An Online Power Metering Model for Cloud Environment

Li, Yanfei; Wang, Ying; Yin, Bo; Guan, Lu

doi:10.1109/nca.2012.10

Cited by 46 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The computation power is related to the character of the computational task (i.e., computation strong, or I/O strong), and the CPU frequency. We assume that there are 4 BCAs (i.e., physical servers) which are used in the edge computing environment, each of which has 4-core Xeon (2 GHz) [ 38 ]. Therefore, the average computation power is 150 W. The evaluation was performed by implementing the analytical solutions using Python 3.8.…”

Section: Simulation and Resultsmentioning

confidence: 99%

Hybrid Blockchain for IoT—Energy Analysis and Reward Plan

Reed

Al-Naday

et al. 2021

Sensors

View full text Add to dashboard Cite

Blockchain technology has brought significant advantages for security and trustworthiness, in particular for Internet of Things (IoT) applications where there are multiple organisations that need to verify data and ensure security of shared smart contracts. Blockchain technology offers security features by means of consensus mechanisms; two key consensus mechanisms are, Proof of Work (PoW) and Practical Byzantine Fault Tolerance (PBFT). While the PoW based mechanism is computationally intensive, due to the puzzle solving, the PBFT consensus mechanism is communication intensive due to the all-to-all messages; thereby, both may result in high energy consumption and, hence, there is a trade-off between the computation and the communication energy costs. In this paper, we propose a hybrid-blockchain (H-chain) framework appropriate for scenarios where multiple organizations exist and where the framework enables private transaction verification and public transaction sharing and audit, according to application needs. In particular, we study the energy consumption of the hybrid consensus mechanisms in H-chain. Moreover, this paper proposes a reward plan to incentivize the blockchain agents so that they make contributions to the H-chain while also considering the energy consumption. While the work is generally applicable to IoT applications, the paper illustrates the framework in a scenario which secures an IoT application connected using a software defined network (SDN). The evaluation results first provide a method to balance the public and private parts of the H-chain deployment according to network conditions, computation capability, verification complexity, among other parameters. The simulation results demonstrate that the reward plan can incentivize the blockchain agents to contribute to the H-chain considering the energy consumption of the hybrid consensus mechanism, this enables the proposed H-chain to achieve optimal social welfare.

show abstract

Section: Simulation and Resultsmentioning

confidence: 99%

Hybrid Blockchain for IoT—Energy Analysis and Reward Plan

Reed

Al-Naday

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In the model defined by Li, at al. in [31], the power consumption is calculated based on the utilization of CPU, operational memory and hard disk.…”

Section: Vm Power Consumptionmentioning

confidence: 99%

Security Supportive Energy Aware Scheduling And Scaling For Cloud Environments

Jakóbik¹,

Grzonka²,

Kołodziej³

2017

ECMS 2017 Proceedings Edited by Zita Zoltay Paprika, Péter Horák, Kata Váradi, Péter Tamás Zwierczyk, Ágnes Vidovics-Dancs, Ján

View full text Add to dashboard Cite

Energy consumption is one of the most important problems in the era of Computational Clouds (CC). CC infrastructures must be elastic and scalable for being accessible by huge population of users in different geographical locations. It means also that CC energy utilization systems must be modern and dynamic in order to reduce the cost of using the cloud services and resources.In this paper, we develop the novel energy saving strategies for resource allocation and task scheduling in computational clouds. We present the new energyaware scheduling policies and methods of scaling the virtual resources. The idea of the proposed models is based on Dynamic Voltage and Frequency Scaling (DVFS) techniques of modulation of the power of microprocessors. Additionally, the proposed model enables the monitoring of the energy consumption, which is necessary for providing the scheduling under the security criterion. The efficiency of the proposed models has been justified in the simple empirical analysis. The obtained results show the need to maintain a balance between energy consumption and task schedule execution.

show abstract

“…Generally, the components of dynamic power consumption in server are processor , memory and hard disk drive and have a dynamic power is about 58%, 28% and 14% [13]. Thus the power presented as follows:…”

Section: IImentioning

confidence: 99%

“…Equation (12) ensures that the users for can be processed by either a single or multiple BBUs . The (13) indicate the total processing capacity of BBU pool is higher than the total computing requirements for all . Constraint (14) ensures that each user is assigned to one BBU .…”

Section: Subject Tomentioning

confidence: 99%