Search

Vision Transformer (ViT) has performed remarkably in various computer vision tasks. Nonetheless, affected by the massive amount of parameters, ViT usually suffers from serious overfitting problems with a relatively limited number of training samples. In addition, ViT generally demands heavy computing resources, which limit its deployment on resource-constrained devices. As a type of model-compression method, model binarization is potentially a good choice to solve the above problems. Compared with the full-precision one, the model with the binarization method replaces complex tensor multiplication with simple bit-wise binary operations and represents full-precision model parameters and activations with only 1-bit ones, which potentially solves the problem of model size and computational complexity, respectively. In this paper, we investigate a binarized ViT model. Empirically, we observe that the existing binarization technology designed for Convolutional Neural Networks (CNN) cannot migrate well to a ViT's binarization task. We also find that the decline of the accuracy of the binary ViT model is mainly due to the information loss of the Attention module and the Value vector. Therefore, we propose a novel model binarization technique, called G roup S uperposition B inarization (GSB), to deal with these issues. Furthermore, in order to further improve the performance of the binarization model, we have investigated the gradient calculation procedure in the binarization process and derived more proper gradient calculation equations for GSB to reduce the influence of gradient mismatch. Then, the knowledge distillation technique is introduced to alleviate the performance degradation caused by model binarization. Analytically, model binarization can limit the parameter's search space during parameter updates while training a model. Therefore, the binarization process can actually play an implicit regularization role and help solve the problem of overfitting in the case of insufficient training data. Experiments on three datasets with limited numbers of training samples demonstrate that the proposed GSB model achieves state-of-the-art performance among the binary quantization schemes and exceeds its full-precision counterpart on some indicators. Code and models are available at: https://github.com/IMRL/GSB-Vision-Transformer. [ABSTRACT FROM AUTHOR]

Abstract: Sybil attacks have been regarded as a serious security threat to Ad hoc Networks and Sensor Networks. They may also impair the potential applications in Vehicular Ad hoc Networks (VANETs) by creating an illusion of traffic congestion. In this paper, we make various attempts to explore the feasibility of detecting Sybil attacks by analyzing signal strength distribution. First, we propose a cooperative method to verify the positions of potential Sybil nodes. We use a Random Sample Consensus (RANSAC)-based algorithm to make this cooperative method more robust against outlier data fabricated by Sybil nodes. However, several inherent drawbacks of this cooperative method prompt us to explore additional approaches. We introduce a statistical method and design a system which is able to verify where a vehicle comes from. The system is termed the Presence Evidence System (PES). With PES, we are able to enhance the detection accuracy using statistical analysis over an observation period. Finally, based on realistic US maps and traffic models, we conducted simulations to evaluate the feasibility and efficiency of our methods. Our scheme proves to be an economical approach to suppressing Sybil attacks without extra support from specific positioning hardware. [Copyright &y& Elsevier]

Abstract: Cloud computing is emerging as an increasingly important service-oriented computing paradigm. Management is a key to providing accurate service availability and performance data, as well as enabling real-time provisioning that automatically provides the capacity needed to meet service demands. In this paper, we present a unified reinforcement learning approach, namely URL, to automate the configuration processes of virtualized machines and appliances running in the virtual machines. The approach lends itself to the application of real-time autoconfiguration of clouds. It also makes it possible to adapt the VM resource budget and appliance parameter settings to the cloud dynamics and the changing workload to provide service quality assurance. In particular, the approach has the flexibility to make a good trade-off between system-wide utilization objectives and appliance-specific SLA optimization goals. Experimental results on Xen VMs with various workloads demonstrate the effectiveness of the approach. It can drive the system into an optimal or near-optimal configuration setting in a few trial-and-error iterations. [Copyright &y& Elsevier]

Abstract: The paper proposes Luenberger-like observers for a rotating body-beam system. The latter is described by a partial differential equation and its dynamic is governed a unitary group. The observers proposed in the paper are able to reconstitute the dynamic evolution of the beam profile, by measuring the moment force on the boundary only. Meanwhile we propose a reliable numerical scheme, based on a finite element method, in order to simulate the observation system and the observers. The efficiency of our proposed scheme and the performances of the observers are illustrated with numerical simulation results. [ABSTRACT FROM AUTHOR]

