Fig 1 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
![A breakdown of energy consumption by different components of a data center [9].](publication/321692822/figure/fig1/AS:569461712986112@1512781660322/A-breakdown-of-energy-consumption-by-different-components-of-a-data-center-9.png)
Source publication
Most information technology (IT) equipment found in a data center is air-cooled as electrical component produces heat, which must be removed to prevent the temperature of the IT equipment from rising to an unacceptable level. The energy consumption for the data center cooling system is positively related to the air temperature outside the data cent...
Similar publications
In job scheduling, the concept of malleability has been explored since many years ago. Research shows that malleability improves system performance, but its utilization in HPC never became widespread. The causes are the difficulty in developing malleable applications, and the lack of support and integration of the different layers of the HPC softwa...
Task scheduling is a well-studied problem in the context of optimizing the Quality of Service (QoS) of cloud computing environments. In order to sustain the rapid growth of computational demands, one of the most important QoS metrics for cloud schedulers is the execution cost. In this regard, several data-driven deep neural networks (DNNs) based sc...
A holistic solution for Traffic Burst Oriented Adaptive Resource Provisioning in Cloud (TRIERS for short) has been proposed to tackle the problem of maintaining performance scalability and service agility in the presence of sudden bursts of workload traffic. The TRIERS framework consists of three core components: workload classification by characte...
Energy consumption is one of the most critical concerns in designing computing devices, ranging from portable embedded systems to computer cluster systems. Furthermore, in the past decade, cluster systems have increasingly risen as popular platforms to run computing-intensive real-time applications in which the performance is of great importance. H...
Aiming at the coupling of energy consumption and completion time in flexible job-shop scheduling, this paper took makespan and energy consumption as the optimization objectives, established a scheduling model, and proposed a scheduling strategy based on improved genetic algorithm. Firstly, a hybrid initialization method based on global minimum comp...
Citations
... Wu et al. [15] address the challenge of reducing data centre cooling energy by siting data centers in locations with a cold climate. They recognize this as a direction being considered by cloud computing operators. ...
... A similar discussion on the role of intelligence is in [18]. The discussion in [14][15][16][17][18] focuses on large cloud platforms. The operational advantages of large scale cloud service providers are inaccessible to cloud service providers with small sized data centers [19]. ...
... This is necessary as intent based networks bring the benefits of cloud computing and artificial intelligence to network infrastructure management [27]. The findings of the discussion are summarized as follows: 1) Sustainable Cloud Computing: There is an increased use of sustainable technologies in cloud computing [14][15][16][17][18] accompanied by consideration of geographically aware free cooling strategies. ...
Intent based networks enable auto-configuration and require low latency access to cloud platforms. The use of cloud platforms incurs high operational costs. Low latency access can be realized by siting data centres close to subscribers. This paper proposes aquaria data centers with low operating costs and latency. In LTE, cloud platforms are normally accessed via the packet network gateway reachable via the serving gateway and mobility management entity. Aquaria data centers are sited close to LTE subscribers and accessed via the mobility management entity. This reduces the size of control packets in the LTE network. Simulations show that the proposed architecture reduces the size of control packets by up to 49.7% and 99.3% when header packets are uncompressed and compressed respectively. The delay associated with receiving configuration information is reduced by 50% on average. The channelcapacity is enhanced by up to 22.8% on average. Keywords: Data centers, LTE-Advanced, Peak Age of Information, Channel Capacity, Header (Control) Packet
... The first stage is energy saving, where the DR of IDCs has no reference to the signals in electricity markets. After realizing an added high energy cost and the environmental impact in the form of greenhouse gas emissions [21], numerous energy-saving technologies and strategies have been carried out to find an efficient and sustainable way to operate IDCs, e.g., energy-saving technologies including DVFS [7], DCSC [8], and VM [9], and energy-saving strategies including joint control of the cooling systems and servers for holistic energy minimization [22][23][24][25][26][27][28]. As the second stage, ISCs passively monitor the DR signals in electricity markets to reduce energy costs, whereas the impact of the spatial load regulation of IDCs on power systems is ignored by system operators (SOs). ...
Internet data centers (IDCs), which have the potential of spatial and temporal load regulation, are excellent demand response (DR) resources. IDCs participating in DR has recently become a popular topic as it is economical and efficiently helps improve power systems. However, there remain abundant opportunities to improve this interdisciplinary domain when considering the lack of applicability of IDC load models for power systems, exploitation regarding the potential of IDC load regulation, and DR mechanisms for spatial-coupling loads. Therefore, a review summarizing the state-of-art studies around the theme of IDCs participating in DR is warranted. A comprehensive survey covering the major parts of the DR in IDCs, along with the order load modeling, load regulation operations, economic considerations, and IDCs participating in DR programs, is presented in this paper. Furthermore, the challenges and future research issues are also discussed for further participation of DR in IDCs.
... Thus, it is necessary to discuss the existing and emerging technologies for datacenter cooling systems to determine the effective approach to maintaining CDCs working in a safe and reliable manner. The evolution of cooling management techniques (see Figure 27) and their comparison along with open research challenges [150][151][152][153][154][155] are provided in Table 20 of Appendix C.7. ...
... Based on the literature [150][151][152][153][154][155], cooling management consists of the following components: (i) cooling management techniques and (ii) the cooling plant as shown in Figure 13. Each of these taxonomy elements are discussed below along with relevant examples. ...
... The SACS technique helps to reduce energy consumption using this cooling process. Wu et al.[151] propose the Weathersaving energy consumption and space. A CFD simulator [86] is used to test the performance of the NCLI technique; the experimental results show that this technique is effective in improving cooling efficiency, which further improves the value of PUE. ...
The cloud computing paradigm offers on-demand services over the Internet and supports a wide variety of applications. With the recent growth of Internet of Things (IoT) based applications the usage of cloud services is increasing exponentially. The next generation of cloud computing must be energy-efficient and sustainable to fulfil the end-user requirements which are changing dynamically. Presently, cloud providers are facing challenges to ensure the energy efficiency and sustainability of their services. The usage of large number of cloud datacenters increases cost as well as carbon footprints, which further effects the sustainability of cloud services. In this paper, we propose a comprehensive taxonomy of sustainable cloud computing. The taxonomy is used to investigate the existing techniques for sustainability that need careful attention and investigation as proposed by several academic and industry groups. Further, the current research on sustainable cloud computing is organized into several categories: application design, sustainability metrics, capacity planning, energy management, virtualization, thermal-aware scheduling, cooling management, renewable energy and waste heat utilization. The existing techniques have been compared and categorized based on the common characteristics and properties. A conceptual model for sustainable cloud computing has been proposed along with discussion on future research directions.
Optimal temperature control of computer room air conditioners (CRACs) is an effective way to lower energy costs in high density data centers. To break the barrier of dimensionality when jointly optimizing the temperature of CRACs in multiple data centers (multi-datacenters) configured in-row cooler systems, a tensor-based sequential quadratic programming (SQP) method is presented in this study. This method takes the temperature tensors as input, and transforms the original high-dimensional optimization problem into several lower-dimensional sub-problems. An effective approach to solve the non-convex optimization of these sub-problems is also proposed. The transformation method not only reduces the dimensionality of optimization, but also increases its convergence speed. On the foundation of the tensorbased SQP, an optimized control strategy is constructed to adjust the outlet temperature of CRACs, with the objective of enhancing the cooling efficiency. The convergence behavior, maximum input temperature of racks, and cooling power are analyzed to illustrate the effectiveness of the proposed tensor-based optimization and control strategy.
