Optimized Thermal-Aware Job Scheduling and Control of Data Centers

Abstract

Abstract-Analyzing data centers with thermal-aware optimization techniques is a viable approach to reduce energy consumption of data centers. By taking into account thermal consequences of job placements among the servers of a data center, it is possible to reduce the amount of cooling necessary to keep the servers below a given safe temperature threshold. We set up an optimization problem to analyze and characterize the optimal setpoints for the workload distribution and the supply temperature of the cooling equipment. Furthermore under mild assumptions we design and analyze controllers that drive the data center to the optimal state without knowledge of the current total workload to be handled by the data center. The response of our controller is validated by simulations and convergence to the optimal setpoints is achieved under varying workload conditions.

Research advances on AI-powered thermal management for data centers

“…By contrast, in Refs. [11][12][13][14][15], the coefficient of performance (CoP) metric was used to measure the efficiency of the system besides the CRAC units. In addition to the CoP for achieving the cooling cost savings in CRAC, Zhao et al [11] used Eq.…”

“…The zonal model is an intermediate method between full computational fluid dynamics (CFD) simulations and multi-node lumped models. Van Damme et al [14] studied the thermodynamic coupling between the workload and the cooling equipment's energy efficiency and adopted the thermodynamic model. The authors demonstrated the direct coupling between the racks' output temperature and both system efficiency and load [14] .…”

“…Van Damme et al [14] studied the thermodynamic coupling between the workload and the cooling equipment's energy efficiency and adopted the thermodynamic model. The authors demonstrated the direct coupling between the racks' output temperature and both system efficiency and load [14] . Fang et al [7] considered using a fasttemperature evaluation model for real-time thermal management.…”

A Taxonomy and Future Directions for Sustainable Cloud Computing

“…Experimental results show that proposed technique performs effectively in terms of temperature and power as compared to greedy and genetic algorithm. Damme et al [50] proposed an Optimized Thermal-aware Job Scheduling (OTJS) technique to analyze the cloud datacenters and reduce consumption of energy. OTJS technique schedules the jobs effectively on cloud resources, so that it maintains the temperature of the system below its threshold value, which reduces the required amount of cooling.…”

Data Mining for Big Dataset-Related Thermal Analysis of High Performance Computing (HPC) Data Center

“…Thermal-aware schedulers adopt different thermal-aware approaches (e.g. system-level for work placements [16]; execute 'hot' jobs on 'cold' compute nodes; predictive model for job schedule selection [17]; ranked node queue based on thermal characteristics of rack layouts and optimisation (e.g. optimal setpoints for workload distribution and supply temperature of the cooling system).…”