Abstract: Networked computing systems continue to grow in scale and in the complexity of their components and interactions. Component failures become norms instead of exceptions in these environments. Moreover, failure events exhibit strong correlations in the time and space domains. In this paper, we develop a spherical covariance model with an adjustable timescale parameter to quantify the temporal correlation and a stochastic model to characterize spatial correlation. The models are further extended to take into account the information of application allocation to discover more correlations among failure instances. We cluster failure events based on their correlations and predict their future occurrences. Experimental results on a production coalition system, the Wayne State Computational Grid, show the offline and online predictions made by our predicting system can forecast 72.7–85.3% of the failure occurrences and capture failure correlations in a cluster coalition environment. [Copyright &y& Elsevier]

Abstract: Distributed hash table (DHT) networks based on consistent hashing functions have an inherent load uneven distribution problem. The objective of DHT load balancing is to balance the workload of the network nodes in proportion to their capacity so as to eliminate traffic bottleneck. It is challenging because of the dynamism, proximity and heterogeneity natures of DHT networks and time-varying load characteristics. In this paper, we present a hash-based proximity clustering approach for load balancing in heterogeneous DHTs. In the approach, DHT nodes are classified as regular nodes and supernodes according to their computing and networking capacities. Regular nodes are grouped and associated with supernodes via consistent hashing of their physical proximity information on the Internet. The supernodes form a self-organized and churn-resilient auxiliary network for load balancing. The hierarchical structure facilitates the design and implementation of a locality-aware randomized (LAR) load balancing algorithm. The algorithm introduces a factor of randomness in the load balancing processes in a range of neighborhood so as to deal with both the proximity and dynamism. Simulation results show the superiority of the clustering approach with LAR, in comparison with a number of other DHT load balancing algorithms. The approach performs no worse than existing proximity-aware algorithms and exhibits strong resilience to the effect of churn. It also greatly reduces the overhead of resilient randomized load balancing due to the use of proximity information. [Copyright &y& Elsevier]

Abstract: Virtualization provides a vehicle to manage the available resources and enhance their utilization in network computing. System dynamics requires virtual machines be distributed and reconfigurable. To construct reconfigurable distributed virtual machines, service migration moves the runtime services among physical servers when necessary. By incorporating the mobile agent technology, distributed virtual machines can improve their resource utilization and service availability significantly. This paper focuses on finding the optimal migration policies for service and agent migrations for high throughput in reconfigurable distributed virtual machines. We analyze three issues of this decision problem: migration candidate determination, migration timing and destination server selection. The service migration timing and destination server selection are formulated by two optimization models. We derive the optimal migration policy for distributed and heterogenous systems based on stochastic optimization theories. Renewal processes are applied to model the dynamics of migration. We solve the agent migration problem by dynamic programming and extend the optimal service migration decision by considering the interplay of the hybrid mobility. We verify the accuracy of our migration decision policy in simulations. [Copyright &y& Elsevier]

Dynamic remapping is critical to the performance of bulk synchronous computations that have non-deterministic behaviors because of the need of barrier synchronization between phases. There are two basic issues in remapping: when and how to remap. This paper presents a formal analysis of the issue of when to remap for dynamic computations with a priori known statistical behaviors, with an objective of finding optimal remapping frequencies for a given tolerance of load imbalance. The problem is formulated as two complement sequential stochastic optimization. Since general optimization techniques tend to reveal stationary properties of the workload process, they are not readily applicable to the analysis of the effect of periodic remapping. Instead, this paper develops new analytical approaches to precisely characterize the transient statistical behaviors of the workload process on both homogeneous and heterogeneous machines. Optimal remapping frequencies are derived for various random workload change processes with known or unknown probabilistic distributions. They are shown accurate via simulations. [Copyright &y& Elsevier]

Abstract The purpose of this paper is to investigate the identification of the water depth and the water velocity potential in a coastal region by using the linearized water wave equation (LWWE). Existence and uniqueness of the solutions to the partial differential equation LWWE are shown by using the semigroup theory. Moreover the analytical solution is found by the separation of variables method. We assume that the surface wave elevation is measurable. We like to recover the water depth and the water velocity potential from the measurement. This identification problem is shown to be well-posed by proving the parameters' identifiability by the surface elevation. Based on the classical gradient descent method we elaborate an identification algorithm to recover simultaneously both the water depth and the velocity potential. Numerical simulations are carried out to illustrate effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

