To decrease the cost of exchanging load information among processors, a dynamic load-balancing (DLB) algorithm which adopts multieast tree technology is proposed. The muhieast tree construction rules are also propos...To decrease the cost of exchanging load information among processors, a dynamic load-balancing (DLB) algorithm which adopts multieast tree technology is proposed. The muhieast tree construction rules are also proposed to avoid wrongly transferred or redundant DLB messages due to the overlapping of multicast trees. The proposed DLB algorithm is distributed controlled, sender initiated and can help heavily loaded processors with complete distribution of redundant loads with minimum number of executions. Experiments were executed to compare the effects of the proposed DLB algorithm and other three ones, the results prove the effectivity and practicability of the proposed algorithm in dealing with great scale compute-intensive tasks.展开更多
This paper proposes a dynamic load balancing with learning model for a Sudoku problem solving system that has multiple workers and multiple solvers.The objective is to minimise the total processing time of problem sol...This paper proposes a dynamic load balancing with learning model for a Sudoku problem solving system that has multiple workers and multiple solvers.The objective is to minimise the total processing time of problem solving.Our load balancing with learning model distributes each Sudoku problem to an appropriate pair of worker and solver when it is received by the system.The information of the estimated solution time for a specific number of given input values,the estimated finishing time of each worker,and the idle status of each worker is used to determine the worker-solver pairs.In addition,the proposed system can estimate the waiting period for each problem.Test results show that the system has shorter processing time than conventional alternatives.展开更多
High level architecture(HLA) is the open standard in the collaborative simulation field. Scholars have been paying close attention to theoretical research on and engineering applications of collaborative simulation ba...High level architecture(HLA) is the open standard in the collaborative simulation field. Scholars have been paying close attention to theoretical research on and engineering applications of collaborative simulation based on HLA/RTI, which extends HLA in various aspects like functionality and efficiency. However, related study on the load balancing problem of HLA collaborative simulation is insufficient. Without load balancing, collaborative simulation under HLA/RTI may encounter performance reduction or even fatal errors. In this paper, load balancing is further divided into static problems and dynamic problems. A multi-objective model is established and the randomness of model parameters is taken into consideration for static load balancing, which makes the model more credible. The Monte Carlo based optimization algorithm(MCOA) is excogitated to gain static load balance. For dynamic load balancing, a new type of dynamic load balancing problem is put forward with regards to the variable-structured collaborative simulation under HLA/RTI. In order to minimize the influence against the running collaborative simulation, the ordinal optimization based algorithm(OOA) is devised to shorten the optimization time. Furthermore, the two algorithms are adopted in simulation experiments of different scenarios, which demonstrate their effectiveness and efficiency. An engineering experiment about collaborative simulation under HLA/RTI of high speed electricity multiple units(EMU) is also conducted to indentify credibility of the proposed models and supportive utility of MCOA and OOA to practical engineering systems. The proposed research ensures compatibility of traditional HLA, enhances the ability for assigning simulation loads onto computing units both statically and dynamically, improves the performance of collaborative simulation system and makes full use of the hardware resources.展开更多
With the growing amount of information and data, object-oriented storage systems have been widely used in many applications, including the Google File System, Amazon S3, Hadoop Distributed File System, and Ceph, in wh...With the growing amount of information and data, object-oriented storage systems have been widely used in many applications, including the Google File System, Amazon S3, Hadoop Distributed File System, and Ceph, in which load balancing of metadata plays an important role in improving the input/output performance of the entire system. Unbalanced load on the metadata server leads to a serious bottleneck problem for system performance. However, most existing metadata load balancing strategies, which are based on subtree segmentation or hashing, lack good dynamics and adaptability. In this study, we propose a metadata dynamic load balancing(MDLB) mechanism based on reinforcement learning(RL). We learn that the Q_learning algorithm and our RL-based strategy consist of three modules, i.e., the policy selection network, load balancing network, and parameter update network. Experimental results show that the proposed MDLB algorithm can adjust the load dynamically according to the performance of the metadata servers, and that it has good adaptability in the case of sudden change of data volume.展开更多
