Energy and QoS aware resource allocation for heterogeneous sustainable cloud datacenters

Peng, Yuyang; Kang, Dong-Ki; Al-Hazemi, Fawaz; Youn, Chan‐Hyun

doi:10.1016/j.osn.2016.02.001

Cited by 35 publications

(19 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We make the following two assumptions 12,14 to ensure that there exists at least one feasible solution of problem P2. 41 1) Boundedness assumptions: for time slot t ∈ {0, 1, 2· · ·, L − 1}, the workload arrival rate A i (t), ∀i, the renewable supplies E s j (t), E w j (t), ∀j, as well as electricity price P b j (t), P w j (t), P s j (t), ∀j are finite. 2) Feasibility assumptions: for the rth frame, where r ∈ {0, 1, 2· · ·, R − 1}, there exists at least one sequence of control decision (eg,…”

Section: Off-line Problem Solutionmentioning

confidence: 99%

Cost‐minimizing online algorithm for internet green data centers on multi‐source energy

Shen

Liang

2018

Concurrency and Computation

View full text Add to dashboard Cite

Huge energy consumption of large-scale cloud data centers damages environments with excessive carbon emission. More and more data center operators are seeking to reduce carbon footprint via various types of renewable energy. However, the intermittent availability of renewable energy sources makes it quite challenging to cooperate with dynamically arriving workload.Meanwhile, the different natures (eg, price and carbon emission) of multiple energy sources also bring more challenges to achieve an optimal trade-off among carbon emission, power cost, and service level agreement (SLA). In this paper, we study the problem of reducing the long-term energy cost for geo-distributed cloud centers, where multiple sources of renewable energy are considered and SLA requirement and carbon budget are satisfied. To tackle the randomness of workload arrival, varying electricity price, and intermittent supply of renewable energy, we first formulate the cost minimization problem as a constraint stochastic optimization problem. Second, based on Lyapunov optimization technique, we propose an online control algorithm to solve it and provide the rigorous theory analysis to demonstrate its performance. By converting the long-term optimization problem to a mixed integer linear programming problem in each time slot, we analyze its inherent structure and propose an efficient algorithm to solve it based on Brenner's method.Our proposed algorithm makes online decisions rely only on the current system state and achieve [O( 1 ∕V), O(V)] cost emission trade-off. Finally, the effectiveness of our algorithm is evaluated by extensive simulations based on real-world data traces. KEYWORDS geo-distributed cloud center, green-aware, Lyapunov optimization, renewable energy INTRODUCTIONDriven by the exploding demand of enterprises and personal computation, the scale of cloud data centers has become increasingly large. As stated in the latest report, 1 some leading IT enterprises (eg, Facebook, Amazon, and Google) own their inter-continental data centers in different regions that contain thousands of servers. Thus, accompanied with the corresponding electricity cost is up to millions dollars per year. Meanwhile, large electricity consumption from "brown energy" (produce from oil or coal) brings a large amount of greenhouse gases (GHG) emissions which cause great damages to the fragile environment. Recent studies have shown that Information and Communications Technology (ICT) sector is responsible for 2% of global carbon emission, which places it on par with the aviation industry, and this is set to be doubled by 2020. 2,3 Therefore, it is significant for the large-scale data centers to reduce the net carbon footprint and power cost.Recently, reducing power consumption to make data centers green with renewable energy has received a lot of attention both in industry. 4 and academia. 5,6 Compared to brown energy, renewable energy (such as wind energy and solar energy) is more environmentally friendly with low carbon footprint. Google, Microsoft, and Faceboo...

show abstract

Section: Off-line Problem Solutionmentioning

confidence: 99%

Cost‐minimizing online algorithm for internet green data centers on multi‐source energy