We are concerned with the PI control/regulation design for a cascaded network of multi systems governed by hyperbolic partial differential equations. The PI controllers have both control inputs and measured outputs situated on the junctions. The stability analysis of closed-loop network is carried out in the L 2 topology by using the Lyapunov direct method. Then the output regulation is proven based on the stability of closed-loop systems. We finally work out detailed PI controller design for a practical cascaded network of n hydraulic Saint-Venant models as well as numerical simulations to validate theoretical results. [ABSTRACT FROM AUTHOR]

We propose an extended recursive Cramér–Rao lower bound (ER-CRLB) method as a fundamental tool to analyze the performance of wireless indoor localization systems. The ER-CRLB fully models the complicated indoor environment, e.g., the sequential position state propagation, the target-anchor geometry effect, the non-line-of-sight (NLOS) identification, and the related prior information. First, we use an abstract function to represent the entire wireless localization system model. Then, the unknown vector of the ER-CRLB consists of two parts: The first part is the estimated vector, and the second part is the auxiliary vector that helps improve the estimation accuracy. Accordingly, the Fisher information matrix (FIM) of the ER-CRLB is divided into two parts, namely, the state matrix and the auxiliary matrix. Based on this idea, ER-CRLB can be a practical fundamental limit to denote the system which fuses multiple information in the complicated environment, e.g., recursive Bayesian estimation based on the hidden Markov model, the map matching method and NLOS identification and mitigation methods. When only a small set of unknown vectors is estimated in the system, the ER-CRLB is equivalent to the other CRLBs of the wireless indoor localization system as well. However, the ER-CRLB is more adaptable than other CRLBs when considering more unknown important factors. We employ the ER-CRLB to analyze the time-of-arrival (TOA) range-based indoor localization system. The influence of the hybrid line-of-sight (LOS)/NLOS channels, the building layout information, and the relative height differences between the target and anchors are analyzed. It is demonstrated that the ER-CRLB exploits all the available information for the indoor localization systems and serves as a fundamental limit of the unbiased estimation accuracy. [ABSTRACT FROM PUBLISHER]

Resource discovery is critical to the usability and accessibility of grid computing systems. Distributed Hash Table (DHT) has been applied to grid systems as a distributed mechanism for providing scalable range-query and multi-attribute resource discovery. Multi-DHT-based approaches depend on multiple DHT networks with each network responsible for a single attribute. Single-DHT-based approaches keep the resource information of all attributes in a single node. Both classes of approaches lead to high overhead. In this paper, we propose a Low-Overhead Range-query Multi-attribute (LORM) DHT-based resource discovery approach. Unlike other DHT-based approaches, LORM relies on a single compound graph-based DHT network and distributes resource information among nodes in balance by taking advantage of the compound graph structure. Moreover, it has high capability to handle the large-scale and dynamic characteristics of resources in grids. Experimental results demonstrate the efficiency of LORM in comparison with other resource discovery approaches. LORM dramatically reduces maintenance and resource discovery overhead. In addition, it yields significant improvements in resource location efficiency. We also analyze the performance of the LORM approach rigorously by comparing it with other multi-DHT-based and single-DHT-based approaches with respect to their overhead and efficiency. The analytical results are consistent with experimental results, and prove the superiority of the LORM approach in theory. [ABSTRACT FROM AUTHOR]

In-network data aggregation is a useful technique to reduce redundant data and to improve communication efficiency. Traditional data aggregation schemes for wireless sensor networks usually rely on a fixed routing structure to ensure data can be aggregated at certain sensor nodes. However, they cannot be applied in highly mobile vehicular environments. In this paper, we propose an adaptive forwarding delay control scheme, namely Catch-Up, which dynamically changes the forwarding speed of nearby reports so that they have a better chance to meet each other and be aggregated together. The Catch-Up scheme is designed based on a distributed learning algorithm. Each vehicle learns from local observations and chooses a delay based on learning results. The simulation results demonstrate that our scheme can efficiently reduce the number of redundant reports and achieve a good trade-off between delay and communication overhead. [ABSTRACT FROM AUTHOR]

