To achieve high quality of service （QoS） on computational grids, the QoS-aware job scheduling is investigated for a hierarchical decentralized grid architecture that consists of multilevel schedulers. An integrated ...To achieve high quality of service （QoS） on computational grids, the QoS-aware job scheduling is investigated for a hierarchical decentralized grid architecture that consists of multilevel schedulers. An integrated QoS-aware job dispatching policy is proposed, which correlates priorities of incoming jobs used for job selecting at the local scheduler of the grid node with the job dispatching policies at the global scheduler for computational grids. The stochastic high-level Petri net （SHLPN） model of a two-level hierarchy computational grid architecture is presented, and a model refinement is made to reduce the complexity of the model solution. A performance analysis technique based on the SHLPN is proposed to investigate the QoS-aware job scheduling policy. Numerical results show that the QoS-aware job dispatching policy outperforms the QoS-unaware job dispatching policy in balancing the high-priority jobs, and thus enables priority-based QoS.展开更多
With rapid advancement of Cloud computing and networking technologies, a wide spectrum of Cloud services have been developed by various providers and utilized by numerous organizations as indispensable ingredients of ...With rapid advancement of Cloud computing and networking technologies, a wide spectrum of Cloud services have been developed by various providers and utilized by numerous organizations as indispensable ingredients of their information systems. Cloud service performance has a significant impact on performance of the future information infrastructure. Thorough evaluation on Cloud service performance is crucial and beneficial to both service providers and consumers; thus forming an active research area. Some key technologies for Cloud computing, such as virtualization and the Service-Oriented Architecture （SOA）, bring in special challenges to service performance evaluation. A tremendous amount of effort has been put by the research community to address these challenges and exciting progress has been made. Among the work on Cloud performance analysis, evaluation approaches developed with a system modeling perspective play an important role. However, related works have been reported in different sections of the literature; thus lacking a big picture that shows the latest status of this area. The objectives of this article is to present a survey that reflects the state of the art of Cloud service performance evaluation from the system modeling perspective. This articles also examines open issues and challenges to the surveyed evaluation approaches and identifies possible opportunities for future research in this important field.展开更多
Today the PC class machines are quite popular for HPC area, especially on the problemsthat require the good cost/performance ratios. One of the drawback of these machines is the poormemory throughput performance. And ...Today the PC class machines are quite popular for HPC area, especially on the problemsthat require the good cost/performance ratios. One of the drawback of these machines is the poormemory throughput performance. And one of the reasons of the poor performance is depend on the lack of the mapping capability of the TLB which is a buffer to accelerate the virtual memory access. In this report, I present that the mapping capability and the performance can be improved with the multi granularity TLB feature that some processors have. And I also present that the new TLB handling routine can be incorporated into the demand paging system of Linux.展开更多
Indicators are the basis for judging the working performance of exhaust hood and capture performance are usually used as the only indicator.An evaluation index system including three factors of cooking oil fumes(COF)i...Indicators are the basis for judging the working performance of exhaust hood and capture performance are usually used as the only indicator.An evaluation index system including three factors of cooking oil fumes(COF)instantaneous capture,health risk impact and thermal comfort was proposed to assess the comprehensive performance of exhaust hood in the present study.The primary capture efficiency(PCE)of formaldehyde,the PCE of particulate matter with the diameter less than or equal to 2.5μm(PM_(2.5)),the incremental lifetime cancer risk(ILCR)of formaldehyde,the ILCR of PM_(2.5)and the predicted mean vote(PMV),which can all be quantified with the aid of computational fluid dynamics(CFD),were selected as the indicators.And the analytic hierarchy process(AHP)method was introduced to perform the comprehensive performance evaluation of exhaust hood.The performance of two exhaust hood structures(grille and orifice type)with three exhaust rates(3000,4000,and 5000 m^(3)/h)in two cooking zones of a university canteen kitchen were evaluated.The result showed that the reduction of ILCR of COF exposure is the most important to the performance of exhaust hood.The comprehensive performance of orifice exhaust hood with exhaust rate of 4000 and 5000 m^(3)/h are optimal;the orifice exhaust hood with exhaust of 3000 m^(3)/h and grille exhaust hood with exhaust rate of 5000 m^(3)/h are moderate;the grille exhaust hood with exhaust rate of 3000 and 4000 m^(3)/h are low.Decision-making priorities based on comprehensive and individual performance are not exactly the same in the two cooking zones.It is necessary to use the index system to evaluate the comprehensive performance of exhaust hood that considers the impact on human health and thermal comfort.展开更多
Cloud computing allows scalability at a lower cost for data analytics in a big data environment. This paradigm considers the dimensioning of resources to process different volumes of data, minimizing the response time...Cloud computing allows scalability at a lower cost for data analytics in a big data environment. This paradigm considers the dimensioning of resources to process different volumes of data, minimizing the response time of big data. This work proposes a performance and availability evaluation of big data environments in the private cloud through a methodology and stochastic and combinatorial models considering performance metrics such as execution times, processor utilization, memory utilization, and availability. The proposed methodology considers objective activities, performance, and availability modeling to evaluate the private cloud environment. A performance model based on stochastic Petrinets is adopted to evaluate the big data environment on the private cloud. Reliability block diagram models are adopted to evaluate the availability of big environment data in the private cloud. Two case studies based on the CloudStack platform and Hadoop cluster are adopted to demonstrate the viability of the proposed methodologies and models. Case Study 1 evaluated the performance metrics of the Hadoop cluster in the private cloud, considering different service offerings, workloads, and the number of data sets. The sentiment analysis technique is used in tweets from users with symptoms of depression to generate the analyzed datasets. Case Study 2 evaluated the availability of big data environments in the private cloud.展开更多
The meteorological high-performance computing resource is the support platform for the weather forecast and climate prediction numerical model operation. The scientific and objective method to evaluate the application...The meteorological high-performance computing resource is the support platform for the weather forecast and climate prediction numerical model operation. The scientific and objective method to evaluate the application of meteorological high-performance computing resources can not only provide reference for the optimization of active resources, but also provide a quantitative basis for future resource construction and planning. In this paper, the concept of the utility value B and index compliance rate E of the meteorological high performance computing system are presented. The evaluation process, evaluation index and calculation method of the high performance computing resource application benefits are introduced.展开更多
This work started out with the in-depth feasibil-ity study and limitation analysis on the current disease spread estimating and countermea-sures evaluating models, then we identify that the population variability is a...This work started out with the in-depth feasibil-ity study and limitation analysis on the current disease spread estimating and countermea-sures evaluating models, then we identify that the population variability is a crucial impact which has been always ignored or less empha-sized. Taking HIV/AIDS as the application and validation background, we propose a novel al-gorithm model system, EEA model system, a new way to estimate the spread situation, evaluate different countermeasures and analyze the development of ARV-resistant disease strains. The model is a series of solvable ordi-nary differential equation (ODE) models to es-timate the spread of HIV/AIDS infections, which not only require only one year’s data to deduce the situation in any year, but also apply the piecewise constant method to employ multi- year information at the same time. We simulate the effects of therapy and vaccine, then evaluate the difference between them, and offer the smallest proportion of the vaccination in the population to defeat HIV/AIDS, especially the advantage of using the vaccination while the deficiency of using therapy separately. Then we analyze the development of ARV-resistant dis-ease strains by the piecewise constant method. Last but not least, high performance computing (HPC) platform is applied to simulate the situa-tion with variable large scale areas divided by grids, and especially the acceleration rate will come to around 4 to 5.5.展开更多
