Energy savings and speed tradeoffs in data center servers
Energy-performance tradeoffs in server farms with batch services and setup times
Performance
Summary
Data centers use lots of energy, especially when servers are idle. The authors study a system design that turns off servers only after grouping incoming jobs into batches, reducing wasted power but keeping performance steady. They model the system with queues that include setup times for turning servers on again. Their results show it’s better to let servers idle a bit longer and handle jobs in batches before shutting down. This approach saves energy while still maintaining system speed.
What this means in practice
- •For data center operators: Optimize energy use by implementing batch processing with delayed server shutdown to save power without hurting service speed.
- •For cloud infrastructure engineers: Design server management policies that reduce energy consumption by batching jobs and controlling setup delays effectively.
Authors
Thu Le-Anh, Tuan Phung-Duc
Abstract
Data centers consume a large amount of energy, much of which is wasted due to idle servers. Turning off idle servers might be an effective power-saving solution; however, there is a trade-off between energy savings and system performance. Hence, we propose a setup queueing model with a batching policy that allows servers to process a set of jobs simultaneously to minimize power consumption while maintaining acceptable performance. We consider an M/M/c/SET--BATCH queue, a multi-server batch service queue with a fixed batch size and setup times, and some variants, including systems in which idle servers delay before turning off or systems in which the batch size is dynamic. We analyze the steady-state probabilities and system performance of the M/M/c/SET--BATCH system and its variants. Our analysis of the M/M/c/SET--BATCH system with lower computational complexity is made possible by utilizing the special structure of the model. In addition, we use simulations to compare the M/M/c/SET--BATCH model with some other variants with different setup time distributions. The results suggest that the model performs better when the setup time has a larger coefficient of variation. Our results indicate that the batching policy enhances the system performance, especially when we allow servers to be idle before turning them off.