A new load balancing algorithm named dynamic weighed random (DWR) algorithm for the session initiation protocol (SIP) application server cluster is proposed. It uses weighted hashing random algorithm that supports...A new load balancing algorithm named dynamic weighed random (DWR) algorithm for the session initiation protocol (SIP) application server cluster is proposed. It uses weighted hashing random algorithm that supports dialog in the SIP protocol to distribute messages. The weight of each server is dynamic adaptive with feedback mechanism. DWR insures that the cluster is balanced, and it performs better than the limited resource vector (LRV) algorithm and minimum sessions first (MSF) algorithm.展开更多
Dynamic load balancing schemes are significant for efficiently executing nonuniform problems in highly parallel multicomputer systems. The objective is to minimize the total execution time of single applications. Thi...Dynamic load balancing schemes are significant for efficiently executing nonuniform problems in highly parallel multicomputer systems. The objective is to minimize the total execution time of single applications. This paper has proposed an ARID strategy for distributed dynamic load balancing. Its principle and control protocol are described, and the communication overhead, the effect on system stability and the performance efficiency are analyzed. Finally,simulation experiments are carried out to compare the adaptive strategy with other dynamic load balancing schemes.展开更多
In the big data platform,because of the large amount of data,the problem of load imbalance is prominent.Most of the current load balancing methods have problems such as high data flow loss rate and long response time;...In the big data platform,because of the large amount of data,the problem of load imbalance is prominent.Most of the current load balancing methods have problems such as high data flow loss rate and long response time;therefore,more effective load balancing method is urgently needed.Taking HBase as the research subject,the study analyzed the dynamic load balancing method of data flow.First,the HBase platform was introduced briefly,and then the dynamic load-balancing algorithm was designed.The data flow was divided into blocks,and then the load of nodes was predicted based on the grey prediction GM(1,1)model.Finally,the load was migrated through the dynamic adjustable method to achieve load balancing.The experimental results showed that the accuracy of the method for load prediction was high,the average error percentage was 0.93%,and the average response time was short;under 3000 tasks,the response time of the method designed in this study was 14.17%shorter than that of the method combining TV white space(TVWS)and long-term evolution(LTE);the average flow of nodes with the largest load was also smaller,and the data flow loss rate was basically 0%.The experimental results show the effectiveness of the proposed method,which can be further promoted and applied in practice.展开更多
A key issue of dynamic load balancing in a loosely coupled distributed systemis selecting appropriate jobs to transfer. In this paper, a job selection policybased on on-line predicting behaviors of jobs is proposed. T...A key issue of dynamic load balancing in a loosely coupled distributed systemis selecting appropriate jobs to transfer. In this paper, a job selection policybased on on-line predicting behaviors of jobs is proposed. Thacing is used atthe beginning of execution of a job to predict the approkimate execution timeand resource requirements of the job so as to make a correct decision aboutwhether transferring the job is worthwhile. A dynamic load balancer using thejob selection policy has been implemelited. Experimelital measurement resultsshow that the policy proposed is able to improve mean response time of jobsand resource utilization of systems substantially.展开更多
The parallel computation capabilities of modern graphics processing units (GPUs) have attracted increasing attention from researchers and engineers who have been conducting high computational throughput studies. How...The parallel computation capabilities of modern graphics processing units (GPUs) have attracted increasing attention from researchers and engineers who have been conducting high computational throughput studies. However, current single GPU based engineering solutions are often struggling to fulfill their real-time requirements. Thus, the multi-GPU-based approach has become a popular and cost-effective choice for tackling the demands. In those cases, the computational load balancing over multiple GPU "nodes" is often the key and bottleneck that affect the quality and performance of the real=time system. The existing load balancing approaches are mainly based on the assumption that all GPU nodes in the same computer framework are of equal computational performance, which is often not the case due to