Redundant Load Research Articles

Load Balancing Evaluation Tools for a Private Cloud: A Comparative Study

Cloud computing turns out to be an emerging technology that revolutionized the world of IT infrastructure. However, since the number of users is increasing daily, the demand for cloud services is increasing too. Thus, congestion occurs on the servers that provide services in the cloud. To avoid congestion, we used load balancer tools such as HAProxy and Nginx to intercept the requests of users and distribute them evenly to the servers. Jmeter is used to measure the performance metrics of least connection algorithm in terms of CPU utilization, response time, and concurrency level. Results showed high performance of HAProxy compared to Nginx in terms of response time and treating requests. Furthermore, we examined the characteristic of availability of the load balancer through deploying redundant load balancers, and we studied the effect of the failure of the load balancer on the quality of service of the end users. Keepalived is used to ensure a smooth transition between the two load balancers. According to the concurrency level, results proved that the number of unsuccessful requests during the failure of the master load balancer is proportionally minuscule compared to the total number of requests sent in a normal situation.

A Survey of Mobile Crowdsensing Techniques

Mobile crowdsensing serves as a critical building block for emerging Internet of Things (IoT) applications. However, the sensing devices continuously generate a large amount of data, which consumes much resources (e.g., bandwidth, energy, and storage) and may sacrifice the Quality-of-Service (QoS) of applications. Prior work has demonstrated that there is significant redundancy in the content of the sensed data. By judiciously reducing redundant data, data size and load can be significantly reduced, thereby reducing resource cost and facilitating the timely delivery of unique, probably critical information and enhancing QoS. This article presents a survey of existing works on mobile crowdsensing strategies with an emphasis on reducing resource cost and achieving high QoS. We start by introducing the motivation for this survey and present the necessary background of crowdsensing and IoT. We then present various mobile crowdsensing strategies and discuss their strengths and limitations. Finally, we discuss future research directions for mobile crowdsensing for IoT. The survey addresses a broad range of techniques, methods, models, systems, and applications related to mobile crowdsensing and IoT. Our goal is not only to analyze and compare the strategies proposed in prior works, but also to discuss their applicability toward the IoT and provide guidance on future research directions for mobile crowdsensing.

SWAROVsky: Optimizing Resource Loading for Mobile Web Browsing

Imperfect Web resource loading prevents mobile Web browsing from providing satisfactory user experience. In this article, we design and implement the SWAROVsky system to address three main issues of current inefficient Web resource loading: (1) on-demand and thus slow loading of sub-resources of webpages ; (2) duplicated loading of resources with different URLs but the same content ; and (3) redundant loading of the same resource due to improper cache configurations . SWAROVsky employs a dual-proxy architecture that comprises a remote cloud-side proxy and a local proxy on mobile devices. The remote proxy proactively loads webpages from their original Web servers and maintains a resource loading graph for every single webpage. Based on the graph, the remote proxy is capable of deciding which resources are “really” needed for the webpage and their loading orders, and thus can synchronize these needed resources with the local proxy of a client efficiently and timely. The local proxy also runs an intelligent and light-weight algorithm to identify resources with different URLs but the same content, and thus can avoid duplicated downloading of the same content via network. Our system can be used with existing Web browsers and Web servers, and does not break the normal semantics of a webpage. Evaluations with 50 websites show that on average our system can reduce the page load time by 43.1 percent and the network data transmission by 57.6 percent, while imposing marginal system overhead.

On the Interactions Between Value Prediction and Compiler Optimizations in the Context of EOLE

Increasing instruction-level parallelism is regaining attractiveness within the microprocessor industry. The {Early | Out-of-order | Late} Execution (EOLE) microarchitecture and Differential Value TAgged GEometric (D-VTAGE) value predictor were recently introduced to solve practical issues of Value Prediction (VP). In particular, they remove the most significant difficulties that forbade an effective VP hardware. In this study, we present a detailed evaluation of the potential of VP in the context of EOLE/D-VTAGE and different compiler options. Our study shows that if no single general rule always applies—more optimization might sometimes lead to more performance—unoptimized codes often get a large benefit from the prediction of redundant loads.