The Internet of Things(IoT)and allied applications have made real-time responsiveness for massive devices over the Internet essential.Cloud-edge/fog ensembles handle such applications'computations.For Beyond 5 th ...The Internet of Things(IoT)and allied applications have made real-time responsiveness for massive devices over the Internet essential.Cloud-edge/fog ensembles handle such applications'computations.For Beyond 5 th Generation(B5G)communication paradigms,Edge Servers(ESs)must be placed within Information Communication Technology infrastructures to meet Quality of Service requirements like response time and resource utilisation.Due to the large number of Base Stations(BSs)and ESs and the possibility of significant variations in placing the ESs within the IoTs geographical expanse for optimising multiple objectives,the Edge Server Placement Problem(ESPP)is NP-hard.Thus,stochastic evolutionary metaheuristics are natural.This work addresses the ESPP using a Particle Swarm Optimization that initialises particles as BS positions within the geography to maintain the workload while scanning through all feasible sets of BSs as an encoded sequence.The Workload-Threshold Aware Sequence Encoding(WTASE)Scheme for ESPP provides the number of ESs to be deployed,similar to existing methodologies and exact locations for their placements without the overhead of maintaining a prohibitively large distance matrix.Simulation tests using open-source datasets show that the suggested technique improves ESs utilisation rate,workload balance,and average energy consumption by 36%,17%,and 32%,respectively,compared to prior works.展开更多
In medical imaging,accurate brain tumor classification in medical imaging requires real-time processing and efficient computation,making hardware acceleration essential.Field Programmable Gate Arrays(FPGAs)offer paral...In medical imaging,accurate brain tumor classification in medical imaging requires real-time processing and efficient computation,making hardware acceleration essential.Field Programmable Gate Arrays(FPGAs)offer parallelism and reconfigurability,making them well-suited for such tasks.In this study,we propose a hardware-accelerated Convolutional Neural Network(CNN)for brain cancer classification,implemented on the PYNQ-Z2 FPGA.Our approach optimizes the first Conv2D layer using different numerical representations:8-bit fixed-point(INT8),16-bit fixed-point(FP16),and 32-bit fixed-point(FP32),while the remaining layers run on an ARM Cortex-A9 processor.Experimental results demonstrate that FPGA acceleration significantly outperforms the CPU(Central Processing Unit)based approach.The obtained results emphasize the critical importance of selecting the appropriate numerical representation for hardware acceleration in medical imaging.On the PYNQ-Z2 FPGA,the INT8 achieves a 16.8%reduction in latency and 22.2%power savings compared to FP32,making it ideal for real-time and energy-constrained applications.FP16 offers a strong balance,delivering only a 0.1%drop in accuracy compared to FP32(94.1%vs.94.2%)while improving latency by 5%and reducing power consumption by 11.1%.Compared to prior works,the proposed FPGA-based CNN model achieves the highest classification accuracy(94.2%)with a throughput of up to 1.562 FPS,outperforming GPU-based and traditional CPU methods in both accuracy and hardware efficiency.These findings demonstrate the effectiveness of FPGA-based AI acceleration for real-time,power-efficient,and high-performance brain tumor classification,showcasing its practical potential in next-generation medical imaging systems.展开更多
基金The National Natural Science Foundation of China(No60673054,90412012)
文摘To achieve high quality of service （QoS） on computational grids, the QoS-aware job scheduling is investigated for a hierarchical decentralized grid architecture that consists of multilevel schedulers. An integrated QoS-aware job dispatching policy is proposed, which correlates priorities of incoming jobs used for job selecting at the local scheduler of the grid node with the job dispatching policies at the global scheduler for computational grids. The stochastic high-level Petri net （SHLPN） model of a two-level hierarchy computational grid architecture is presented, and a model refinement is made to reduce the complexity of the model solution. A performance analysis technique based on the SHLPN is proposed to investigate the QoS-aware job scheduling policy. Numerical results show that the QoS-aware job dispatching policy outperforms the QoS-unaware job dispatching policy in balancing the high-priority jobs, and thus enables priority-based QoS.
文摘With rapid advancement of Cloud computing and networking technologies, a wide spectrum of Cloud services have been developed by various providers and utilized by numerous organizations as indispensable ingredients of their information systems. Cloud service performance has a significant impact on performance of the future information infrastructure. Thorough evaluation on Cloud service performance is crucial and beneficial to both service providers and consumers; thus forming an active research area. Some key technologies for Cloud computing, such as virtualization and the Service-Oriented Architecture （SOA）, bring in special challenges to service performance evaluation. A tremendous amount of effort has been put by the research community to address these challenges and exciting progress has been made. Among the work on Cloud performance analysis, evaluation approaches developed with a system modeling perspective play an important role. However, related works have been reported in different sections of the literature; thus lacking a big picture that shows the latest status of this area. The objectives of this article is to present a survey that reflects the state of the art of Cloud service performance evaluation from the system modeling perspective. This articles also examines open issues and challenges to the surveyed evaluation approaches and identifies possible opportunities for future research in this important field.
