Extended Kepler Grid-based System for Diabetes Study Workspace

( Fawaz Al Hazemi ),( Chan-hyun Youn ) 한국정보처리학회 2011 한국정보처리학회 학술대회논문집 Vol.18 No.1

Chronic disease is linked to patient’s’ lifestyle. Therefore, doctor has to monitor his/her patient over time. This may involve reviewing many reports, finding any changes, and modifying several treatments. One solution to optimize the burden is using a visualizing tool over time such as a timeline-based visualization tool where all reports and medicine are integrated in a problem centric and time-based style to enable the doctor to predict and adjust the treatment plan. This solution was proposed by Bui et. al. [2] to observe the medical history of a patient. However, there was limitation of studying the diabetes patient’s history to find out what was the cause of the current development in patient’s condition; moreover what would be the prediction of current implication in one of the diabetes’ related factors (such as fat, cholesterol, or potassium). In this paper, we propose a Grid-based Interactive Diabetes System (GIDS) to support bioinformatics analysis application for diabetes diseases. GIDS used an agglomerative clustering algorithm as clustering correlation algorithm as primary algorithm to focus medical researcher in the findings to predict the implication of the undertaken diabetes patient. The algorithm was Chronological Clustering proposed by P. Legendre [11] [12].

LPC $$_\mathrm{FreqSchd}$$ FreqSchd : A local power controller using the frequency scheduling approach for virtualized servers

AL-Hazemi, Fawaz,Kang, Dong-Ki,Kim, Seong-Hwan,Peng, Yuyang,Newaz, S. H. Shah,Youn, Chan-Hyun Springer-Verlag 2016 CLUSTER COMPUTING Vol.19 No.2

<P>For more than a decade, the power consumption of data centers has been addressed from different perspectives. Many solutions have been proposed to reduce (or optimize) this power consumption, such as controlling the operation of the servers in data centers. However, these approaches have not yet reached their optimum goals. Existing power control solutions using CPU frequency with an ad hoc or frequency modulator approach are not sufficient. In this paper, we review the power consumption effects of different configuration settings applied to the server's CPU. We propose our local power controller using frequency scheduling (LPC), which is a server-level power controller that depends on an extended gain scheduling technique. Our proposed LPC considers the impact of different CPU configuration settings that are typically not considered simultaneously, such as the allocated CPU credits and CPU frequency level. Through a real experimental test bed, our LPC exhibits effective power management of different types of machines and outperforms other existing approaches, such as ad hoc and frequency modulation, when the power budget is low. Moreover, our proposed LPC has a very lightweight control actuation overhead compared with other approaches: approximately of the ad hoc approach's overhead and of the frequency modulator approach's overhead. This lightweight control actuation overhead reduces the power consumption overhead caused by the controller, and it could be used by other controllers, such as performance or thermal controllers running on the same server.</P>

Dynamic allocation of power delivery paths in consolidated data centers based on adaptive UPS switching

AL-Hazemi, Fawaz,Peng, Yuyang,Youn, Chan-Hyun,Lorincz, Josip,Li, Chao,Song, Guo,Boutaba, Raouf Elsevier 2018 COMPUTER NETWORKS - Vol.144 No.-

<P><B>Abstract</B></P> <P>Although technique known as server consolidation approach in a data center can reduce the overall power consumption, the Power Usage Effectiveness (PUE) of the data center will still be negatively affected with presence of distributed Uninterruptible Power Supplies (UPSs). The impact on the PUE arises from the fact that all UPS modules are kept running to maintain power availability for only a few active servers during off-peak periods. To address this problem, in this paper technique for reducing power consumption in a data center by consolidating the UPSs used during off peak periods is proposed. The proposed technique achieves power savings by leveraging a micro Automatic Transfer Switch (micro-ATS) at the server end. The novelty of this work lies in developed adaptive algorithm that continuously looks for opportunities to reduce the number of UPSs by offloading under-loaded UPSs to a neighboring UPS whenever that neighboring UPS can handle the extra load. In various simulated scenarios involving corporate data centers, our approach demonstrates the ability to save more power and achieve lower PUE degradation compared with state-of-the-art approaches such as server consolidation. Specifically, the proposed approach achieves a savings of approximately 20% to 40% in a data center’s power consumption, depending on the data center’s off-peak periods, which can be accomplished using only 80% of the UPS modules in the data center.</P>

만성질환 클러스터링을 위한 서비스 지향형 PACS-Grid

( Fawaz Al Hazemi ),송혜원 ( Hyewon Song ),윤찬현 ( Chan-hyun Youn ),김병상,김영헌 ( Younghun Kim ),진광자 한국정보처리학회 2010 한국정보처리학회 학술대회논문집 Vol.17 No.1

본 논문에서는 전산화 및 통합된 환경에서 의료정보처리 요구사항을 만족시키기 위하여 만성질환 클러스터링 기법을 제안하고, 이를 서비스 지향형 PACS-Grid 플랫폼에 적용하여 그 성능을 평가한다. 마지막으로 제안된 시스템 형상이 기존의 PACS-Grid 보다 데이터 처리 성능이 개선되었음을 보여준다.

Enhancing Energy Efficiency via Cooperative MIMO in Wireless Sensor Networks: State of the Art and Future Research Directions

Peng, Yuyang,Al-Hazemi, Fawaz,Boutaba, Raouf,Tong, Fei,Hwang, Il-Sun,Youn, Chan-Hyun IEEE 2017 IEEE communications magazine Vol.55 No.11

<P>CMIMO is an effective approach to increase throughput and energy efficiency through the collaboration of individual antennas working together as a virtual multi-antenna system. Several CMIMO strategies have been propounded as major candidates for achieving green communications in wireless sensor networks. Compared to conventional MIMO, CMIMO provides significant gains in terms of flexibility. Recently, more advanced cooperation strategies have been proposed to improve the performance of CMIMO by using emerging techniques such as spatial modulation and coding. Although some breakthroughs have been made in this area, the problem of how to accurately adopt these emerging techniques to model CMIMO is far from being fully understood. This article surveys several state-of-the-art CMIMO models for different scenarios, including data aggregated, multihop-based, and clustered schemes. Moreover, it discusses the implementation of CMIMO techniques, which are expected to be candidate techniques for green communications in modern applications. In the implementation, the trade-offs between energy efficiency and spectral efficiency, quality of service, fairness, and security are discussed. Several simulation results are given to show how emerging techniques in CMIMO design can lead to energy efficiency enhancement. Finally, some challenges and open issues that present future research directions are discussed.</P>

Design and Optimization for Energy-Efficient Cooperative MIMO Transmission in Ad Hoc Networks

Peng, Yuyang,Al-Hazemi, Fawaz,Kim, Heejae,Youn, Chan-Hyun IEEE 2017 IEEE Transactions on Vehicular Technology VT Vol.66 No.1

<P>The need to reduce energy consumption for lowering operating costs has pushed energy efficiency to become one of the major issues of current research in the field of ad hoc networks. In this paper, a new cooperative strategy of multiple-input–multiple-output (MIMO) based on spatial modulation (SM) for the randomly distributed nodes (CMIMO-SMR) in an ad hoc network is proposed to optimize the whole energy consumption of the network. In this new strategy, the head node and the assistant node are jointly set up using a cooperative technique in each cluster to obtain the diversity. In this strategy, the effect of the amount of nodes on the energy consumption is analyzed. Moreover, the different factors such as number of hops and bit error ratio (BER) for energy savings are investigated in a CMIMO-SMR-based multihop ad hoc network where the optimal number of hops and the BER relationship are derived by taking into account the transmission energy and the circuit energy, as well as the bit-recovery situation. In the simulation, it is demonstrated that CMIMO-SMR is more energy efficient compared with the existing works. Moreover, an adaptive algorithm for choosing the appropriate number of hops to minimize the energy consumption is designed when the end-to-end designated BER is required. The results demonstrate that the minimum energy consumption can be achieved by using the proposed algorithm without compromising the designated BER requirement at the destination.</P>

Joint Selection for Cooperative Spectrum Sensing in Wireless Sensor Networks

Peng, Yuyang,Al-Hazemi, Fawaz,Kim, Heejae,Youn, Chan-Hyun IEEE 2016 IEEE SENSORS JOURNAL Vol.16 No.22

<P>A joint selected strategy is proposed for wireless sensor networks to address the energy consumption problem in this letter. The proposed strategy saves energy by selecting the sensor and modulation constellation size. Results from simulations show that the proposed strategy obtains significant energy reduction compared with the existing strategy under the same environment.</P>

Adaptive VM Management with Two Phase Power Consumption Cost Models in Cloud Datacenter

Kang, D. K.,Al-Hazemi, F.,Kim, S. H.,Chen, M.,Peng, L.,Youn, C. H. Springer Science + Business Media 2016 MOBILE NETWORKS AND APPLICATIONS Vol.21 No.5

<P>As cloud computing models have evolved from clusters to large-scale data centers, reducing the energy consumption, which is a large part of the overall operating expense of data centers, has received much attention lately. From a cluster-level viewpoint, the most popular method for an energy efficient cloud is Dynamic Right Sizing (DRS), which turns off idle servers that do not have any virtual resources running. To maximize the energy efficiency with DRS, one of the primary adaptive resource management strategies is a Virtual Machine (VM) migration which consolidates VM instances into as few servers as possible. In this paper, we propose a Two Phase based Adaptive Resource Management (TP-ARM) scheme that migrates VM instances from under-utilized servers that are supposed to be turned off to sustainable ones based on their monitored resource utilizations in real time. In addition, we designed a Self-Adjusting Workload Prediction (SAWP) method to improve the forecasting accuracy of resource utilization even under irregular demand patterns. From the experimental results using real cloud servers, we show that our proposed schemes provide the superior performance of energy consumption, resource utilization and job completion time over existing resource allocation schemes.</P>

Grant management procedure for energy saving TDM-PONs

Alaelddin, Fuad Yousif Mohammed,Newaz, S.H. Shah,AL-Hazemi, Fawaz,Choi, Jun Kyun Elsevier 2018 Optical fiber technology Vol.40 No.-

<P><B>Abstract</B></P> <P>In order to minimize energy consumption in Time Division Multiplexing-Passive Optical Network (TDM-PON), IEEE and ITU-T have mandated sleep mode mechanism for Optical Network Units (ONUs) in the latest TDM-PON standards (e.g. IEEE P1904.1 SIEPON, ITU-T G.sup45). The sleep mode mechanism is a promising mean for maximizing energy saving in an ONU. An ONU in sleep mode flips between <I>sleep</I> and <I>active state</I> depending on the presence or absent of upstream and downstream frames. To ensure Quality of Service (QoS) of upstream frames, the recent TDM-PON standards introduced an early wake-up mechanism, in which an ONU is forced to leave the <I>sleep state</I> on upstream frame arrival. When the Optical Line Terminal (OLT) of a TDM-PON allows early wake-up of its connected ONUs, it allocates gratuitous grants for the sleeping ONUs along with allocating upstream grants for the ONUs in <I>active state</I>. Note that, the gratuitous grants control message sent periodically by the OLT on Inter-Gratuitous grant Interval (IGI) time. After leaving <I>sleep state</I> due to the arrival of upstream frame, the ONU uses its allocated gratuitous grant to send a control message mentioning the amount of upstream bandwidth (upstream grant) required in order to forward the remaining frames in its buffer. However, the existing early wake-up process of ONU can lead to increase the energy consumption of an ONU. It is because of the ONU wakes-up immediately from the <I>sleep state</I> on arrival of the upstream frame, but even so, it needs to wait for forwarding the frame until its allocated gratuitous grant period, resulting in spending energy unnecessarily. In addition, current energy saving solution for TDM-PONs do not provide a clear solution on how to manage different types of grants (e.g. listening grant, upstream transmission grant) within a Dynamic Bandwidth Allocation (DBA) polling cycle. To address this problem, we propose a state-of-art Grant Management Procedure (GMP) in order to maximize energy saving in a TDM-PON with sleep mode enabled ONUs. GMP contributes in defining the location of the different types of grants during a DBA polling cycle. Furthermore, GMP devises a mechanism so as to allow an ONU to predict its assigned gratuitous grant control message arrival time, thereby allowing an ONU to remain its transceiver unit powered off until the arrival period of the next gratuitous grant control message, increasing the energy saving of the ONU. Results show that, with the increment of IGI, the energy saving performance of an ONU with GMP increases noticeably in compare to a conventional ONU (an ONU that does not use GMP) without imposing any additional upstream frame delay.</P> <P><B>Highlights</B></P> <P> <UL> <LI> First effort dedicated to arrange different types of grants during a DBA cycle. </LI> <LI> We proposed a state-of-art Grant Management Procedure (GMP). </LI> <LI> GMP maximizes the energy saving in TDM-PONs with sleep mode enabled ONUs. </LI> <LI> ONUs utilizing GMP can predict gratuitous grant control message arrival time. </LI> </UL> </P>