Performance-based seismic design framework for RC floor diaphragms in dual systems

Floor diaphragms play several roles in the seismic response of dual systems: support vertically spanning components, transfer lateral forces to walls and frames, provide restraint to columns and walls, tie the structure together, and enable redundant load paths for lateral forces. In many buildings after events as recent as the 2010-2011 Christchurch earthquakes, floor diaphragms were unable to perform one or more of these functions, leading to extensive damage and collapse. Research consistently highlights three underlying causes: a failure to ensure the integrity of the load path, underestimation of in-plane forces, and poorly understood interactions with walls, supporting beams and RC moment frames. Most recent and ongoing research has focused on modifying the prescriptive code provisions, and indeed many codes–but not all- have been consequently updated. Such prescriptive rules, however, are not helpful for assessing existing buildings, comparing alternate means and methods, or in displacement-based design (DBD) for which a performance-based design (PBD) framework is necessary. This paper proposes a new performance-based framework for the seismic design of reinforced-concrete (RC) floor diaphragms with or without precast elements. The floor diaphragm performance limit states (LS) are re-defined in terms of the observed failure modes (FM). Results from prior research on these failure modes are used to select damage measures (DM, e.g. ‘crack width’) for pairs of FM and LS. Expressions for DMs in terms of engineering demand parameters (EDP, e.g., ‘strain’) are derived from experimental results or from first principles. EDPs are the basic output from numerical analysis in PBD; this paper comments on the suitability of different analytical approaches.

Fault Detection and Diagnosis Based on Sparse PCA and Two-Level Contribution Plots

A novel process monitoring method is proposed based on sparse principal component analysis (SpPCA). To reveal meaningful variable correlations from process data, the SpPCA is developed to sequentially extract a set of sparse loading vectors from process data. To build a high-performance monitoring model, a fault detectability matrix is applied to select the sparse loading vectors used for process modeling from all sparse loading vectors obtained by SpPCA. The fault detectability matrix ensures that the faults related to any monitored process variable are detectable in the principal component subspace and no overlapped (or redundant) loading vectors are involved in the monitoring model. Moreover, the selected sparse loading vectors classify all process variables into nonoverlapping groups according to variable correlations. Two-level contribution plots, which consist of group-wise and group-variable-wise contribution plots, are used for fault diagnosis. The first-level group-wise contribution plot describe...

Game theoretic approaches for wireless proactive caching

Recently proposed wireless proactive caching has opened up a promising avenue for reducing the redundant traffic load of the future wireless network. In addition to infrastructure updating, caching schemes for different wireless caching scenarios are also essential problems of concern. Along with the benefits brought by proactive caching, the cost of proactive caching should also be taken into account, since caching schemes can be influenced by different interest relevant parties in wireless networks. In this article, we discuss several typical caching scenarios and apply corresponding game theoretical models to illustrate how the selfishness of different parties may influence the overall wireless proactive caching. Efficient caching strategies can be designed by carefully considering the relations and interactions among these parties by using game theory. We also outline possible future research directions in this emerging area.

A new shoulder model with a biologically inspired glenohumeral joint

Kinematically unconstrained biomechanical models of the glenohumeral (GH) joint are needed to study the GH joint function, especially the mechanisms of joint stability. The purpose of this study is to develop a large-scale multibody model of the upper limb that simulates the 6 degrees of freedom (DOF) of the GH joint and to propose a novel inverse dynamics procedure that allows the evaluation of not only the muscle and joint reaction forces of the upper limb but also the GH joint translations. The biomechanical model developed is composed of 7 rigid bodies, constrained by 6 anatomical joints, and acted upon by 21 muscles. The GH joint is described as a spherical joint with clearance. Assuming that the GH joint translates according to the muscle load distribution, the redundant muscle load sharing problem is formulated considering as design variables the 3 translational coordinates associated with the GH joint translations, the joint reaction forces associated with the remaining kinematic constraints, and the muscle activations. For the abduction motion in the frontal plane analysed, the muscle and joint reaction forces estimated by the new biomechanical model proposed are similar to those estimated by a model in which the GH joint is modeled as an ideal spherical joint. Even though this result supports the assumption of an ideal GH joint to study the muscle load sharing problem, only a 6 DOF model of the GH joint, as the one proposed here, provides information regarding the joint translations. In this study, the biomechanical model developed predicts an initial upward and posterior migration of the humeral head, followed by an inferior and anterior movement, which is in good agreement with the literature.

