Performance Prediction Based Workload Scheduling in Co-Located Cluster

Cloud service providers generally co-locate online services and batch jobs onto the same computer cluster,where the resources can be pooled in order to maximize data center resource utilization.Due to resource competition between batch jobs and online services,co-location frequently impairs the performance of online services.This study presents a quality of service(QoS)prediction-based schedulingmodel(QPSM)for co-locatedworkloads.The performance prediction of QPSM consists of two parts:the prediction of an online service’s QoS anomaly based on XGBoost and the prediction of the completion time of an offline batch job based on randomforest.On-line service QoS anomaly prediction is used to evaluate the influence of batch jobmix on on-line service performance,and batch job completion time prediction is utilized to reduce the total waiting time of batch jobs.When the same number of batch jobs are scheduled in experiments using typical test sets such as CloudSuite,the scheduling time required by QPSM is reduced by about 6 h on average compared with the first-come,first-served strategy and by about 11 h compared with the random scheduling strategy.Compared with the non-co-located situation,QPSM can improve CPU resource utilization by 12.15% and memory resource utilization by 5.7% on average.Experiments show that the QPSM scheduling strategy proposed in this study can effectively guarantee the quality of online services and further improve cluster resource utilization.

A Sharding Scheme Based on Graph Partitioning Algorithm for Public Blockchain

Blockchain technology,with its attributes of decentralization,immutability,and traceability,has emerged as a powerful catalyst for enhancing traditional industries in terms of optimizing business processes.However,transaction performance and scalability has become the main challenges hindering the widespread adoption of blockchain.Due to its inability to meet the demands of high-frequency trading,blockchain cannot be adopted in many scenarios.To improve the transaction capacity,researchers have proposed some on-chain scaling technologies,including lightning networks,directed acyclic graph technology,state channels,and shardingmechanisms,inwhich sharding emerges as a potential scaling technology.Nevertheless,excessive cross-shard transactions and uneven shard workloads prevent the sharding mechanism from achieving the expected aim.This paper proposes a graphbased sharding scheme for public blockchain to efficiently balance the transaction distribution.Bymitigating crossshard transactions and evening-out workloads among shards,the scheme reduces transaction confirmation latency and enhances the transaction capacity of the blockchain.Therefore,the scheme can achieve a high-frequency transaction as well as a better blockchain scalability.Experiments results show that the scheme effectively reduces the cross-shard transaction ratio to a range of 35%-56%and significantly decreases the transaction confirmation latency to 6 s in a blockchain with no more than 25 shards.

Hybrid Strategy of Partitioned and Monolithic Methods for Solving Strongly Coupled Analysis of Inverse and Direct Piezoelectric and Circuit Coupling

The inverse and direct piezoelectric and circuit coupling are widely observed in advanced electro-mechanical systems such as piezoelectric energy harvesters.Existing strongly coupled analysis methods based on direct numerical modeling for this phenomenon can be classified into partitioned or monolithic formulations.Each formulation has its advantages and disadvantages,and the choice depends on the characteristics of each coupled problem.This study proposes a new option:a coupled analysis strategy that combines the best features of the existing formulations,namely,the hybrid partitioned-monolithic method.The analysis of inverse piezoelectricity and the monolithic analysis of direct piezoelectric and circuit interaction are strongly coupled using a partitioned iterative hierarchical algorithm.In a typical benchmark problem of a piezoelectric energy harvester,this research compares the results from the proposed method to those from the conventional strongly coupled partitioned iterative method,discussing the accuracy,stability,and computational cost.The proposed hybrid concept is effective for coupled multi-physics problems,including various coupling conditions.

Restraint effect of partition wall on the tunnel floor heave in layered rock mass

The presence of horizontal layered rocks in tunnel engineering significantly impacts the stability and strength of the surrounding rock mass,leading to floor heave in the tunnel.This study focused on preparing layered specimens of rock-like material with varying thickness to investigate the failure behaviors of tunnel floors.The results indicate that thin-layered rock mass exhibits weak interlayer bonding,causing rock layers near the surface to buckle and break upwards when subjected to horizontal squeezing.With an increase in the layer thickness,a transition in failure mode occurs from upward buckling to shear failure along the plane,leading to a noticeable reduction in floor heave deformation.The primary cause of significant deformation in floor heave is upward buckling failure.To address this issue,the study proposes the installation of a partition wall in the middle of the floor to mitigate heave deformation of the rock layers.The results demonstrate that the partition wall has a considerable stabilizing effect on the floor,reducing the zone of buckling failure and minimizing floor heave deformation.It is crucial for the partition wall to be sufficiently high to prevent buckling failure and ensure stability.Through simulation calculations on an engineering example,it is confirmed that implementing a partition wall can effectively reduce floor heave and enhance the stability of tunnel floor.

Density estimation-based method to determine sample size for random sample partition of big data

Random sample partition(RSP)is a newly developed big data representation and management model to deal with big data approximate computation problems.Academic research and practical applications have confirmed that RSP is an efficient solution for big data processing and analysis.However,a challenge for implementing RSP is determining an appropriate sample size for RSP data blocks.While a large sample size increases the burden of big data computation,a small size will lead to insufficient distribution information for RSP data blocks.To address this problem,this paper presents a novel density estimation-based method(DEM)to determine the optimal sample size for RSP data blocks.First,a theoretical sample size is calculated based on the multivariate Dvoretzky-Kiefer-Wolfowitz(DKW)inequality by using the fixed-point iteration(FPI)method.Second,a practical sample size is determined by minimizing the validation error of a kernel density estimator(KDE)constructed on RSP data blocks for an increasing sample size.Finally,a series of persuasive experiments are conducted to validate the feasibility,rationality,and effectiveness of DEM.Experimental results show that(1)the iteration function of the FPI method is convergent for calculating the theoretical sample size from the multivariate DKW inequality;(2)the KDE constructed on RSP data blocks with sample size determined by DEM can yield a good approximation of the probability density function(p.d.f);and(3)DEM provides more accurate sample sizes than the existing sample size determination methods from the perspective of p.d.f.estimation.This demonstrates that DEM is a viable approach to deal with the sample size determination problem for big data RSP implementation.

Algorithm Selection Method Based on Coupling Strength for Partitioned Analysis of Structure-Piezoelectric-Circuit Coupling

In this study, we propose an algorithm selection method based on coupling strength for the partitioned analysis ofstructure-piezoelectric-circuit coupling, which includes two types of coupling or inverse and direct piezoelectriccoupling and direct piezoelectric and circuit coupling. In the proposed method, implicit and explicit formulationsare used for strong and weak coupling, respectively. Three feasible partitioned algorithms are generated, namely(1) a strongly coupled algorithm that uses a fully implicit formulation for both types of coupling, (2) a weaklycoupled algorithm that uses a fully explicit formulation for both types of coupling, and (3) a partially stronglycoupled and partially weakly coupled algorithm that uses an implicit formulation and an explicit formulation forthe two types of coupling, respectively.Numerical examples using a piezoelectric energy harvester,which is a typicalstructure-piezoelectric-circuit coupling problem, demonstrate that the proposed method selects the most costeffectivealgorithm.

Partitioning Calculation Method of Short-Circuit Current for High Proportion DG Access to Distribution Network

Aiming at the problemthat the traditional short-circuit current calculationmethod is not applicable to Distributed Generation(DG)accessing the distribution network,the paper proposes a short-circuit current partitioning calculation method considering the degree of voltage drop at the grid-connected point of DG.Firstly,the output characteristics of DG in the process of low voltage ride through are analyzed,and the equivalent output model of DG in the fault state is obtained.Secondly,by studying the network voltage distribution law after fault in distribution networks under different DG penetration rates,the degree of voltage drop at the grid-connected point of DG is used as a partition index to partition the distribution network.Then,iterative computation is performed within each partition,and data are transferred between partitions through split nodes to realize the fast partition calculation of short-circuit current for high proportion DG access to distribution network,which solves the problems of long iteration time and large calculation error of traditional short-circuit current.Finally,a 62-node real distribution network model containing a high proportion of DG access is constructed onMATLAB/Simulink,and the simulation verifies the effectiveness of the short-circuit current partitioning calculation method proposed in the paper,and its calculation speed is improved by 48.35%compared with the global iteration method.

Understanding and simulating of three-dimensional subsurface hydrological partitioning in an alpine mountainous area, China

Critical zone(CZ)plays a vital role in sustaining biodiversity and humanity.However,flux quantification within CZ,particularly in terms of subsurface hydrological partitioning,remains a significant challenge.This study focused on quantifying subsurface hydrological partitioning,specifically in an alpine mountainous area,and highlighted the important role of lateral flow during this process.Precipitation was usually classified as two parts into the soil:increased soil water content(SWC)and lateral flow out of the soil pit.It was found that 65%–88%precipitation contributed to lateral flow.The second common partitioning class showed an increase in SWC caused by both precipitation and lateral flow into the soil pit.In this case,lateral flow contributed to the SWC increase ranging from 43%to 74%,which was notably larger than the SWC increase caused by precipitation.On alpine meadows,lateral flow from the soil pit occurred when the shallow soil was wetter than the field capacity.This result highlighted the need for three-dimensional simulation between soil layers in Earth system models(ESMs).During evapotranspiration process,significant differences were observed in the classification of subsurface hydrological partitioning among different vegetation types.Due to tangled and aggregated fine roots in the surface soil on alpine meadows,the majority of subsurface responses involved lateral flow,which provided 98%–100%of evapotranspiration(ET).On grassland,there was a high probability(0.87),which ET was entirely provided by lateral flow.The main reason for underestimating transpiration through soil water dynamics in previous research was the neglect of lateral root water uptake.Furthermore,there was a probability of 0.12,which ET was entirely provided by SWC decrease on grassland.In this case,there was a high probability(0.98)that soil water responses only occurred at layer 2(10–20 cm),because grass roots mainly distributed in this soil layer,and grasses often used their deep roots for water uptake during ET.To improve the estimation of soil water dynamics and ET,we established a random forest(RF)model to simulate lateral flow and then corrected the community land model(CLM).RF model demonstrated good performance and led to significant improvements in CLM simulation.These findings enhance our understanding of subsurface hydrological partitioning and emphasize the importance of considering lateral flow in ESMs and hydrological research.

Airgap-harmonic-oriented Partitioned Design Method of PMV Motor with Improved Torque Performances

Here,we introduce a partitioned design method that is oriented toward airgap harmonic for permanent magnet vernier(PMV)motors.The method proposes the utilization of airgap flux harmonics as an effective bridge between the torque design region and the torque performances.To illustrate the efficacy of this method,a partitioned design PMV motor is presented and compared with the initial design.Firstly,the torque design region of the rotor is artfully divided into the torque enhancement region and ripple reduction region.Meanwhile,the main harmonics that generate output torque are chosen and enhanced,optimization.Moreover,the harmonics that generate torque ripple are selected and reduced based on torque harmonics optimization.Finally,the functions of the partitioned PMV motor torque are assessed based on the finite element method.By the purposeful design of these two regions,the output torque is strengthened while torque ripple is inhibited effectively,verifying the effectiveness and reasonability of the proposed design method.

A Two-Layer Active Power Optimization and Coordinated Control for Regional Power Grid Partitioning to Promote Distributed Renewable Energy Consumption

With the large-scale development and utilization of renewable energy,industrial flexible loads,as a kind of loadside resource with strong regulation ability,provide new opportunities for the research on renewable energy consumption problem in power systems.This paper proposes a two-layer active power optimization model based on industrial flexible loads for power grid partitioning,aiming at improving the line over-limit problem caused by renewable energy consumption in power grids with high proportion of renewable energy,and achieving the safe,stable and economical operation of power grids.Firstly,according to the evaluation index of renewable energy consumption characteristics of line active power,the power grid is divided into several partitions,and the interzone tie lines are taken as the optimization objects.Then,on the basis of partitioning,a two-layer active power optimization model considering the power constraints of industrial flexible loads is established.The upper-layer model optimizes the planned power of the inter-zone tie lines under the constraint of the minimum peak-valley difference within a day;the lower-layer model optimizes the regional source-load dispatching plan of each resource in each partition under the constraint of theminimumoperation cost of the partition,so as to reduce the line overlimit phenomenon caused by renewable energy consumption and save the electricity cost of industrial flexible loads.Finally,through simulation experiments,it is verified that the proposed model can effectively mobilize industrial flexible loads to participate in power grid operation and improve the economic stability of power grid.

Symplectic partitioned Runge-Kutta method based onthe eighth-order nearly analytic discrete operator and its wavefield simulations

We propose a symplectic partitioned Runge-Kutta （SPRK） method with eighth-order spatial accuracy based on the extended Hamiltonian system of the acoustic waveequation. Known as the eighth-order NSPRK method, this technique uses an eighth-orderaccurate nearly analytic discrete （NAD） operator to discretize high-order spatial differentialoperators and employs a second-order SPRK method to discretize temporal derivatives.The stability criteria and numerical dispersion relations of the eighth-order NSPRK methodare given by a semi-analytical method and are tested by numerical experiments. We alsoshow the differences of the numerical dispersions between the eighth-order NSPRK methodand conventional numerical methods such as the fourth-order NSPRK method, the eighth-order Lax-Wendroff correction （LWC） method and the eighth-order staggered-grid （SG）method. The result shows that the ability of the eighth-order NSPRK method to suppress thenumerical dispersion is obviously superior to that of the conventional numerical methods. Inthe same computational environment, to eliminate visible numerical dispersions, the eighth-order NSPRK is approximately 2.5 times faster than the fourth-order NSPRK and 3.4 timesfaster than the fourth-order SPRK, and the memory requirement is only approximately47.17% of the fourth-order NSPRK method and 49.41% of the fourth-order SPRK method,which indicates the highest computational efficiency. Modeling examples for the two-layermodels such as the heterogeneous and Marmousi models show that the wavefields generatedby the eighth-order NSPRK method are very clear with no visible numerical dispersion.These numerical experiments illustrate that the eighth-order NSPRK method can effectivelysuppress numerical dispersion when coarse grids are adopted. Therefore, this methodcan greatly decrease computer memory requirement and accelerate the forward modelingproductivity. In general, the eighth-order NSPRK method has tremendous potential value forseismic exploration and seismology research.

Fruit Photosynthesis and Assimilate Translocation and Partitioning: Their Characteristics and Role in Sugar Accumulation in Developing Citrus unshiu Fruit

Dynamics of dry- or fresh-weight of fruit, peel photosynthetic rate and chlorophyll content, and the characteristics of translocation and distribution of radiolabelled assimilates from leaf or fruit were examined in developing satsuma mandarin (Citrus unshiu Marc. cv. Miyagawa wase) fruit from primary stage of fruit enlargement up to fruit full ripe. Change in fruit photosynthetic rate was some what related to the change in the chlorophyll content of peel. Fruit photosynthetic rate markedly declined as chlorophyll degradation occurred in the peel. Before full ripe stage of the fruit, photosynthates produced by a 14C-fed leaf were mainly distributed to juice sacs even during periods when dry matter accumulation in peel was more rapid than that in juice sacs. At the full ripe stage, peel photosynthetic rate approached zero and peel became the major sink of leaf photosynthates. Most of the peel assimilates, however, remained in situ for up to 48 h after feeding 14CO 2 to the fruit, only a small portion being transported to other parts of fruit. The percentage of fruit photosynthates exported decreased with fruit development and ripening, but the peak rate of export to juice sacs amount to as high as 12%. The sugar content and dry weights of peel and juice sacs in shaded fruit were lower than that in the control fruit. These results show that peel assimilate was mainly consumed in peel respiration and growth and thus the dependence on leaf photosynthates decreased. Part of this assimiate was used in sugar accumulation in juice sacs of fruit.

A Reduced-Order Modeling of Multi-Port RC Networks by Means of Graph Partitioning

A modified reduced-order method for RC networks which takes a division-and-conquest strategy is presented.The whole network is partitioned into a set of sub-networks at first,then each of them is reduced by Krylov subspace techniques,and finally all the reduced sub-networks are incorporated together.With some accuracy,this method can reduce the number of both nodes and components of the circuit comparing to the traditional methods which usually only offer a reduced net with less nodes.This can markedly accelerate the sparse-matrix-based simulators whose performance is dominated by the entity of the matrix or the number of components of the circuits.

Comparison of spectral partitioning techniques for wind wave and swell

The ocean waves are generally mixed with wind wave and swell. In order to separate these two kinds of ocean waves, many wave spectral partitioning techniques have been proposed. In this study, a two-dimensional（2D） and three one-dimensional （1D） wave spectral partitioning techniques （denoted as PM, WH, and JP） are examined based on the model simulations and in-situ observations. It is shown that the 2D technique could provide the most reliable results as a whole. Compared with 2D technique, PM and JP techniques obviously overestimate the wind-wave components, and the same situation happens for WH technique at low wind speed. With the adjustment of the partitioning frequency ratio, the 1D PM technique is modified, in which the result agree well with that of the 2D scheme.

Adaptive Layout Partitioning for Dark Field Alternating Phase-Shift Mask Design

A new partitioning methodology is presented to accelerate 130nm and beyond large scale alternating phase shift mask(Alt PSM) design flow.This method deals with granularity self adaptively.Phase conflicts resolution approaches are described and strategies guaranteeing phase compatible during layout compaction are also discussed.An efficient CAD prototype for dark field Alt PSM based on these algorithms is implemented.The experimental results on several industry layouts show that the tool can successfully cope with the rapid growth of phase conflicts with good quality and satisfy lower resource consumption with different requirements of precision and speedup.

Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of AuCu_3-type sublattice system

Taking AuCu3-type sublattice system as an example, three discoveries have been presented: First, the third barrier hindering the progress in metal materials science is that researchers have got used to recognizing experimental phenomena of alloy phase transitions during extremely slow variation in temperature by equilibrium thinking mode and then taking erroneous knowledge of experimental phenomena as selected information for establishing Gibbs energy function and so-called equilibrium phase diagram. Second, the equilibrium holographic network phase diagrams of AuCu3-type sublattice system may be used to describe systematic correlativity of the composition?temperature-dependent alloy gene arranging structures and complete thermodynamic properties, and to be a standard for studying experimental subequilibrium order-disorder transition. Third, the equilibrium transition of each alloy is a homogeneous single-phase rather than a heterogeneous two-phase, and there exists a single-phase boundary curve without two-phase region of the ordered and disordered phases; the composition and temperature of the top point on the phase-boundary curve are far away from the ones of the critical point of the AuCu3 compound.

Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of Au_3Cu-type sublattice system

Taking Au3Cu-type sublattice system as an example, three discoveries have been presented. First, the fourth barrier to hinder the progress of metal materials science is that today’s researchers do not understand that the Gibbs energy function of an alloy phase should be derived from Gibbs energy partition function constructed of alloy gene sequence and their Gibbs energy sequence. Second, the six rules for establishing alloy gene Gibbs energy partition function have been discovered, and it has been specially proved that the probabilities of structure units occupied at the Gibbs energy levels in the degeneracy factor for calculating configuration entropy should be degenerated as ones of component atoms occupied at the lattice points. Third, the main characteristics unexpected by today’s researchers are as follows. There exists a single-phase boundary curve without two-phase region coexisting by the ordered and disordered phases. The composition and temperature of the top point on the phase-boundary curve are far away from those of the critical point of the Au3Cu compound; At 0 K, the composition of the lowest point on the composition-dependent Gibbs energy curve is notably deviated from that of the Au3Cu compounds. The theoretical limit composition range of long range ordered Au3Cu-type alloys is determined by the first jumping order degree.

Food Resource Partitioning in Alpine Weasel,Steppe Polecat and Upland Buzzard:Evidence from Stable Isotope Ratios

Based on mass balance theory and IsoSource program,stable carbon and nitrogen isotopic ratios revealed that small mammals (plateau pika,root vole and plateau zokor) contributed 26.8% and 27.0% and 29.2% to alpine weasel,steppe polecat and upland buzzard of carnivores as food respectively;adult passerine birds contributed 22.3%,47.7% and 69.1%,with hatchlings contributing 50.9%,25.6% and 1.70% to each respectively.δ 13 C values plotted against δ 15 N indicated significant partitioning in two-dimensional space among the three carnivores.It was reasonable to propose a food resource partitioning among alpine weasel,steppe polecat and upland buzzard,which partially revealed their co-existence mechanisms.

基于关联规则的Apriori-Partition算法的可视化研究

关联规则的提取是数据挖掘中的重要研究内容,对关联规则提取中的Apriori算法进行了分析与研究,针对该算法的运算效率不高,对该算法进行了优化。Partition算法以经典的Apriori算法为基础,通过将数据库分成几个互不相交的块来实现算法效率的提高。同时,还介绍了一种基于Apriori-Partition算法的可视化挖掘模型,并讨论了该可视化模型的实现方法。

An Efficient Partitioning Method in Quadratic Placement

A method of combining the MFFC clustering and hMETIS partitioning based quadratic placement algorithm is proposed. Experimental results show that it can gain good results but consume long running time.In order to cut down the running time,an improved MFFC clustering method (IMFFC) based Q-place algorithm is proposed.Comparing with the combining clustering and partitioning based method,it is much faster but with a little increase in total wire length.