cluster design and other legacy issues. This paper presents a novel dynamic load balancing (DLB) model for rapid data division and allocation on heterogeneous GPU nodes based on an innovative fuzzy neural network (FNN). In this research, a 5-state parameter feedback mechanism defining the overall cluster and node performance is proposed. The corresponding FNN-based DLB model will be capable of monitoring and predicting individual node performance under different workload scenarios. A real=time adaptive scheduler has been devised to reorganize the data inputs to each node when necessary to maintain their runtime computational performance. The devised model has been implemented on two dimensional (2D) discrete wavelet transform (DWT) applications for evaluation. Experiment results show that this DLB model enables a high computational throughput while ensuring real=time and precision requirements from complex computational tasks.展开更多
Pseudo-Particle Modeling (PPM) is a particle method proposed by Ge and Li in 1996 [Ge, W., & Li, J. (1996). Pseudo-particle approach to hydrodynamics of particle-fluid systems, in M. Kwauk & J. Li (Eds.), Proc...Pseudo-Particle Modeling (PPM) is a particle method proposed by Ge and Li in 1996 [Ge, W., & Li, J. (1996). Pseudo-particle approach to hydrodynamics of particle-fluid systems, in M. Kwauk & J. Li (Eds.), Proceedings of the 5th international conference on drculating fluidized bed (pp. 260-265). Beijing: Science Press] and has been used to explore the microscopic mechanism in complex particle-fluid systems. But as a particle method, high computational cost remains a main obstacle for its large-scale application; therefore, parallel implementation of this method is highly desirable. Parallelization of two-dimensional PPM was carried out by spatial decomposition in this paper. The time costs of the major functions in the program were analyzed and the program was then optimized for higher efficiency by dynamic load balancing and resetting of particle arrays. Finally, simulation on a gas-solid fluidized bed with 102,400 solid particles and 1.8 × 10^7 pseudo-particles was performed successfully with this code, indicating its scalability in future applications.展开更多
Parallel frequent pattern discovery algorithms exploit parallel and distributed computing resources to relieve the sequential bottlenecks of current frequent pattern mining (FPM) algorithms. Thus, parallel FPM algor...Parallel frequent pattern discovery algorithms exploit parallel and distributed computing resources to relieve the sequential bottlenecks of current frequent pattern mining (FPM) algorithms. Thus, parallel FPM algorithms achieve better scalability and performance, so they are attracting much attention in the data mining research community. This paper presents a comprehensive survey of the state-of-the-art parallel and distributed frequent pattern mining algorithms with more emphasis on pattern discovery from complex data (e.g., sequences and graphs) on various platforms. A review of typical parallel FPM algorithms uncovers the major challenges, methodologies, and research problems in the field of parallel frequent pattern discovery, such as work-load balancing, finding good data layouts, and data decomposition. This survey also indicates a dramatic shift of the research interest in the field from the simple parallel frequent itemset mining on traditional parallel and distributed platforms to parallel pattern mining of more complex data on emerging architectures, such as multi-core systems and the increasingly mature grid infrastructure.展开更多
基金the National Natural Science Foundation of China(69973007)
文摘To decrease the cost of exchanging load information among processors, a dynamic load-balancing (DLB) algorithm which adopts multieast tree technology is proposed. The muhieast tree construction rules are also proposed to avoid wrongly transferred or redundant DLB messages due to the overlapping of multicast trees. The proposed DLB algorithm is distributed controlled, sender initiated and can help heavily loaded processors with complete distribution of redundant loads with minimum number of executions. Experiments were executed to compare the effects of the proposed DLB algorithm and other three ones, the results prove the effectivity and practicability of the proposed algorithm in dealing with great scale compute-intensive tasks.
文摘This paper proposes a dynamic load balancing with learning model for a Sudoku problem solving system that has multiple workers and multiple solvers.The objective is to minimise the total processing time of problem solving.Our load balancing with learning model distributes each Sudoku problem to an appropriate pair of worker and solver when it is received by the system.The information of the estimated solution time for a specific number of given input values,the estimated finishing time of each worker,and the idle status of each worker is used to determine the worker-solver pairs.In addition,the proposed system can estimate the waiting period for each problem.Test results show that the system has shorter processing time than conventional alternatives.