Research on maximum power point tracking in redundant load mode for photovoltaic system

In order to ensure that the photovoltaic (PV) array always works at the global maximum point of power to increase the system’s overall efficiency, this paper leads the study on maximum power point tracking (MPPT) in redundant load mode. A new control system is designed by combining the redundant electronic load module, embedded controller, supportive capacitor and boost circuit. The system adjusts duty ratio of boost circuit dynamically based on the maximum power point parameter provided by redundant load unit in order to realize MPPT. An experiment shows that no matter whether system is under an even illumination or partly perturbed by shadow, this method can find the exact maximum power point.

An intra-bone axial load transducer: development and validation in an in-vitro radius model.

BackgroundAccurate measurement of forces through the proximal radius can assess the effects of some surgical procedures on radioulnar load sharing, but is difficult to achieve given the redundant loading nature of the musculoskeletal system. Previously reported devices have relied on indirect measurements that may alter articular joint location and function. An axial load transducer interposed in the diaphysis of the radius may accurately quantify unknown axial loads of the proximal radius, and maintain articular location.MethodsAn in-vitro radius model was developed by interposing an axial load transducer in the diaphysis of the proximal radius. Static loads of 20, 40, 60, 80, and 100 N were applied with a servo-hydraulic actuator to the native radial head at angles of 10°, 20°, 30°, and 40° in the anterior, posterior, medial and lateral directions.FindingsLinear regression of five repeatability trials showed excellent agreement between the transducer and applied loads (R2 = 1 for all trials). For off-axis net joint loads, the majority of measured loading errors were within the inter-quartile range for mean loads up to 80 N. Loads below 80 N and outside the inter-quartile range had errors of less than 1 N.ConclusionsThe repeatability and off-axis net joint load results of this study validate the effectiveness of the interposed axial load transducer to accurately quantify proximal radius loads. The surgical technique preserves the native articular location and soft-tissue constructs, like the annular ligament. The modular design allows for testing the effects of length-changing osteotomies in subsequent biomechanical studies.

Stochastic stability of the derivative unscented Kalman filter**Project supported by the National Natural Science Foundation of China (Grant No. 61174193) and the Doctorate Foundation of Northwestern Polytechnical University, China (Grant No. CX201409).

This is the second of two consecutive papers focusing on the filtering algorithm for a nonlinear stochastic discrete-time system with linear system state equation. The first paper established a derivative unscented Kalman filter (DUKF) to eliminate the redundant computational load of the unscented Kalman filter (UKF) due to the use of unscented transformation (UT) in the prediction process. The present paper studies the error behavior of the DUKF using the boundedness property of stochastic processes. It is proved that the estimation error of the DUKF remains bounded if the system satisfies certain conditions. Furthermore, it is shown that the design of the measurement noise covariance matrix plays an important role in improvement of the algorithm stability. The DUKF can be significantly stabilized by adding small quantities to the measurement noise covariance matrix in the presence of large initial error. Simulation results demonstrate the effectiveness of the proposed technique.

Managing the load on a reader's mind.

None

The Physicochemical Properties and Catalytic Characteristics of Different Biomass Ashes

Steam gasification of petroleum coke catalyzed by different biomass ashes and different biomass ash loadings were investigated to examine the catalytic effects not only on the gasification activity but also on the H2 production characteristics, and the physicochemical properties of three biomass ashes (rice straw ash, wheat straw ash, and cotton straw ash) were also analyzed. The total contents of alkali metals (K and Na), alkaline earth metals (Ca and Mg), and transition metal (Fe) in RSA, WSA, and CSA were separately up to 22.63, 43.88, and 55.68%, and a large quantity of catalytic components (such as KCl, K2SO4, etc.) were contained in these biomass ashes. The biomass ashes could not only enhance the gasification activity of petroleum coke effectively, but also promote the H2 production greatly. The ordering of the catalytic action of various biomass ashes was CSA > WSA > RSA. The increasing loading of biomass ash was favorable for elevating the gasification activity of petroleum coke and promoting the H2 production, and the effects of the redundant biomass ash loading on those were very little. The mineral matters in biomass was conducive to improve the gasification activity of petroleum coke during the co-gasification processes and to promote the H2 production to produce syngas with high purity H2 (up to 61%) and no virtual CH4 at relatively low temperatures.

