基于NR-Transformer的集群作业运行时间预测

高性能集群的作业调度通常使用作业调度系统来实现，准确填写作业运行时间能在很大程度上提升作业调度效率。现有的研究通常使用机器学习的预测方式，在预测精度和实用性上还存在一定的提升空间。为了进一步提高集群作业运行时间预测的准确率，考虑先对集群作业日志进行聚类，将作业类别信息添加到作业特征中，再使用基于注意力机制的NR-Transformer网络对作业日志数据建模和预测。在数据处理上，根据与预测目标的相关性、特征的完整性和数据的有效性，从历史日志数据集中筛选出7维特征，并按作业运行时间的长度将其划分为多个作业集，再对各作业集分别进行训练和预测。实验结果表明，相比于传统机器学习和BP神经网络，时序神经网络结构有更好的预测性能，其中NR-Transformer在各作业集上都有较好的性能。     

Nanocellulose-based reusable liquid metal printed electronics fabricated by evaporation-induced transfer printing

Reusable electronics have received widespread attention and are urgently needed. Here, nanocellulosebased liquid metal(NC-LM) printed circuit has been fabricated by the evaporation-induced transfer printing technology. In this way, the liquid metal pattern is embedded into the nanocellulose membrane, which is beneficial for the stability of the circuit during use. Besides, the NC-LM circuit is ultrathin with just tens of microns. In particular, the finished product is environmentally friendly because it can be completely dissolved by water, and both the liquid metal ink and the nanocellulose membrane can be easily recollected and reused, thereby reducing waste and pollution to the environment. Several examples of flexible circuits have been designed to evaluate their performance. The mechanism of evaporation-induced transfer printing technology involves the deposition, aggregation, and coverage tightly of the nanosized cellulose fibrils as the water evaporated. This study provides an economical and environmentally friendly way for the fabrication of renewable flexible electronics.     

Automatic design for shop scheduling strategies based on hyper-heuristics: A systematic review

Against the background of smart manufacturing and Industry 4.0, how to achieve real-time scheduling has become a problem to be solved. In this regard, automatic design for shop scheduling based on hyper-heuristics has been widely studied, and a number of reviews and scheduling algorithms have been presented. Few studies, however, have specifically discussed the technical points involved in algorithm development. This study, therefore, constructs a general framework for automatic design for shop scheduling strategies based on hyper-heuristics, and various state-of-the-art technical points in the development process are summarized. First, we summarize the existing types of shop scheduling strategies and classify them using a new classification method. Second, we summarize an automatic design algorithm for shop scheduling. Then, we investigate surrogate-assisted methods that are popular in the current algorithm field. Finally, current problems and challenges are discussed, and potential directions for future research are proposed.     

Chicken nuggets-like core/shell nanosheet arrays as high performance flexible all-solid-state supercapacitor cathode and buckwheat shell as anode

The energy density of a flexible all-solid-state supercapacitor (ASC) requires new electrode material with special structure and morphology as a prerequisite for its secured improvement. In this paper, a new morphological exploration of chicken nuggets-like core/shell NiCo₂O₄/MnO₂ (NCM) nanosheet arrays on Ni foam was employed. The application of this special morphology aims to greatly improve the electrochemical performance of the cathode electrode. Additionally, Buckwheat Biochar (BBC) is utilized as the anode while the PVA/KOH thin film is prepared as the separator. The chicken nuggets-like core/shell NCM nanosheet arrays were obtained by a two-step hydrothermal method. A series of characterization methods were carried out to further support the core/shell's well-designed structure and precise composition. The tests exhibited excellent specific capacitance of 593.3 F g^?1 at 5 mA cm^?2 and outstanding cycling stability with a retention of 90% after 10000 cycles. Furthermore, the assembled NCM//BBC ASC device indicated a high specific capacitance (239 F g^?1 at the current density of 5 mA cm^?2), this is in due part of the unique architecture of NCM nanosheet arrays and interconnected special porous structure of the BBC and the thin film PVA/KOH. Hence, the assembled ASC device exhibited high energy density (an energy density of 58 Wh·kg^?1 at 3263 W kg^?1) and remarkable cycling stability.     