基金supported by National Science and Technology Support Program of China (Grant No. 2012BAF15G00)
文摘High level architecture(HLA) is the open standard in the collaborative simulation field. Scholars have been paying close attention to theoretical research on and engineering applications of collaborative simulation based on HLA/RTI, which extends HLA in various aspects like functionality and efficiency. However, related study on the load balancing problem of HLA collaborative simulation is insufficient. Without load balancing, collaborative simulation under HLA/RTI may encounter performance reduction or even fatal errors. In this paper, load balancing is further divided into static problems and dynamic problems. A multi-objective model is established and the randomness of model parameters is taken into consideration for static load balancing, which makes the model more credible. The Monte Carlo based optimization algorithm(MCOA) is excogitated to gain static load balance. For dynamic load balancing, a new type of dynamic load balancing problem is put forward with regards to the variable-structured collaborative simulation under HLA/RTI. In order to minimize the influence against the running collaborative simulation, the ordinal optimization based algorithm(OOA) is devised to shorten the optimization time. Furthermore, the two algorithms are adopted in simulation experiments of different scenarios, which demonstrate their effectiveness and efficiency. An engineering experiment about collaborative simulation under HLA/RTI of high speed electricity multiple units(EMU) is also conducted to indentify credibility of the proposed models and supportive utility of MCOA and OOA to practical engineering systems. The proposed research ensures compatibility of traditional HLA, enhances the ability for assigning simulation loads onto computing units both statically and dynamically, improves the performance of collaborative simulation system and makes full use of the hardware resources.
基金Project supported by the National Natural Science Foundation of China(Nos.61572520 and 61521003)。
文摘With the growing amount of information and data, object-oriented storage systems have been widely used in many applications, including the Google File System, Amazon S3, Hadoop Distributed File System, and Ceph, in which load balancing of metadata plays an important role in improving the input/output performance of the entire system. Unbalanced load on the metadata server leads to a serious bottleneck problem for system performance. However, most existing metadata load balancing strategies, which are based on subtree segmentation or hashing, lack good dynamics and adaptability. In this study, we propose a metadata dynamic load balancing(MDLB) mechanism based on reinforcement learning(RL). We learn that the Q_learning algorithm and our RL-based strategy consist of three modules, i.e., the policy selection network, load balancing network, and parameter update network. Experimental results show that the proposed MDLB algorithm can adjust the load dynamically according to the performance of the metadata servers, and that it has good adaptability in the case of sudden change of data volume.
基金supported by the National Science Fund for Distinguished Young Scholars (60525110)the National Basic Research Program of China (2007CB307100, 2007CB307103)Development Fund Project for Electronic and Information Industry
文摘A new load balancing algorithm named dynamic weighed random (DWR) algorithm for the session initiation protocol (SIP) application server cluster is proposed. It uses weighted hashing random algorithm that supports dialog in the SIP protocol to distribute messages. The weight of each server is dynamic adaptive with feedback mechanism. DWR insures that the cluster is balanced, and it performs better than the limited resource vector (LRV) algorithm and minimum sessions first (MSF) algorithm.
文摘Dynamic load balancing schemes are significant for efficiently executing nonuniform problems in highly parallel multicomputer systems. The objective is to minimize the total execution time of single applications. This paper has proposed an ARID strategy for distributed dynamic load balancing. Its principle and control protocol are described, and the communication overhead, the effect on system stability and the performance efficiency are analyzed. Finally,simulation experiments are carried out to compare the adaptive strategy with other dynamic load balancing schemes.
文摘In the big data platform,because of the large amount of data,the problem of load imbalance is prominent.Most of the current load balancing methods have problems such as high data flow loss rate and long response time;therefore,more effective load balancing method is urgently needed.Taking HBase as the research subject,the study analyzed the dynamic load balancing method of data flow.First,the HBase platform was introduced briefly,and then the dynamic load-balancing algorithm was designed.The data flow was divided into blocks,and then the load of nodes was predicted based on the grey prediction GM(1,1)model.Finally,the load was migrated through the dynamic adjustable method to achieve load balancing.The experimental results showed that the accuracy of the method for load prediction was high,the average error percentage was 0.93%,and the average response time was short;under 3000 tasks,the response time of the method designed in this study was 14.17%shorter than that of the method combining TV white space(TVWS)and long-term evolution(LTE);the average flow of nodes with the largest load was also smaller,and the data flow loss rate was basically 0%.The experimental results show the effectiveness of the proposed method,which can be further promoted and applied in practice.