A silicon force sensor for large magnitude impact loads

We present a novel force sensor to measure large forces over a wide bandwidth (from static loads to 100's of kHz) for use as a shock sensor in challenging environments. The sensor is configured as a washer with embedded MEMS (Microelectromechanical Systems) piezo-resistive doped polysilicon sensing elements. The silicon sensing elements utilize photolithographically patterned strain gages on deforming sense plates to provide a high sensitivity linear response (1–10mV/1000lbf, 0.2–2mV/kN) to input loads of up to 10,000lbf (45,000N). Higher loads are achievable by implementing relatively simple design changes, for instance a thicker or smaller diameter sense plate. Very small silicon sensor elements (as small as 10–100μm in diameter) allow multiple sensors to be embedded in the washer to provide redundant load measurement and the determination of load direction. Readily available engineering materials FR4 (epoxy circuit board), copper, Kapton (polyimide), and steel are used to package the silicon sensor die in a sandwich that protects the brittle silicon allowing it to survive high magnitude impact loads. The design procedures presented allow the sensor designer to control the stress level at the silicon sensor die and therefore the effective load range of the sensor, while maintaining a high signal to noise ratio (>100:1).

MESIP: A Configurable and Data Reusable Motion Estimation Specific Instruction-Set Processor

This paper proposes a new motion estimation (ME)-specific instruction-set processor (MESIP) with a novel search scan order with high data reusability, to efficiently implement various advanced ME algorithms. The proposed ME-specific instructions can be selectively used for ME algorithms. The novel data-reusing search scan order, called center biased search scan (CBSS), exploits the symmetry of the search pattern to reduce redundant data loading on MESIP by about 26.9% and 16.1% compared with raster scan and snake scan, respectively. MESIP has been implemented with IBM's 90-nm CMOS technology and has 203 K gates excluding memory. Simulation results show that the proposed MESIP can reduce the number of required instructions by up to 18.9% compared with existing ME processors. Moreover, MESIP achieves comparable performance even with ME ASICs and hence may be quite suitable for a low-power and high-performance ME implementation.

저전력 움직임 추정을 위한 데이터 재사용 스캔 방법

본 논문은 저전력 움직임 추정장치를 구현하기 위한 전역 탐색 및 고속 탐색용 데이터 재사용 스캔 방법을 제안한다. 제안하는 최적화된 소 구역 분할방법은 탐색 영역을 여러 개의 소 구역으로 나누어 기존의 smart snake scan 방법과 비교 하였을 때 같은 양의 데이터 재사용에 필요한 재구성 가능한 레지스터 어레이를 반으로 줄일 수 있다. 또한 제안하는 중심 편향 탐색 스캔방법은 다양한 고속탐색 알고리즘의 데이터 재사용 가능성을 향상 시킬 수 있다. 제안하는 탐색 순서는 기존의 래스터 스캔과 snake scan 방법에 비해 평균적으로 각각 26%와 16.1%의 반복된 데이터 로딩을 줄일 수 있다. 따라서 제안하는 스캔 방법은 메모리의 접근 횟수를 줄일 수 있기 때문에 저전력과 고성능의 움직임 추정 구현에 적합하다.

