دانلود رایگان مقاله پیش بینی درجه حرارت مرکز داده حین رانش با استفاده از تکنیک تکامل دستوری

Abstract

Data Centers are huge power consumers, both because of the energy required for computation and the cooling needed to keep servers below thermal redlining. The most common technique to minimize cooling costs is increasing data room temperature. However, to avoid reliability issues, and to enhance energy efficiency, there is a need to predict the temperature attained by servers under variable cooling setups. Due to the complex thermal dynamics of data rooms, accurate runtime data center temperature prediction has remained as an important challenge. By using Grammatical Evolution techniques, this paper presents a methodology for the generation of temperature models for data centers and the runtime prediction of CPU and inlet temperature under variable cooling setups. As opposed to time costly Computational Fluid Dynamics techniques, our models do not need specific knowledge about the problem, can be used in arbitrary data centers, re-trained if conditions change and have negligible overhead during runtime prediction. Our models have been trained and tested by using traces from real Data Center scenarios. Our results show how we can fully predict the temperature of the servers in a data rooms, with prediction errors below 2 °C and 0.5 °C in CPU and server inlet temperature respectively.

8. Conclusions

In this paper we have presented a methodology for the unsupervised generation of models to predict on runtime the thermal behavior of production data centers running arbitrary workloads and equipped with heterogeneous servers. Our approach leverages the usage of Grammatical Evolution to automatically generate models of the data room by using real data center traces. Our solution allows to predict the CPU temperature and inlet temperature of servers, with an average error below 2 ◦C and 0.5 ◦C respectively. These errors are within the margin obtained by other off-line supervised approaches in the state-of-the art. Our solution, generates the models in an unsupervised way, is able to work on runtime, is trained and tested in a real scenario, and does not require the usage of CFD software. To the best of our knowledge our work is the first to propose data center temperature forecastingusing evolutionary techniques, allowing predictive model generation for runtime optimization.