文摘Today the PC class machines are quite popular for HPC area, especially on the problemsthat require the good cost/performance ratios. One of the drawback of these machines is the poormemory throughput performance. And one of the reasons of the poor performance is depend on the lack of the mapping capability of the TLB which is a buffer to accelerate the virtual memory access. In this report, I present that the mapping capability and the performance can be improved with the multi granularity TLB feature that some processors have. And I also present that the new TLB handling routine can be incorporated into the demand paging system of Linux.
基金supported by the National Key R&D Program of China(No.2017YFC0211502).
文摘Indicators are the basis for judging the working performance of exhaust hood and capture performance are usually used as the only indicator.An evaluation index system including three factors of cooking oil fumes(COF)instantaneous capture,health risk impact and thermal comfort was proposed to assess the comprehensive performance of exhaust hood in the present study.The primary capture efficiency(PCE)of formaldehyde,the PCE of particulate matter with the diameter less than or equal to 2.5μm(PM_(2.5)),the incremental lifetime cancer risk(ILCR)of formaldehyde,the ILCR of PM_(2.5)and the predicted mean vote(PMV),which can all be quantified with the aid of computational fluid dynamics(CFD),were selected as the indicators.And the analytic hierarchy process(AHP)method was introduced to perform the comprehensive performance evaluation of exhaust hood.The performance of two exhaust hood structures(grille and orifice type)with three exhaust rates(3000,4000,and 5000 m^(3)/h)in two cooking zones of a university canteen kitchen were evaluated.The result showed that the reduction of ILCR of COF exposure is the most important to the performance of exhaust hood.The comprehensive performance of orifice exhaust hood with exhaust rate of 4000 and 5000 m^(3)/h are optimal;the orifice exhaust hood with exhaust of 3000 m^(3)/h and grille exhaust hood with exhaust rate of 5000 m^(3)/h are moderate;the grille exhaust hood with exhaust rate of 3000 and 4000 m^(3)/h are low.Decision-making priorities based on comprehensive and individual performance are not exactly the same in the two cooking zones.It is necessary to use the index system to evaluate the comprehensive performance of exhaust hood that considers the impact on human health and thermal comfort.
文摘Cloud computing allows scalability at a lower cost for data analytics in a big data environment. This paradigm considers the dimensioning of resources to process different volumes of data, minimizing the response time of big data. This work proposes a performance and availability evaluation of big data environments in the private cloud through a methodology and stochastic and combinatorial models considering performance metrics such as execution times, processor utilization, memory utilization, and availability. The proposed methodology considers objective activities, performance, and availability modeling to evaluate the private cloud environment. A performance model based on stochastic Petrinets is adopted to evaluate the big data environment on the private cloud. Reliability block diagram models are adopted to evaluate the availability of big environment data in the private cloud. Two case studies based on the CloudStack platform and Hadoop cluster are adopted to demonstrate the viability of the proposed methodologies and models. Case Study 1 evaluated the performance metrics of the Hadoop cluster in the private cloud, considering different service offerings, workloads, and the number of data sets. The sentiment analysis technique is used in tweets from users with symptoms of depression to generate the analyzed datasets. Case Study 2 evaluated the availability of big data environments in the private cloud.
文摘The meteorological high-performance computing resource is the support platform for the weather forecast and climate prediction numerical model operation. The scientific and objective method to evaluate the application of meteorological high-performance computing resources can not only provide reference for the optimization of active resources, but also provide a quantitative basis for future resource construction and planning. In this paper, the concept of the utility value B and index compliance rate E of the meteorological high performance computing system are presented. The evaluation process, evaluation index and calculation method of the high performance computing resource application benefits are introduced.
