PTEC: A System for Predictive Thermal and Energy Control in Data Centers

Abstract

Abstract-Current data centers often adopt conservative and static settings for cooling and air circulation systems, leading to excessive energy consumption. This paper presents the design and evaluation of PTEC -a system for predictive thermal and energy control in data centers. PTEC leverages the server built-in sensors and monitoring utilities, as well as a wireless sensor network, to monitor both the cyber and physical status of a data center. By predicting the temperature evolution of a data center in real time, PTEC finds the temperature setpoints, the cold air supply rates, and the speeds of server internal fans to minimize the expected total energy consumption of cooling and circulation systems. Moreover, PTEC enforces the upper bounds on server inlet temperatures and their temporal variations to prevent server overheating and reduce server hardware failure rate. We evaluated PTEC on a hardware testbed consisting of 15 servers and a total of 23 temperature and power sensors, as well as through Computational Fluid Dynamics (CFD) simulations based on real data traces collected from a data center with 229 servers. The experimental results show that PTEC can reduce the cooling and circulation energy consumption by more than 30%, compared with baseline thermal control strategies.

Gerenciamento Térmico e Elétrico de um Centro de Dados utilizando Sensoriamento IoT

“…Em [Chen et al 2014], os autores apresentam o design e avaliação do sistema PTEC, um sistema de previsão de controle térmico e energético em centro de dados. O foco do estudoé verificar se o PTEC consegue realizar de maneira eficiente o monitoramento do centro de dados com um baixo custo no uso do sistema de resfriamento e de energia.…”

“…A inoperância pode ocorrer devido a falha de equipamentos, problemas de configuração, aumento na demanda de usuários ou até mesmo devido a falta de fornecimento de energia elétrica [Lu et al 2016]. Nesseúltimo caso, passa a existir também o risco de prejuízos financeiros devidos a quebra ou desgaste de equipamentos [Chen et al 2014].…”

IoT Power Monitoring System for Smart Environments

“…In [6], the authors presented the design and evaluation of the system PTEC (predictive thermal and energy control system), a thermal and energy control prediction system in a data center. The focus of the study was to verify if the PTEC could efficiently perform monitoring of the data center with a low cost in the use of power.…”

Cooling-aware node-level task allocation for next-generation green HPC systems

“…Several works in literature have proposed techniques to control the rotating speed of the fans to achieve a higher energy efficiency. This can be done either by reducing the fan speed and balancing the power gain in the fans with the power loss due to the increased leakage power caused by the higher silicon temperature [4], [10], [18] or by balancing the CPU temperature by mean of task migration and dynamic thermal management [1], [6].…”

“…Authors in [4], [10] show that the fan power can be reduced by iteratively modulating the fan speed based on die temperature and a node power measurements. Indeed by reducing the fan power iteratively with small steps, until the silicon temperature raises and the overall power decreases, it is possible to account for leakage power while finding the energy minimum.…”