" do that once and for all, saving runtime and energy. The rasdaman engine, for example, is implemented in the C++ language which also is known to generate particularly efficient code.
With its proprietary GreenCube innovation rasdaman now goes one step further: incoming requests get translated directly into machine code - regardless of the request API used, like WMS, WMTS, WCS, WCPS, or OAPI-Coverages. Federated data fusion benefits from this GreenCube® method and additionally determines a distributed processing plan which provably incurs only the minimum data transport between the nodes.
Altogether, GreenCube optimizes the carbon footprint while retaining full flexibility for users; they additionally benefit from the outstanding performance allowing complex analytics in realtime, with location-transparent combination of secured in-house and public EO data. GreenCube is being exploited already in a series of ambitious projects. In ORBiDANSe, partly funded by German Ministry for Digital and Tranport (BMDV), rasdaman has shown in-orbit datacube processing on an ESA nanosat.
In AI-Cube, datacube fusion and AI-based analytics has been integrated and demonstrated on large-scale Copernicus datacubes, in collaboration with TU Berlin. Machine Learning prediction now can be invoked seamlessly within the OGC-standardized datacube analytics language, WCPS. The project is partly funded by the German Ministry of Economics and Climate Affairs under grant no. 50EE2012.
FAIRiCUBE has set out to enable players from beyond classic Earth Observation (EO) domains to provide, access, process, and share gridded data and algorithms in a FAIR and TRUSTable manner. The project is funded through Horizon Europe grant 101059238.
Cube4EnvSec exploits Big Earth Datacube Analytics for transnational security and environment protection. A series of use cases proves the capabilities of realtime datacube management, analytics, and federation of fixed and moving data sources and sinks. Cube4EnvSec is partly funded by the NATO Science for Peace and Security (SPS) program. More information here.
Subscribe to our newsletter
Stay updated on the latest technology, innovation product arrivals and exciting offers to your inbox.Newsletter