Performance Degradation Of Applications Research Articles

Text Enhancement Network for Cross-Domain Scene Text Detection

Conventional scene text detection approaches essentially assume that training and test data are drawn from the same distribution and have achieved compelling results. However, scene text detectors often suffer from performance degradation in real-world applications, since the feature distribution of training images is different from that of test images obtained from a new scene. To address the above problems, we propose a novel method called Text Enhancement Network (TEN) based on adversarial learning for cross-domain scene text detection. Specifically, we first design a Multi-adversarial Feature Alignment (MFA) module to maximally align features of the source and target data from low-level texture to high-level semantics. Second, we develop the Text Attention Enhancement (TAE) module to re-weigh the importance of text regions and accordingly enhance the corresponding features, in order to improve the robustness against noisy background. Additionally, we design a self-training strategy to further boost the performance of our TEN. We conduct extensive experiments on five benchmarks, and the experimental results demonstrate the effectiveness of our TEN.

SDCBench: A Benchmark Suite for Workload Colocation and Evaluation in Datacenters

Colocating workloads are commonly used in datacenters to improve server utilization. However, the unpredictable application performance degradation caused by the contention for shared resources makes the problem difficult and limits the efficiency of this approach. This problem has sparked research in hardware and software techniques that focus on enhancing the datacenters’ isolation abilities. There is still lack of a comprehensive benchmark suite to evaluate such techniques. To address this problem, we present SDCBench, a new benchmark suite that is specifically designed for workload colocation and characterization in datacenters. SDCBench includes 16 applications that span a wide range of cloud scenarios, which are carefully selected from the existing benchmarks using the clustering analysis method. SDCBench implements a robust statistical methodology to support workload colocation and proposes a concept of latency entropy for measuring the isolation ability of cloud systems. It enables cloud tenants to understand the performance isolation ability in datacenters and choose their best-fitted cloud services. For cloud providers, it also helps them to improve the quality of service to increase their revenues. Experimental results show that SDCBench can simulate different workload colocation scenarios by generating pressures on multidimensional resources with simple configurations. We also use SDCBench to compare the latency entropies in public cloud platforms such as Huawei Cloud and AWS Cloud and a local prototype system FlameCluster-II; the evaluation results show FlameCluster-II has the best performance isolation ability over these three cloud systems, with 0.99 of experience availability and 0.29 of latency entropy.

HMGOWM: A Hybrid Decision Mechanism for Automating Migration of Virtual Machines

Large-scale data centers have been widely used for cloud services, and the stability of various cloud services has received additional attention from users. Although service disruptions are not as catastrophic as they once were, their impact might be more extensive than before. These outages may trigger the migration of virtual machines (VMs) located in the failure node. However, the access time of each VM is random, unlike the accident time, which can be predicted. This means that traditional migration caused by service interruptions may result in a large number of unwanted migrations, regardless of the user’s downtime experience. Migration is an expensive process in terms of the resources needed as well as the degradation of application performance during migration. A balance between the recovery time of the service (to minimize the migration resulting from a given placement) and the downtime experience of the users (to minimize the impact of access interruptions) is needed. In this paper, we propose HMGOWM, a hybrid decision-making mechanism for automating the migration of VMs. Our proposed mechanism extends the original VM migration performance cost model, greatly reducing the downtime experience of the users. To achieve high performance and a good load balance, a multi-objective monitoring system for both VMs and physical machine nodes and an adaptive VM migration-scheduling scheme for the OpenStack cloud platform are proposed. Extensive experiment results indicate that the downtime experienced by users can be efficiently reduced and that the implementation of HMGOWM outperforms the original scheduling of the OpenStack cloud platform.

Precise Power Capping for Latency-Sensitive Applications in Datacenter

Power capping is widely used in cloud datacenters to mitigate power over-provisioning problem, thus improve datacenter capacity and cut off their operation cost. However, inappropriate or aggressive power capping may lead to performance degradation of applications (especially latency-sensitive ones), and there are few effective methods that can accurately evaluate and control such negative impact caused by aggressive power capping. In this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Fine-Grained Differential Method</i> (FGD) to quantitatively analyze how inappropriate power capping degrades the performance of latency-sensitive applications. By using FGD, we can minimize the provisioned power for each server by setting a precise power budget according to application’s <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Service Level Agreement</i> (SLA). And we further propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Precise Power Capping</i> (PPCapping) which is designed to increase the datacenter capacity with a fixed power supply by means of FGD. Our research also provides an insight of precise tradeoff between applications’ SLAs and datacenter capacity. We verify FGD and PPCapping by using real world traces from Tencent’s datecenter with 25,328 servers. The experimental results show that FGD can accurately analyze the impact of power capping on the performance of latency-sensitive applications, and PPCapping can effectively increase datacenter capacity compared with the typical power provisioning strategy.

Empirical power consumption characterization and energy aware scheduling in data centers

Energy-efficient management is key to reduce operational cost and environmental contamination in modern data centers. Energy management and renewable energy utilization are strategies to optimize energy consumption in high-performance computing. In any case, understanding the power consumption behavior of physical servers in datacenter is fundamental to implement energy-aware policies effectively. These policies should deal with possible performance degradation of applications to ensure quality of service. This manuscript presents an empirical evaluation of power consumption for scientific computing applications in multicore systems. Three types of applications are studied, in single and combined executions on Intel and AMD servers, for evaluating the overall power consumption of each application. The main results indicate that power consumption behavior has a strong dependency with the type of application. Additional performance analysis shows that the best load of the server regarding energy efficiency depends on the type of the applications, with efficiency decreasing in heavily loaded situations. These results allow formulating models to characterize applications according to power consumption, efficiency, and resource sharing, which provide useful information for resource management and scheduling policies. Several scheduling strategies are evaluated using the proposed energy model over realistic scientific computing workloads. Results confirm that strategies that maximize host utilization provide the best energy efficiency.

Effects of acoustic nonlinearity on through-tissue communication performance

Wide signal bandwidth and high signal amplitude, which are desirable properties to achieve high data rates with linear communication systems, may cause performance degradation in through-tissue communication applications because of acoustic nonlinearity. In this talk, I will quantify the effects of acoustic nonlinearity on data rates and achievable bit error rates in a simulated through-tissue communication system.

Achieving Fine-Grained Flow Management Through Hybrid Rule Placement in SDNs

Fine-grained flow management is useful in many practical applications, e.g., resource allocation, anomaly detection and traffic engineering. However, it is difficult to provide fine-grained management for a large number of flows in SDNs due to switches’ limited flow table capacity. While using wildcard rules can reduce the number of flow entries needed, it cannot fully ensure fine-grained management for all the flows without degrading application performance. In this article, we design and implement hybrid rule placement for fine-grained flow management (to be referred to as HiFi here after). HiFi achieves fine-grained management with a minimal number of flow entries through taking a two-step approach: wildcard entry installment and application-specific exact-match entry installment. How to optimally install wildcard and exact-match flow entries, however, is intractable. Therefore, we design approximation algorithms with bounded factors to solve these problems. We consider how to achieve network-wide load balancing via fine-grained flow management as a case study. Both experiment on a testbed built with open virtual switches and extensive simulation show that HiFi can reduce the number of required flow entries by about 45-69 percent and reduce the control overhead by about 28-50 percent compared with the state-of-the-art approaches for achieving fine-grained flow management.

Improving SD-WAN Resilience: From Vertical Handoff to WAN-Aware MPTCP

Demands for wide-area connectivity between enterprise site-edge networks and central office core networks/cloud data centers have grown rapidly. Various software defined wide area network (SD-WAN) solutions have been developed with the primary aim of improving WAN link utilization. However, mechanisms used by existing SD-WAN solutions fail to provide high reliability and performance required by today's edge to cloud applications. In this article, we present WAN-aware MPTCP which seamlessly aggregates multiple WAN links into a “big pipe” for better WAN resilience thus minimizing application performance degradation under WAN link failures. We leverage the congestion control of MPTCP to balance traffic across multiple WAN links. The key innovation is to combine LAN virtualization at end systems with WAN virtualization at SD-WAN gateways. Through evaluation in both emulated testbeds and real-world deployment, we demonstrate the performance gain of WAN-aware MPTCP in terms of resilience and throughput over existing SD-WAN solutions.

Error-robust low-rank tensor approximation for multi-view clustering

Multi-view clustering has been widely developed to improve the clustering performance over that of single-view clustering. However, the types of errors vary and behave inconsistently in each view, which results in performance degradation in real applications. To address this limitation, in this paper, we propose a novel Markov chain-based spectral clustering method for multi-view clustering to handle different types of errors. Unlike most of the existing self-representation-based subspace clustering methods, which process each view separately, ignoring complementary information among views, our method first computes the transition probability matrices of all views, then forms each transition probability matrix as a frontal slice of a third-order tensor to capture the multi-view information, and finally decomposes the tensor into an ideal tensor with the tensor nuclear norm constraint and an error term. Furthermore, the proposed method imposes the group l1 and l2,1 norms on the error matrix for error learning such that various errors can be clearly characterized and processed to improve performance. To solve the challenging optimization model, we propose an efficient algorithm using the augmented Lagrangian multiplier method. Experimental results on three real-world datasets show that the proposed method is superior to the state-of-the art methods in various evaluation metrics.

Performance-Energy Trade-off in Modern CMPs

Chip multiprocessors (CMPs) are ubiquitous in all computing systems ranging from high-end servers to mobile devices. In these systems, energy consumption is a critical design constraint as it constitutes the most significant operating cost for computing clouds. Analogous to this, longer battery life continues to be an essential user concern in mobile devices. To optimize on power consumption, modern processors are designed with Dynamic Voltage and Frequency Scaling (DVFS) support at the individual core as well as the uncore level. This allows fine-grained control of performance and energy. For an n core processor with m core and uncore frequency choices, the total DVFS configuration space is now m (n+1) (with the uncore accounting for the + 1). In addition to that, in CMPs, the performance-energy trade-off due to core/uncore frequency scaling concerning a single application cannot be determined independently as cores share critical resources like the last level cache (LLC) and the memory. Thus, unlike the uni-processor environment, the energy consumption of an application running on a CMP depends not only on its characteristics but also on those of its co-runners (applications running on other cores). The key objective of our work is to select a suitable core and uncore frequency that minimizes power consumption while limiting application performance degradation within certain pre-defined limits (can be termed as QoS requirements). The key contribution of our work is a learning-based model that is able to capture the interference due to shared cache, bus bandwidth, and memory bandwidth between applications running on multiple cores and predict near-optimal frequencies for core and uncore.

Exploiting Data Resilience in Wireless Network-on-chip Architectures

The emerging wireless Network-on-Chip (WiNoC) architectures are a viable solution for addressing the scalability limitations of manycore architectures in which multi-hop long-range communications strongly impact both the performance and energy figures of the system. The energy consumption of wired links as well as that of radio communications account for a relevant fraction of the overall energy budget. In this article, we extend the approximate computing paradigm to the case of the on-chip communication system in manycore architectures. We present techniques, circuitries, and programming interfaces aimed at reducing the energy consumption of a WiNoC by exploiting the trade-off energy saving vs. application output degradation. The proposed platform—namely, xWiNoC—uses variable voltage swing links and tunable transmitting power wireless interfaces along with a programming interface that allows the programmer to specify those data structures that are error-resilient. Thus, communications induced by the access to such error-resilient data structures are carried out by using links and radio channels that are configured to work in a low energy mode, albeit by exposing a higher bit error rate. xWiNoC is assessed on a set of applications belonging to different domains in which the trade-off energy vs. performance vs. application result quality is discussed. We found that up to 50% of communication energy saving can be obtained with a negligible impact on the application output quality and 3% in application performance degradation.

Fine Tuning of Rank Based VM Placement and Scheduling Strategies on Opennebula Based Cloud

The HPC Clouds are good option over deploying actual physical infrastructure. This helps in running applications efficiently and in cost effective manner as applications leverage resources in pay as you go manner. But HPC clouds suffer performance issues due to Hypervisor layer. This work addresses the issue by coming up with a VM placement strategy considering the intensity of the applications and also resources available in the host machines and avoid performance degradation of parallel running applications. This placement strategy identifies the and ranks the available host machines and places the maximum possible VMs in highest ranking nodes. This avoids communication over the network since the VMs use shared memory for communication.

Job placement using reinforcement learning in GPU virtualization environment

Graphics Processing Units (GPU) are widely used for high-speed processes in the computational science areas of biology, chemistry, meteorology, etc. and the machine learning areas of image and video analysis. Recently, data centers and cloud companies have adopted GPUs to provide them as computing resources. Because the majority of cloud providers allocate the GPU resource to users in an exclusive access method, the allocated GPU resource may not be all used. Although the method of allocating a GPU resource to multiple users for sharing can increase the resource utilization, performance degradation may occur in individual jobs because of interference between different jobs. It is difficult for a cloud provider to predict or control the performance of various applications executed on various cloud resources by considering their characteristics heuristically. Therefore, an intelligent job placement technique is required to minimize the interference between different jobs and increase resource utilization. This study defines the resource utilization history of applications and proposes a reinforcement learning-based job placement technique, which uses it as an input. For resource utilization history learning, a deep reinforcement learning model (DQN) is used. As a result of learning, the current resource’s state is not exceeded, and the resource is still provided by predicting which commonly placed jobs will have less impact on the total performance when executed simultaneously. This approach prevents the performance degradation of applications with diverse execution characteristics and increases the resource utilization by executing the applications while sharing the resources. The superiority of this study is demonstrated by using the proposed learning method and other methods to analyze workloads with various resource utilization characteristics. Through the experiments, it is proven that the proposed method facilitates a reduction of the total execution time and the effective use of resources, while the maintaining performance.

Joint Optimization of Computation Offloading and Task Scheduling in Vehicular Edge Computing Networks

Resource-intensive applications on smart vehicles is posing difficulties to the use of traditional cloud computing for computation offloading in vehicular networks. In particular, the long transmission distance between the vehicles and the cloud center can cause high latency and poor reliability which may degrade application performance and quality of service. As an integration of mobile edge computing and vehicular networks, vehicular edge computing is a promising paradigm that aims to improve vehicular services by performing computation offloading in close proximity to vehicles. In this paper, the task offloading algorithm that efficiently optimizes task delay and computing resource consumption in multi-user, multi-server vehicular edge computing scenarios is studied. The offloading algorithm not only determines where the tasks are performed, but also indicates the execution order of the tasks on the server. In order to reduce the time complexity, this paper proposes a hybrid intelligent optimization algorithm based on partheno genetic algorithm and heuristic rules. Extensive simulations are conducted, and the results show that compared with the baseline algorithms, the proposed algorithm effectively improves the offloading utility of the VEC system and is suitable for task offloading in various situations.

On Learning Spectral Masking for Single Channel Speech Enhancement Using Feedforward and Recurrent Neural Networks

Human speech in real-world environments is typically degraded by the background noise. They have a negative impact on perceptual speech quality and intelligibility which causes performance degradation in various speech-related technological applications, such as hearing aids and automatic speech recognition systems. It also degrades the original phase of the clean speech and introduces perceptual disturbance which leads to the negative impacts on the quality of speech. Therefore, speech enhancement must vigilantly be dealt with in everyday listening environments. In this article, speech enhancement is performed using supervised learning of spectral masking. Deep neural networks (DNN) and recurrent neural networks (RNN) are trained to learn the spectral masking from the magnitude spectrograms of the degraded speech. An iterative procedure is adopted as a post-processing step to deal with the noisy phase. Additionally, an intelligibility improvement filter is also used to incorporate the critical band importance function weights where higher weights contribute more towards intelligibility. Systematic experiments demonstrated that the proposed approaches greatly attenuated the background noise. Also, they led to large improvements of the perceived speech quality and intelligibility, as well as automatic speech recognition. In experiments, TIMIT database is used. The STOI is improved by 17.6% over the noisy speech. Also, SDR and PESQ are improved by 5.22dB and 19% over the noisy speech utterances. These comparisons showed that the proposed speech enhancement approaches outperformed the related speech enhancement methods.

An Adaptive and Fuzzy Resource Management Approach in Cloud Computing

Resource management plays a key role in the cloud-computing environment in which applications face with dynamically changing workloads. However, such dynamic and unpredictable workloads can lead to performance degradation of applications, especially when demands for resources are increased. To meet Quality of Service (QoS) requirements based on Service Level Agreements (SLA), resource management strategies must be taken into account. The question addressed in this research includes how to reduce the number of SLA violations based on the optimization of resources allocated to users applying an autonomous control cycle and a fuzzy knowledge management system. In this paper, an adaptive and fuzzy resource management framework (AFRM) is proposed in which the last resource values of each virtual machine are gathered through the environment sensors and are sent to a fuzzy controller. Then, AFRM analyzes the received information to make decision on how to reallocate the resources in each iteration of a self-adaptive control cycle. All the membership functions and rules are dynamically updated based on workload changes to satisfy QoS requirements. Two sets of experiments were conducted on the storage resource to examine AFRM in comparison to rule-based and static-fuzzy approaches in terms of RAE, utility, number of SLA violations, and cost applying HIGH, MEDIUM, MEDIUM-HIGH, and LOW workloads. The results reveal that AFRM outweighs the rule-based and static-fuzzy approaches from several aspects.

Sentinel: Failure Recovery in Centralized Traffic Engineering

Network failures are common in wide area networks (WANs). Failure recovery in a software-defined WAN takes minutes or longer, as the controller needs to calculate a new traffic engineering solution and update the forwarding rules across all switches. This severely degrades application performance. Existing reactive and proactive approaches inevitably lead to transient congestion or bandwidth underutilization and impair the efficiency of running the expensive WANs. We present Sentinel, a novel failure recovery system for traffic engineering in software-defined WANs. Sentinel pre-computes and installs backup tunnels to accelerate failure recovery. When a link fails, switches locally redirect traffic to backup tunnels and recover immediately in the data plane, thus substantially reducing the transient congestion compared to reactive rescaling. On the other hand, Sentinel completely avoids the bandwidth headroom required by existing proactive approaches. Extensive experiments on Mininet and numerical simulations show that similar to state-of-the-art FFC, Sentinel reduces congestion by 45% compared with rescaling, and its algorithm runs much faster than FFC. Sentinel only introduces a small number of additional forwarding rules and can be readily implemented on today’s Openflow switches.

SciSpace: A scientific collaboration workspace for geo-distributed HPC data centers

Abstract Future terabit networks are committed to dramatically improving big data motion between geographically dispersed HPC data centers. The scientific community takes advantage of the terabit networks such as DOE’s ESnet and accelerates the trend to build a small world of collaboration between geospatial HPC data centers. It improves information and resource sharing for joint simulation and analysis between the HPC data centers. However, there exist several challenges for effective collaborations such as a collective view of multi-site shared data, minimal performance degradation of scientific applications running in a such collaboration environments and critical of all, data sharing policies in such collaborations. In this paper, we propose to build SciSpace , Scientific Collaboration Workspace for collaborative data centers. It provides a global view of information shared from multiple geo-distributed HPC data centers under a single workspace. SciSpace supports native data-access to gain high-performance when data read or write is required in native data center namespace. It is accomplished by integrating an on-demand metadata export protocol. To optimize scientific collaborations across HPC data centers, SciSpace implements search and discovery service. To evaluate, we configured two geo-distributed small-scale HPC data centers connected via high-speed Infiniband network such as terabits network of DOE’s ESnet, equipped with LustreFS. We show the feasibility of SciSpace using real scientific datasets and applications. The evaluation results show average 36% performance boost when the proposed native-data access is employed in collaborations. We also emulate a real climate science collaboration to validate the usefulness of SciSpace .

How File-access Patterns Influence the Degree of I/O Interference between Cluster Applications

On large-scale clusters, tens to hundreds of applications can simultaneously access a parallel file system, leading to contention and, in its wake, to degraded application performance. In this article, we analyze the influence of file-access patterns on the degree of interference. As it is by experience most intrusive, we focus our attention on write-write contention. We observe considerable differences among the interference potentials of several typical write patterns. In particular, we found that if one parallel program writes large output files while another one writes small checkpointing files, then the latter is slowed down when the checkpointing files are small enough and the former is vice versa. Moreover, applications with a few processes writing large output files already can significantly hinder applications with many processes from checkpointing small files. Such effects can seriously impact the runtime of real applications—up to a factor of five in one instance. Our insights and measurement techniques offer an opportunity to automatically classify the interference potential between applications and to adjust scheduling decisions accordingly.

Adaptive beamforming with unknown scattering coefficients of near‐field scatterers

Conventionally, near-field scattering effect was considered in antenna measurement, which requires a great amount of measuring efforts and re-measurement if the operational platform has changed. In this study, the authors consider the near-field scattering problem in the framework of adaptive array beamforming theory, which avoids re-measurement and can be adaptive to the arbitrary scenario. Generally, the near-field scattering can result in severe performance degradation in adaptive beamforming applications. They propose a robust adaptive beamforming approach that can maintain the performance in the presence of near-field scatterers with unknown scattering coefficients. In the authors’ approach, the near-field scatterering signal component is incorporated into the presumed steering vector. Thus, it is treated as useful information in this study instead of nuisance interference in the literature. In particular, the properties of the far-field direct-path signal and near-field signal are explored and the large uncertainty set is divided into two small ones describing the far-field and near-field steering vectors, respectively. Simulation examples are provided to show the performance improvement by making use of the near-field scattering signals.