Design and validation of robotic bionic eye with multiple flexible ropes parallel mechanism inspired by oculomotor law

Producing a stable and agile bionic eye for visual image acquisition in robotics is a challenging task. In this paper, we design a bionic eye with mirror-symmetric distribution and cross-connection of flexible ropes. This mechanism is based on oculomotor law and the physiological structure of the extraocular muscles (EOMs). Specifically, the basic structural parameters are determined by Listing’s law, and the unique connection of the flexible ropes can realize the functions of the recti and oblique muscles. Furthermore, to mimic the trochlea structure, a pulley mechanism is constructed to permit the free movement of the flexible ropes. Through simulation and physical experiments, it is demonstrated that the bionic eye mechanism can move with agility under the structural parameters. The experimental results indicate that the proposed bionic eye mechanism has a superior motion accuracy of 2.798 mm, which is 6.7% of the maximum motion distance, and the repeatable accuracy of the mechanism can up to 0.210 mm.     

A globally convergent BFGS method for pseudo-monotone variational inequality problems

In this paper, we propose a globally convergent BFGS method to solve Variational Inequality Problems (VIPs). In fact, a globalization technique on the basis of the hyperplane projection method is applied to the BFGS method. The technique, which is independent of any merit function, is applicable for pseudo-monotone problems. The proposed method applies the BFGS direction and tries to reduce the distance of iterates to the solution set. This property, called Fejer monotonicity of iterates with respect to the solution set, is the basis of the convergence analysis. The method applied to pseudo-monotone VIP is globally convergent in the sense that subproblems always have unique solutions, and the sequence of iterates converges to a solution to the problem without any regularity assumption. Finally, some numerical simulations are included to evaluate the efficiency of the proposed algorithm.     

Multiple Empirical Kernel Learning with Majority Projection for imbalanced problems

Traditional Multiple Empirical Kernel Learning (MEKL) expands the expressions of the sample and brings better classification ability by using different empirical kernels to map the original data space into multiple kernel spaces. To make MEKL suit for the imbalanced problems, this paper introduces a weight matrix and a regularization term into MEKL. The weight matrix assigns high misclassification cost to the minority samples to balanced misclassification cost between minority and majority class. The regularization term named Majority Projection (MP) is used to make the classification hyperplane fit the distribution shape of majority samples and enlarge the between-class distance of minority and majority class. The contributions of this work are: (i) assigning high cost to minority samples to deal with imbalanced problems, (ii) introducing a new regularization term to concern the property of data distribution, (iii) and modifying the original PAC-Bayes bound to test the error upper bound of MEKL-MP. Through analyzing the experimental results, the proposed MEKL-MP is well suited to the imbalanced problems and has lower generalization risk in accordance with the value of PAC-Bayes bound.     

Container-based cluster orchestration systems: A taxonomy and future directions

Containers, enabling lightweight environment and performance isolation, fast and flexible deployment, and fine-grained resource sharing, have gained popularity in better application management and deployment in addition to hardware virtualization. They are being widely used by organizations to deploy their increasingly diverse workloads derived from modern-day applications such as web services, big data, and internet of things in either proprietary clusters or private and public cloud data centers. This has led to the emergence of container orchestration platforms, which are designed to manage the deployment of containerized applications in large-scale clusters. These systems are capable of running hundreds of thousands of jobs across thousands of machines. To do so efficiently, they must address several important challenges including scalability, fault tolerance and availability, efficient resource utilization, and request throughput maximization among others. This paper studies these management systems and proposes a taxonomy that identifies different mechanisms that can be used to meet the aforementioned challenges. The proposed classification is then applied to various state-of-the-art systems leading to the identification of open research challenges and gaps in the literature intended as future directions for researchers.