Holistic thermal-aware workload management and infrastructure control for heterogeneous data centers using machine learning

MirhoseiniNejad, SeyedMorteza; Badawy, Ghada; Down, Douglas G.

doi:10.1016/j.future.2021.01.007

Cited by 24 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MirhoseiniNejad et al [18] has developed a novel machine learning (ML) approach for quantifying the thermal heterogeneities in data centers. The cost of supplying cold air at the front of servers may be estimated using the thermal models, along with the cooling capacity of servers.…”

Section: Related Studies Using Machine Learning Techniquesmentioning

confidence: 99%

Optimization of power consumption in data centers using machine learning based approaches: a review

Kumar

Khatri

Diván

2022

IJECE

View full text Add to dashboard Cite

<span>Data center hosting is in higher demand to fulfill the computing and storage requirements of information technology (IT) and cloud services platforms which need more electricity to power on the IT devices and for data center cooling requirements. Because of the increased demand for data center facilities, optimizing power usage and ensuring that data center energy quality is not compromised has become a difficult task. As a result, various machine learning-based optimization approaches for enhancing overall power effectiveness have been outlined. This paper aims to identify and analyze the key ongoing research made between 2015 and 2021 to evaluate the types of approaches being used by researchers in data center energy consumption optimization using Machine Learning algorithms. It is discussed how machine learning can be used to optimize data center power. A potential future scope is proposed based on the findings of this review by combining a mixture of bioinspired optimization and neural network.</span>

show abstract

Section: Related Studies Using Machine Learning Techniquesmentioning

confidence: 99%

Optimization of power consumption in data centers using machine learning based approaches: a review

Kumar

Khatri

Diván

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…The 'holistic' column represents whether the approach provides an end-to-end solution for scheduling, considering all parameters for sustainable cloud computing [6]. TOPSIS [20] Threshold Based MALE [21] Memory Mapping CRUZE [6] Cuckoo Optimization MITEC [8] Genetic Algorithm PADQN [12] Deep Q Learning ANN [10] Neural Network SDAE-MMQ [13] Autoencoders HDIC [9] NARX Network HUNTER Surrogate Modelling…”

Section: Related Workmentioning

confidence: 99%

“…SDAE-MMQ uses a stacked denoising autoencoder as a value network and MiniMax-Q instead of vanilla Q-learning [13]. Another work, HDIC [9], uses a nonlinear auto-regressive network with exogenous inputs (NARX) as a value network. Advanced neural models typically take a long time to train and infer Q values for large-scale state inputs.…”

Section: Related Workmentioning

confidence: 99%

“…Most prior work presents meta-heuristic algorithms [6] and deep learning techniques [7]. Most state-ofthe-art models use meta-heuristic approaches like genetic algorithms or integer linear programming [6,8,9,10,11]. Other recent methods use reinforcement learning (RL); specifically, the traditional tabular models like Q-Learning [12,13].…”

Section: Introductionmentioning

confidence: 99%

“…One such network, called Gated Graph Convolution Network (GGCN) enables aggregation of the graph node information using convolution operations and message passing [16], making it suitable to model distributed computing network as a graph. This enables a more versatile optimization approach that also takes into account the task hierarchy and edge-cloud hierarchy, not considered in most prior work [14,9]. We use a GGCN model as a surrogate of the QoS objective scores allowing us to swiftly run placement optimization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing

Tuli,

Gill,

et al. 2021

Preprint

View full text Add to dashboard Cite

The worldwide adoption of cloud data centers (CDCs) has given rise to the ubiquitous demand for hosting application services on the cloud. Further, contemporary data-intensive industries have seen a sharp upsurge in the resource requirements of modern applications. This has led to the provisioning of an increased number of cloud servers, giving rise to higher energy consumption and, consequently, sustainability concerns. Traditional heuristics and reinforcement learning based algorithms for energy-efficient cloud resource management address the scalability and adaptability related challenges to a limited extent. Existing work often fails to capture dependencies across thermal characteristics of hosts, resource consumption of tasks and the corresponding scheduling decisions. This leads to poor scalability and an increase in the compute resource requirements, particularly in environments with non-stationary resource demands. To address these limitations, we propose an artificial intelligence (AI) based holistic resource management technique for sustainable cloud computing called HUNTER. The proposed model formulates the goal of optimizing energy efficiency in data centers as a multi-objective scheduling problem, considering three important models: energy, thermal and cooling. HUNTER utilizes a Gated Graph Convolution Network as a surrogate model for approximating the Quality of Service (QoS) for a system state and generating optimal scheduling decisions. Experiments on simulated and physical cloud environments using the CloudSim toolkit and the COSCO framework show that HUNTER outperforms state-of-the-art baselines in terms of energy consumption, SLA violation, scheduling time, cost and temperature by up to 12, 35, 43, 54 and 3 percent respectively.

show abstract

A Shapley value-based thermal-efficient workload distribution in heterogeneous data centers

Akbar

2022

J Supercomput

View full text Add to dashboard Cite

Holistic thermal-aware workload management and infrastructure control for heterogeneous data centers using machine learning

Cited by 24 publications

References 17 publications

Optimization of power consumption in data centers using machine learning based approaches: a review

Optimization of power consumption in data centers using machine learning based approaches: a review

HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing

A Shapley value-based thermal-efficient workload distribution in heterogeneous data centers

Contact Info

Product

Resources

About