Shen

Liang

2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…However, the model focuses only on homogeneous HPC system but not on heterogeneous cloud environment. Y. Peng et al [8] have discussed about Energy and QoS to minimize performance degradation and bandwidth cost. Based on these two constraints, authors have proposed a new algorithm called Evolutionary Energy Efficient Virtual Machine Allocation (EEE-VMA).…”

Section: Related Workmentioning

confidence: 99%

“…Yuyang Peng et al [16] have introduced an EEE-VMA for geographical data center locations. It works based on a Genetic Algorithm (GA) metaheuristic optimization technique.…”

Section: Related Workmentioning

confidence: 99%

Energy and Service Level Agreement Aware Resource Allocation Heuristics for Cloud Data Centers

2018

TIIS

View full text Add to dashboard Cite

Cloud computing offers a wide range of on-demand resources over the internet. Utility-based resource allocation in cloud data centers significantly increases the number of cloud users. Heavy usage of cloud data center encounters many problems such as sacrificing system performance, increasing operational cost and high-energy consumption. Therefore, the result of the system damages the environment extremely due to heavy carbon (CO 2) emission. However, dynamic allocation of energy-efficient resources in cloud data centers overcomes these problems. In this paper, we have proposed Energy and Service Level Agreement (SLA) Aware Resource Allocation Heuristic Algorithms. These algorithms are essential for reducing power consumption and SLA violation without diminishing the performance and Quality-of-Service (QoS) in cloud data centers. Our proposed model is organized as follows: a) SLA violation detection model is used to prevent Virtual Machines (VMs) from overloaded and underloaded host usage; b) for reducing power consumption of VMs, we have introduced Enhanced minPower and maxUtilization (EMPMU) VM migration policy; and c) efficient utilization of cloud resources and VM placement are achieved using SLA-aware Modified Best Fit Decreasing (MBFD) algorithm. We have validated our test results using CloudSim toolkit 3.0.3. Finally, experimental results have shown better resource utilization, reduced energy consumption and SLA violation in heterogeneous dynamic cloud environment.

show abstract

“…Green cloud data centers and QoS assurance are considered to be main issues in cloud computing. Peng et al [106] recommend an evolutionary energy efficient virtual machine allocation (EEE-VMA) method for minimizing the energy consumption of the data centers. To fulfill the VM allocation request, GA algorithm is used for saving energy, cost and utility in the method.…”

Section: Power Aware Resource Allocationmentioning

confidence: 99%

Recent advancements in resource allocation techniques for cloud computing environment: a systematic review

et al. 2016

View full text Add to dashboard Cite

There are two actors in cloud computing environment cloud providers and cloud users. On one hand cloud providers hold enormous computing resources in the cloud large data centers that rent the resources out to the cloud users on a pay-per-use basis to maximize the profit by achieving high resource utilization. On the other hand cloud users who have applications with loads variation and lease the resources from the providers they run their applications within minimum expenses. One of the most critical issues of cloud computing is resource management in infrastructure as a service (IaaS). Resource management related problems include resource allocation, resource adaptation, resource brokering, resource discovery, resource mapping, resource modeling, resource provisioning and resource scheduling. In this review we investigated resource allocation schemes and algorithms used by different researchers and categorized these approaches according to the problems addressed schemes and the parameters used in evaluating different approaches. Based on different studies considered, it is observed that different schemes did not consider some important parameters and enhancement is required to improve the performance of the existing schemes. This review contributes to the existing body of research and will help the researchers to gain more insight into resource allocation techniques for IaaS in cloud computing in the future.

show abstract

Energy and QoS aware resource allocation for heterogeneous sustainable cloud datacenters

Cited by 35 publications

References 20 publications

Cost‐minimizing online algorithm for internet green data centers on multi‐source energy

Cost‐minimizing online algorithm for internet green data centers on multi‐source energy

Energy and Service Level Agreement Aware Resource Allocation Heuristics for Cloud Data Centers

Recent advancements in resource allocation techniques for cloud computing environment: a systematic review

Contact Info

Product

Resources

About