Big data is now mostly processed in the cloud and will keep growing, fed by databases and the Internet of Things (IoT: sensors, mobile devices, edge computing). On the other hand, AI is pushing computers and data analysis to limits we had not witnessed before. Analytics in the cloud is now a major fraction of energy consumption, among other less CPU-intensive tasks like web services. With this green computing motivation in mind, we present a survey of past research and a vision of big data analytics in the cloud. Energy consumption is difficult to minimize because it has conflicting correlated variables behind: high performance, money cost and pollution, We identify which software subsystems and hardware components have a higher impact on energy consumption, understanding how they can be tweaked or tuned to optimize energy consumption.
No takes yet. Share an insight, caveat, or question.
Ordońẽz et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: