近年来,作为重要的多目标决策手段的轮廓查询逐渐得到学术界的重视,相继提出了基于不同支配关系的多种轮廓变体查询.首先,通过对实际应用需求进行分析,提出了基于元组对应数值间比例值大小的ρ-支配关系的定义,进而提出了ρ-支配轮廓查询的概念.其次,对ρ-支配轮廓的基本性质进行了细致而深入的分析,在此基础上,提出了基于分支定界的ρ-支配轮廓查询算法(Branch and Boundρ-Dominant Skyline Algorithm,BBDS),避免了对R-树索引的多次访问,从而提高了ρ-支配轮廓查询的执行效率.最后,通过大量的仿真实验对ρ-支配轮廓查询的语义进行分析,并对BBDS算法的性能进行验证.实验结果表明,ρ-支配轮廓查询是轮廓查询语义的扩展和补充,而提出的BBDS算法则是求解ρ-支配轮廓查询的高效算法.
Aiming at the load imbalance and poor scalability in single-tier Web server clusters, an efficient load balancing ap- proach is proposed for constructing an N-hierarchical (multi-tier) Web server cluster. In each layer, multiple load balancers are set to receive the user requests simultaneously, and different load bal- ancing algorithms are used to construct the high-scalable Web cluster system. At the same time, an improved load balancing al- gorithm is proposed, which can dynamically calculate weights according to the utilization of the server resources, and reasonably distribute the loads for each server according to the load status of the servers. The experimental results show that the proposed ap- proach can greatly decrease the load imbalance among the Web servers and reduce the response time of the entire Web cluster system.
PAK IlcholQIAO BaiyouSHEN MuchuanZHU JunhaiCHEN Donghai
Accurate prediction of sea surface temperature (SST) is extremely important for forecasting oceanic environmental events and for ocean studies. However, the existing SST prediction methods do not consider the seasonal periodicity and abnormal fluctuation characteristics of SST or the importance of historical SST data from different times;thus, these methods suffer from low prediction accuracy. To solve this problem, we comprehensively consider the effects of seasonal periodicity and abnormal fluctuation characteristics of SST data, as well as the influence of historical data in different periods, on prediction accuracy. We propose a novel ensemble learning approach that combines the Predictive Recurrent Neural Network(PredRNN) network and an attention mechanism for effective SST field prediction. In this approach, the XGBoost model is used to learn the long-period fluctuation law of SST and to extract seasonal periodic features from SST data. The exponential smoothing method is used to mitigate the impact of severely abnormal SST fluctuations and extract the a priori features of SST data. The outputs of the two aforementioned models and the original SST data are stacked and used as inputs for the next model, the PredRNN network. PredRNN is the most recently developed spatiotemporal deep learning network, which simulates both spatial and temporal representations and is capable of transferring memory across layers and time steps. Therefore, we used it to extract the spatiotemporal correlations of SST data and predict future SSTs. Finally, an attention mechanism is added to capture the importance of different historical SST data, weigh the output of each step of the PredRNN network, and improve the prediction accuracy. The experimental results on two ocean datasets confirm that the proposed approach achieves higher training efficiency and prediction accuracy than the existing SST field prediction approaches do.
Baiyou QIAOZhongqiang WULing MAYicheng ZhouYunjiao SUN