文摘This work started out with the in-depth feasibil-ity study and limitation analysis on the current disease spread estimating and countermea-sures evaluating models, then we identify that the population variability is a crucial impact which has been always ignored or less empha-sized. Taking HIV/AIDS as the application and validation background, we propose a novel al-gorithm model system, EEA model system, a new way to estimate the spread situation, evaluate different countermeasures and analyze the development of ARV-resistant disease strains. The model is a series of solvable ordi-nary differential equation (ODE) models to es-timate the spread of HIV/AIDS infections, which not only require only one year’s data to deduce the situation in any year, but also apply the piecewise constant method to employ multi- year information at the same time. We simulate the effects of therapy and vaccine, then evaluate the difference between them, and offer the smallest proportion of the vaccination in the population to defeat HIV/AIDS, especially the advantage of using the vaccination while the deficiency of using therapy separately. Then we analyze the development of ARV-resistant dis-ease strains by the piecewise constant method. Last but not least, high performance computing (HPC) platform is applied to simulate the situa-tion with variable large scale areas divided by grids, and especially the acceleration rate will come to around 4 to 5.5.
基金the Deanship of Research and Graduate Studies at King Khalid University for funding this work through the Large Research Project under grant number RGP2/603/46。
文摘The Internet of Things(IoT)and allied applications have made real-time responsiveness for massive devices over the Internet essential.Cloud-edge/fog ensembles handle such applications'computations.For Beyond 5 th Generation(B5G)communication paradigms,Edge Servers(ESs)must be placed within Information Communication Technology infrastructures to meet Quality of Service requirements like response time and resource utilisation.Due to the large number of Base Stations(BSs)and ESs and the possibility of significant variations in placing the ESs within the IoTs geographical expanse for optimising multiple objectives,the Edge Server Placement Problem(ESPP)is NP-hard.Thus,stochastic evolutionary metaheuristics are natural.This work addresses the ESPP using a Particle Swarm Optimization that initialises particles as BS positions within the geography to maintain the workload while scanning through all feasible sets of BSs as an encoded sequence.The Workload-Threshold Aware Sequence Encoding(WTASE)Scheme for ESPP provides the number of ESs to be deployed,similar to existing methodologies and exact locations for their placements without the overhead of maintaining a prohibitively large distance matrix.Simulation tests using open-source datasets show that the suggested technique improves ESs utilisation rate,workload balance,and average energy consumption by 36%,17%,and 32%,respectively,compared to prior works.
基金supported by Northern Border University Researchers Supporting Project number(NBU-FFR-2025-432-03),Northern Border University,Arar,Saudi Arabia.
文摘In medical imaging,accurate brain tumor classification in medical imaging requires real-time processing and efficient computation,making hardware acceleration essential.Field Programmable Gate Arrays(FPGAs)offer parallelism and reconfigurability,making them well-suited for such tasks.In this study,we propose a hardware-accelerated Convolutional Neural Network(CNN)for brain cancer classification,implemented on the PYNQ-Z2 FPGA.Our approach optimizes the first Conv2D layer using different numerical representations:8-bit fixed-point(INT8),16-bit fixed-point(FP16),and 32-bit fixed-point(FP32),while the remaining layers run on an ARM Cortex-A9 processor.Experimental results demonstrate that FPGA acceleration significantly outperforms the CPU(Central Processing Unit)based approach.The obtained results emphasize the critical importance of selecting the appropriate numerical representation for hardware acceleration in medical imaging.On the PYNQ-Z2 FPGA,the INT8 achieves a 16.8%reduction in latency and 22.2%power savings compared to FP32,making it ideal for real-time and energy-constrained applications.FP16 offers a strong balance,delivering only a 0.1%drop in accuracy compared to FP32(94.1%vs.94.2%)while improving latency by 5%and reducing power consumption by 11.1%.Compared to prior works,the proposed FPGA-based CNN model achieves the highest classification accuracy(94.2%)with a throughput of up to 1.562 FPS,outperforming GPU-based and traditional CPU methods in both accuracy and hardware efficiency.These findings demonstrate the effectiveness of FPGA-based AI acceleration for real-time,power-efficient,and high-performance brain tumor classification,showcasing its practical potential in next-generation medical imaging systems.