文摘A key issue of dynamic load balancing in a loosely coupled distributed systemis selecting appropriate jobs to transfer. In this paper, a job selection policybased on on-line predicting behaviors of jobs is proposed. Thacing is used atthe beginning of execution of a job to predict the approkimate execution timeand resource requirements of the job so as to make a correct decision aboutwhether transferring the job is worthwhile. A dynamic load balancer using thejob selection policy has been implemelited. Experimelital measurement resultsshow that the policy proposed is able to improve mean response time of jobsand resource utilization of systems substantially.
基金supported by National Natural Science Foundation of China(No.61203172)the SSTP of Sichuan(Nos.2018YYJC0994 and 2017JY0011)Shenzhen STPP(No.GJHZ20160301164521358)
文摘The parallel computation capabilities of modern graphics processing units (GPUs) have attracted increasing attention from researchers and engineers who have been conducting high computational throughput studies. However, current single GPU based engineering solutions are often struggling to fulfill their real-time requirements. Thus, the multi-GPU-based approach has become a popular and cost-effective choice for tackling the demands. In those cases, the computational load balancing over multiple GPU "nodes" is often the key and bottleneck that affect the quality and performance of the real=time system. The existing load balancing approaches are mainly based on the assumption that all GPU nodes in the same computer framework are of equal computational performance, which is often not the case due to cluster design and other legacy issues. This paper presents a novel dynamic load balancing (DLB) model for rapid data division and allocation on heterogeneous GPU nodes based on an innovative fuzzy neural network (FNN). In this research, a 5-state parameter feedback mechanism defining the overall cluster and node performance is proposed. The corresponding FNN-based DLB model will be capable of monitoring and predicting individual node performance under different workload scenarios. A real=time adaptive scheduler has been devised to reorganize the data inputs to each node when necessary to maintain their runtime computational performance. The devised model has been implemented on two dimensional (2D) discrete wavelet transform (DWT) applications for evaluation. Experiment results show that this DLB model enables a high computational throughput while ensuring real=time and precision requirements from complex computational tasks.
基金the Designated Funding for Winners of President’s Awards of Chinese Academy of Sciences(CAS,2006)financial supports from the National Natural Science Foundation of China(NSFC)under the Grant No.20221603 and 20706057
文摘Pseudo-Particle Modeling (PPM) is a particle method proposed by Ge and Li in 1996 [Ge, W., & Li, J. (1996). Pseudo-particle approach to hydrodynamics of particle-fluid systems, in M. Kwauk & J. Li (Eds.), Proceedings of the 5th international conference on drculating fluidized bed (pp. 260-265). Beijing: Science Press] and has been used to explore the microscopic mechanism in complex particle-fluid systems. But as a particle method, high computational cost remains a main obstacle for its large-scale application; therefore, parallel implementation of this method is highly desirable. Parallelization of two-dimensional PPM was carried out by spatial decomposition in this paper. The time costs of the major functions in the program were analyzed and the program was then optimized for higher efficiency by dynamic load balancing and resetting of particle arrays. Finally, simulation on a gas-solid fluidized bed with 102,400 solid particles and 1.8 × 10^7 pseudo-particles was performed successfully with this code, indicating its scalability in future applications.
基金Supported by the Basic Research Foundation of Tsinghua Na-tional Laboratory for Information Science and Technology (TNList)
文摘Parallel frequent pattern discovery algorithms exploit parallel and distributed computing resources to relieve the sequential bottlenecks of current frequent pattern mining (FPM) algorithms. Thus, parallel FPM algorithms achieve better scalability and performance, so they are attracting much attention in the data mining research community. This paper presents a comprehensive survey of the state-of-the-art parallel and distributed frequent pattern mining algorithms with more emphasis on pattern discovery from complex data (e.g., sequences and graphs) on various platforms. A review of typical parallel FPM algorithms uncovers the major challenges, methodologies, and research problems in the field of parallel frequent pattern discovery, such as work-load balancing, finding good data layouts, and data decomposition. This survey also indicates a dramatic shift of the research interest in the field from the simple parallel frequent itemset mining on traditional parallel and distributed platforms to parallel pattern mining of more complex data on emerging architectures, such as multi-core systems and the increasingly mature grid infrastructure.