As e-commerce services are exponentially growing, businesses need quantitative estimates of client-perceived response times to continuously improve the quality of their services. Current server-side nonintrusive measurement techniques are limited to nonsecured HTTP traffic. In this paper, we present the design and evaluation a monitor, namely sMonitor, which is able to measure client-perceived response times for both HTTP and HTTPS traffic. At the heart of sMonitor is a novel size-based analysis method that parses live packets to delimit different webpages and to infer their response times. The method is based on the observation that most HTTP(S)-compatible browsers send significantly larger requests for container objects than those for embedded objects. sMonitor is designed to operate accurately in the presence of complicated browser behaviors, such as parallel downloading of multiple webpages and HTTP pipelining, as well as packet losses and delays. It requires only to passively collect network traffic in and out of the monitored secured services. We conduct comprehensive experiments across a wide range of operating conditions using live secured Internet services, on the PlanetLab, and on controlled networks. The experimental results demonstrate that sMonitor is able to control the estimation error within 6.7 percent, in comparison with the actual measured time at the client side. [ABSTRACT FROM AUTHOR]

Understanding server capacity is crucial to system capacity planning, configuration, and QoS-aware resource management. Conventional stress testing approaches measure server capacity offline in terms of application-level performance metrics like response time and throughput. They are limited in measurement accuracy and timeliness. In a multitier website, resource bottleneck often shifts between tiers as client access pattern changes. This makes the problem of online capacity measurement even more challenge. This paper presents an online measurement approach based on low-level hardware performance metrics such as instructions execution rate and cache access behavior. Such metrics together define a system internal running state. The measurement approach uses machine learning techniques to infer application-level performance at each tier from a set of selected hardware performance counters. A coordinated predictor is induced over individual tier-wide models to make global system performance prediction and identify the bottleneck when the system becomes overloaded. Experiments were conducted on a two-tier Tomcat/MySQL-configured website using TPC-W benchmarks. Experimental results demonstrated that this approach was able to achieve an overload prediction accuracy of higher than 90 percent for a priori known input traffic mix and over 85 percent accuracy even for traffic causing frequent bottleneck shifting. It costs less than 0.5 percent runtime overhead for data collection and no more than 50 ms for each online decision making. [ABSTRACT FROM AUTHOR]

Internet traffic often exhibits a structure with rich high-order statistical properties like self-similarity and long-range dependency (LRD). This greatly complicates the problem of server performance modeling and optimization. Existing tools like queuing models in most cases only hold in mean value analysis under the assumption of simplified traffic structures. In this paper, we present a filter model to characterize the relationship among the factors of server capacity, request scheduling, and service quality for general input traffic. By the model, a server scheduler operates as an finite-duration impulse response (FIR) filter that transforms request processes into workload processes with the objective of minimizing load variation or overload probability, and meanwhile, without violating request response deadlines as defined in service-level agreements. We present a design and analysis of the filter for traffic with strong LRD in the frequency domain. Most Internet traffic has monotonically decreasing strength of variation functions over frequency. For this type of input traffic, we prove that optimal schedulers must have a convex structure. Uniform resource allocation is an extreme case of the convexity and is proved to be optimal for Poisson traffic. We integrate the convex structural principle with the Generalized Processor Sharing (GPS) discipline and show that the enhanced GPS policy improves the service quality significantly. Furthermore, we show that the presence of LRD in the input traffic results in shift of variation strength from high frequency to lower frequency bands and consequently leads to a degradation of the service quality. [ABSTRACT FROM PUBLISHER]

Similarity among vectors is basic knowledge required to carry out recommendation and classification in recommender systems, which support personalized recommendation during online interactions. In this paper, we propose a Semi-sparse Algorithm based on Multi-layer Optimization to speed up the Pearson Correlation Coefficient, which is conventionally used in obtaining similarity among sparse vectors. In accelerating the batch of similarity-comparisons within one thread, the semi-sparse algorithm spares out over-reduplicated accesses and judgements on the selected sparse vector by making this vector dense locally. Moreover, a reduce-vector is proposed to restrict using locks on critical resources in the thread-pool, which is wrapped with Pthreads on a multi-core node to improve parallelism. Furthermore, among processes in our framework, a shared zip file is read to cut down messages within the Message Passing Interface package. Evaluation shows that the optimized multi-layer framework achieves a brilliant speedup on three benchmarks, Netflix, MovieLens and MovieLen1600. [ABSTRACT FROM AUTHOR]

Abstract: According to the pay-per-use model adopted in clouds, the more resources an application running in a cloud computing environment consumes, the greater the amount of money the owner of the corresponding application will be charged. Therefore, applying intelligent solutions to minimize the resource consumption is of great importance. In this paper, we study the problem of identifying an assignment scheme between the interacting components of an application, such as processes and virtual machines, and the computing nodes of a cloud system, such that the total amount of resources consumed by the respective application is minimized. Because centralized solutions are deemed unsuitable for large distributed systems or large-scale applications, we propose a fully distributed algorithm (called DRA) to overcome scalability issues. DRA takes decisions concerning the transition from one assignment scheme to another in a dynamic way, based solely on local information. We also propose and test two modifications of the basic DRA algorithm to deal better with the heterogeneity of cloud servers in terms of capacity constraints. We must note that we capture heterogeneity regarding the network model. Through theoretical analysis, we formally prove that DRA achieves convergence and always provides an optimal solution for tree-based networks in the uncapacitated case. Moreover, we prove through experimental evaluation that DRA achieves up to 55% network cost reduction when compared to the most recent algorithm in the literature. We also show that the proposed modifications of DRA improve the algorithm’s performance considerably in the case where servers have limited capacity. [Copyright &y& Elsevier]

With automated driving forthcoming, lane-changing for Connected and Automated Vehicles (CAVs) has received wide attention. The main challenge is that lane-changing requires not only local CAV control but also interactions with the surrounding traffic. Nevertheless, the Line-of-Sight (LoS) sensing range of the CAVs imposes severe limitations on lane-changing safety, and the lane-changing decision that is made based only on self-interest ignores its impact on the traffic flow efficiency. To overcome these difficulties, this article proposes a Digital Twin (DT) empowered mobile edge computing (MEC) architecture. With MEC, the sensing and computing capabilities of the CAVs can be strengthened to guarantee real-time safety. The virtualization and offline learning capabilities of the DT can be leveraged to enable the CAVs to learn from the experience of the physical MEC network and make lane-changing decisions via a ‘foresight intelligent’ approach. A case study of lane-changing is provided where the DT is constituted by a cellular automata based road traffic simulator coupled with a LTE-V based MEC network simulator. Deep reinforcement learning is adopted to train the lane-changing strategy and results validate the effectiveness of our proposed architecture. [ABSTRACT FROM AUTHOR]

Live migration of virtual machine (VM) provides a significant benefit for virtual server mobility without disrupting service. It is widely used for system management in virtualized data centers. However, migration costs may vary significantly for different workloads due to the variety of VM configurations and workload characteristics. To take into account the migration overhead in migration decision-making, we investigate design methodologies to quantitatively predict the migration performance and energy consumption. We thoroughly analyze the key parameters that affect the migration cost from theory to practice. We construct application-oblivious models for the cost prediction by using learned knowledge about the workloads at the hypervisor (also called VMM) level. This should be the first kind of work to estimate VM live migration cost in terms of both performance and energy in a quantitative approach. We evaluate the models using five representative workloads on a Xen virtualized environment. Experimental results show that the refined model yields higher than 90% prediction accuracy in comparison with measured cost. Model-guided decisions can significantly reduce the migration cost by more than 72.9% at an energy saving of 73.6%. [ABSTRACT FROM AUTHOR]

Cloud computing has a key requirement for resource configuration in a real-time manner. In such virtualized environments, both virtual machines (VMs) and hosted applications need to be configured on-the-fly to adapt to system dynamics. The interplay between the layers of VMs and applications further complicates the problem of cloud configuration. Independent tuning of each aspect may not lead to optimal system wide performance. In this paper, we propose a framework, namely CoTuner, for coordinated configuration of VMs and resident applications. At the heart of the framework is a model-free hybrid reinforcement learning (RL) approach, which combines the advantages of Simplex method and RL method and is further enhanced by the use of system knowledge guided exploration policies. Experimental results on Xen-based virtualized environments with TPC-W and TPC-C benchmarks demonstrate that CoTuner is able to drive a virtual server cluster into an optimal or near-optimal configuration state on the fly, in response to the change of workload. It improves the systems throughput by more than 30 percent over independent tuning strategies. In comparison with the coordinated tuning strategies based on basic RL or Simplex algorithm, the hybrid RL algorithm gains 25 to 40 percent throughput improvement. [ABSTRACT FROM PUBLISHER]

Ensemble learning is a widely used technique to train deep convolutional neural networks (CNNs) for improved robustness and accuracy. While existing algorithms usually first train multiple diversified networks and then assemble these networks as an aggregated classifier, we propose a novel learning paradigm, namely, "In-Network Ensemble" (INE) that incorporates the diversity of multiple models through training a SINGLE deep neural network. Specifically, INE segments the outputs of the CNN into multiple independent classifiers, where each classifier is further fine-tuned with better accuracy through a so-called diversified knowledge distillation process. We then aggregate the fine-tuned independent classifiers using an Averaging-and-Softmax operator to obtain the final ensemble classifier. Note that, in the supervised learning settings, INE starts the CNN training from random, while, under the transfer learning settings, it also could start with a pre-trained model to incorporate the knowledge learned from additional datasets. Extensive experiments have been done using eight large-scale real-world datasets, including CIFAR, ImageNet, and Stanford Cars, among others, as well as common deep network architectures such as VGG, ResNet, and Wide ResNet. We have evaluated the method under two tasks: supervised learning and transfer learning. The results show that INE outperforms the state-of-the-art algorithms for deep ensemble learning with improved accuracy. [ABSTRACT FROM AUTHOR]

Scalability of distributed deep learning (DL) training with parameter server (PS) architecture is often communication constrained in large clusters. There are recent efforts that use a layer by layer strategy to overlap gradient communication with backward computation so as to reduce the impact of communication constraint on the scalability. However, the approaches could bring significant overhead in gradient communication. Meanwhile, they cannot be effectively applied to the overlap between parameter communication and forward computation. In this article, we propose and develop iPart, a novel approach that partitions communication and computation in various partition sizes to overlap gradient communication with backward computation and parameter communication with forward computation. iPart formulates the partitioning decision as an optimization problem and solves it based on a greedy algorithm to derive communication and computation partitions. We implement iPart in the open-source DL framework BigDL and perform evaluations with various DL workloads. Experimental results show that iPart improves the scalability of a cluster of 72 nodes by up to 94 percent over the default PS and 52 percent over the layer by layer strategy. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction plays an important role in guaranteeing safe operation and reducing maintenance cost in modern industry. In this paper, we present a novel deep learning method for RUL estimation based on time empirical mode decomposition (EMD) and temporal convolutional networks (TCN). The proposed framework can effectively reveal the non-stationary characteristics of bearing degradation signals and acquire time-series degradation signals which namely intrinsic mode functions through empirical mode decomposition. Furthermore, the feature information is used as the input to convolution layer and trained by TCN to predict remaining useful life. The proposed EMD–TCN model structure maintains a superior result compared to several state-of-the-art convolutional algorithms on public data sets. Experimental results show that the average score of EMD–TCN model is improved by 10–20% than traditional convolutional algorithms. [ABSTRACT FROM AUTHOR]

Abstract Minimizing energy consumption and network load is a major challenge for network-on-chip (NoC) based multi-processor systems-on-chip (MPSoCs). Efficient task and core mapping can greatly reduce the overall energy consumption and communication overhead among the interdependent tasks. In this paper, we propose a novel Knapsack based bin packing algorithm for workload consolidation that places tasks in such a manner that utilization of available processing elements is maximized, while network overhead, regarding the communication among the tasks, is minimized. We also propose a task swapping algorithm that attempts to further optimize the task placement produced by the bin packing algorithms. Moreover, several core mapping techniques are implemented and the performance of each technique is evaluated under varying configurations. In addition, we also apply a Pareto-efficient algorithm, on top of the bin packing algorithms, attempting to explore the solution in two dimensions, i.e., energy consumption and network load. The experimental results show that the proposed Knapsack based bin packing algorithm coupled with the Pareto-efficient algorithm achieves significant energy savings and reduction in network load as compared to state-of-the-art algorithms, as well as the greedy algorithm. Particularly, the Pareto-efficient algorithm when applied on top of the Knapsack algorithm shows on average 50% and 55% reduction in energy consumption and network load as compared to the greedy algorithm, respectively. While the proposed Pareto-efficient algorithm applied with Knapsack algorithm also demonstrate superior performance compared to three other state-of-the-art heuristics. Highlights • Introduce a new class of bin packing problem, i.e., variable benefit bin packing. • A Knapsack based bin packing algorithm is proposed for workload consolidation. • Proposed Knapsack algorithm reduces both energy consumption and network load. • Various mapping heuristics are proposed to map the bins onto cores of MPSoC. • Pareto-efficient algorithm to explore solutions in two dimensions simultaneously. [ABSTRACT FROM AUTHOR]

In virtualization environments, static memory allocation for virtual machines (VMs) can lead to severe service level agreement (SLA) violations or inefficient use of memory. Dynamic memory allocation mechanisms such as ballooning and memory hotplug were proposed to handle the dynamics of memory demands. However, these mechanisms so far have not been quantitatively or comparatively studied. In this paper, we first develop a runtime system called U-tube, which provides a framework to adopt memory hotplug or ballooning for dynamic memory allocation. We then implement fine-grained memory hotplug in Xen. We demonstrate the effectiveness of U-tube for dynamic memory management through two case studies: dynamic memory balancing and memory overcommitment. With these two case studies, we make a quantitative comparison between memory hotplug and ballooning. The experiments show that there is no absolute winner for different scenarios. Our findings can be very useful for practitioners to choose the suitable dynamic memory management techniques in different scenarios. [ABSTRACT FROM AUTHOR]

In the large-scale parallel computing environment, resource allocation and energy efficient techniques are required to deliver the quality of services (QoS) and to reduce the operational cost of the system. Because the cost of the energy consumption in the environment is a dominant part of the owner's and user's budget. However, when considering energy efficiency, resource allocation strategies become more difficult, and QoS (i.e., queue time and response time) may violate. This paper therefore is a comparative study on job scheduling in large-scale parallel systems to: (a) minimize the queue time, response time, and energy consumption and (b) maximize the overall system utilization. We compare thirteen job scheduling policies to analyze their behavior. A set of job scheduling policies includes (a) priority-based, (b) first fit, (c) backfilling, and (d) window-based policies. All of the policies are extensively simulated and compared. For the simulation, a real data center workload comprised of 22385 jobs is used. Based on results of their performance, we incorporate energy efficiency in three policies i.e., (1) best result producer, (2) average result producer, and (3) worst result producer. We analyze the (a) queue time, (b) response time, (c) slowdown ratio, and (d) energy consumption to evaluate the policies. Moreover, we present a comprehensive workload characterization for optimizing system's performance and for scheduler design. Major workload characteristics including (a) Narrow, (b) Wide, (c) Short, and (d) Long jobs are characterized for detailed analysis of the schedulers' performance. This study highlights the strengths and weakness of various job scheduling polices and helps to choose an appropriate job scheduling policy in a given scenario. [ABSTRACT FROM AUTHOR]

Recent embedded middleware platforms enable the structuring of an application as a set of collaborating agents deployed on various nodes of the underlying wireless sensor network (WSN). Of particular importance is the network cost incurred due to agent communication, which in turn depends on how the agents are placed within the WSN system. In this paper, we present two agent migration algorithms with the aim of minimizing the total network overhead. The first one takes independent single agent migration decisions, while the second one considers groups of agents for migration. Both algorithms work in a fully distributed fashion based on the knowledge available locally at each node, and can be used both for one-shot initial application deployment as well as for the continuous updating of agent placement. We also propose two methodologies to tackle the problem when WSN nodes have limited capacity. We show through theoretical analysis that one of our algorithms (called GRAL\ast) always results in an optimal placement, while for the rest of the algorithms, we derive approximation ratios pertaining to their performance. We evaluate the performance of our algorithms through a series of simulation experiments. Results show that group migration algorithms are superior compared to single agent migration algorithms with the performance difference reaching 34% for some settings. [ABSTRACT FROM AUTHOR]

Highlights: [•] Classification of high performance computing (HPC) systems is provided. [•] Current HPC paradigms and industrial application suites are discussed. [•] State of the art in HPC resource allocation is reported. [•] Hardware and software solutions are discussed for optimized HPC systems. [Copyright &y& Elsevier]

With the mushroom growth of state‐of‐the‐art digital image and video manipulations tools, establishing the authenticity of multimedia content has become a challenging issue. Digital image forensics is an increasingly growing research field that symbolises a never ending struggle against forgery and tampering. This survey attempts to cover the blind techniques that have been proposed for exposing forgeries. This work dwells on the detection techniques for three of the most common forgery types, namely copy/move, splicing and retouching. [ABSTRACT FROM AUTHOR]

The mobile agent paradigm has been adopted by several systems in the area of wireless sensor networks as it enables a flexible distribution and placement of application components on nodes, at runtime. Most agent placement and migration algorithms proposed in the literature, assume that the communication rates between agents remain stable for a sufficiently long time to amortize the migration costs. Then, the problem is that frequent changes in the application-level communication may lead to several non-beneficial agent migrations, which may actually increase the total network cost, instead of decreasing it. To tackle this problem, we propose two distributed algorithms that take migration decisions in an online fashion, trying to deal with fluctuations in agent communication. The first algorithm is more of theoretical value, as it assumes infinite storage to keep information about the message exchange history of agents, while the second algorithm is a refined version that works with finite storage and limited information. We describe these algorithms in detail, and provide proofs for their competitive ratio vs. an optimal oracle. In addition, we evaluate the performance of the proposed algorithms for different parameter settings through a series of simulated experiments, also comparing their results with those achieved by an optimal static placement that is computed with full (a posteriori) knowledge of the execution scenarios. Our theoretical and experimental results are a strong indication for the robustness and effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Two major constraints demand more consideration for energy efficiency in cluster computing: (a) operational costs, and (b) system reliability. Increasing energy efficiency in cluster systems will reduce energy consumption, excess heat, lower operational costs, and improve system reliability. Based on the energy-power relationship, and the fact that energy consumption can be reduced with strategic power management, we focus in this survey on the characteristic of two main power management technologies: (a) static power management (SPM) systems that utilize low-power components to save the energy, and (b) dynamic power management (DPM) systems that utilize software and power-scalable components to optimize the energy consumption. We present the current state of the art in both of the SPM and DPM techniques, citing representative examples. The survey is concluded with a brief discussion and some assumptions about the possible future directions that could be explored to improve the energy efficiency in cluster computing. [ABSTRACT FROM AUTHOR]

With the rapid development of blockchain technology, the cross-blockchain asset transfer has been in great demand. However, most existing cross-blockchain solutions encounter low efficiency problems due to the centralized features, unfriendly development environment, and difficulty in cooperation. This paper proposes an interaction protocol for secure and efficient cross-blockchain transfer process, wherein the cross-blockchain asset transfer is modeled as an auction process. We design our protocol by leveraging the atomic swap technology and Vickrey auction scheme to achieve efficient cross-blockchain asset transfer, without sacrificing the decentralized control. To achieve the transfer efficiency, we optimize the Vickrey auction scheme to share data within the auction and delivery process synchronously. This results in a efficient user information exchange. The experimental results show that not only can our protocol achieve compatibility, but it also incurs little communication overhead in high throughput. A cross-blockchain transfer process can be accomplished in average 4 rounds of interaction. The difference between the transaction completion time and the bid waiting time is less than 1 second. Besides, our protocol guarantees the exchange rate at a reasonable range. The ratio of the cross-blockchain exchange rate to the real exchange rate converges to 0.9 for approximately 200 participants. The transaction fee decreases sharply with the increase of the number of auction participants. [ABSTRACT FROM AUTHOR]

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (K nowledge S haring D eep D eterministic P olicy G radient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden. • A multi-agent reinforcement learning for adaptive signal control. • Agents can communicate with others through knowledge-sharing protocol. • Proposed algorithm achieves consistent improvements over baselines. [ABSTRACT FROM AUTHOR]

The nineteen papers in this special issue focus on the development and applications of cyber-physical systems. These systems refer to the tight link between computational, virtual, and physical resources that drive the potential of having a pervasive effect in the citizens everyday life. Cyber-physical systems find direct applicability in a wide range of areas and disciplines, and promise to transform our world with systems that will far exceed those of today in terms of: effectiveness, adaptability, energy efficiency, precision, reliability, and safety. [ABSTRACT FROM AUTHOR]

Live migration of virtual machines (VM) across physical hosts provides a significant new benefit for administrators of data centers and clusters. Previous memory-to-memory approaches demonstrate the effectiveness of live VM migration in local area networks (LAN), but they would cause a long period of downtime in a wide area network (WAN) environment. This paper describes the design and implementation of a novel approach, namely, CR/TR-Motion, which adopts checkpointing/recovery and trace/replay technologies to provide fast, transparent VM migration for both LAN and WAN environments. With execution trace logged on the source host, a synchronization algorithm is performed to orchestrate the running source and target VMs until they reach a consistent state. CR/TR-Motion can greatly reduce the migration downtime and network bandwidth consumption. Experimental results show that the approach can drastically reduce migration overheads compared with memory-to-memory approach in a LAN: up to 72.4 percent on application observed downtime, up to 31.5 percent on total migration time, and up to 95.9 percent on the data to synchronize the VM state. The application performance overhead due to migration is kept within 8.54 percent on average. The results also show that for a variety of workloads migrated across WANs, the migration downtime is less than 300 milliseconds. [ABSTRACT FROM PUBLISHER]