Finite Element Modeling and Experimental Characterization of Enhanced Hybrid Composite Structures for Improved Crashworthiness

In this work, two hybrid composite structures were designed, modeled, and tested for improved resistance to impact. They were inspired by bistable composite structures, which are structures composed of two parts: a so-called “main link” and a so-called “waiting link.” These links work together as a mechanism that will provide enhanced damage tolerance, and the structure exhibits a bistable stress/strain curve under static tension. The function of the main link is to break early, at which point the waiting link becomes active and provides a redundant load path. The goal of the current study was to design, manufacture, and test a similar concept for impact loading and achieve greatly improved impact resistance per unit weight. In the current project, the main link was designed to be a brittle composite material (in this case, woven carbon/epoxy) exposed to impact, while the waiting link was chosen to be made with a highly nonlinear and strong composite material (in this case, polyethylene/epoxy), on the opposite surface. Hence, the structure, if proven successful, can be considered an enhanced hybrid concept. An explicit finite element (FE) commercial code, LS-DYNA, was used to design and analyze the baseline as well as two proposed designs. The simulations' methodology was validated with results published in the literature, which reported tests from linear fiber-reinforced composites. The plots were obtained via the ASCII files generated from the FE code, processed using matlab®, and compared to experimental impact tests. An instrumented drop-weight testing machine performed impact tests, and a high-speed camera validated the specimens' displacement under impact. It is shown that the FE model provided qualitative behavior very consistent with the experiments but requires further improvements. Experimentally, it is shown that one of the two enhanced hybrid models leads to up to a 30% increase of returned energy/weight when compared to its baseline and, therefore, is worthy of further investigations.

Loop scheduling with memory access reduction subject to register constraints for DSP applications

SUMMARYMemory accesses introduce big‐time overhead and power consumption because of the performance gap between processors and main memory. This paper describes and evaluates a technique, loop scheduling with memory access reduction (LSMAR), that replaces hidden redundant load operations with register operations in loop kernels and performs partial scheduling for newly generated register operations subject to register constraints. By exploiting data dependence of memory access operations, the LSMAR technique can effectively reduce the number of memory accesses of loop kernels, thereby improving timing performance. The technique has been implemented into the Trimaran compiler and evaluated using a set of benchmarks from DSPstone and MiBench on the cycle‐accurate simulator of the Trimaran infrastructure. The experimental results show that when the LSMAR technique is applied, the number of memory accesses can be reduced by 18.47% on average over the benchmarks when it is not applied. The measurements also indicate that the optimizations only lead to an average 1.41% increase in code size. With such small code size expansion, the technique is more suitable for embedded systems compared with prior work.Copyright © 2013 John Wiley & Sons, Ltd.

Laser Ablative Surface Treatment for Enhanced Bonding of Ti-6Al-4V Alloy

Adhesive bonding offers many advantages over mechanical fastening, but requires certification before it can be incorporated in primary structures for commercial aviation without disbond-arrestment features or redundant load paths. Surface preparation is widely recognized as the key step to producing robust and predictable adhesive bonds. Surface preparation by laser ablation provides an alternative to the expensive, hazardous, polluting, and less precise practices used currently such as chemical-dip, manual abrasion and grit blast. This report documents preliminary testing of a surface preparation technique using laser ablation as a replacement for the chemical etch and abrasive processes currently applied to Ti-6Al-4V alloy adherends. Surface roughness and surface chemical composition were characterized using interference microscopy and X-ray photoelectron spectroscopy, respectively. A technique for fluorescence visualization was developed which allowed for quantitative failure mode analysis. Wedge crack extension testing in a hot, humid environment indicated the relative effectiveness of various surface treatments. Increasing ablation duty cycle reduced crack propagation and adhesive failure. Single lap shear testing showed an increase in strength and durability as laser ablation duty cycle and power were increased. Chemical analyses showed trends for surface chemical species, which correlated with improved bond strength and durability.

A Centralized State Repository Approach to Highly Scalable and High-Availability Parallel Firewall

Conventional high-availability stateful parallel firewall suffers from low scalability due to two overlapping requirements: workload distribution and redundancy. To achieve high throughput, load-distribution with complex algorithm is conventionally employed, consuming a lot of resources and making the system susceptible to state-related attacks such as SYN-flooding. On the other hand, making the system redundant usually implies N-to-N crossreplication of connection-state data among firewall nodes. These make the scaling effort very difficult at best. This paper presents the novel design and implementation of a highly scalable, high-availability, stateful parallel firewall with centralized state repository intending for high-speed connection environment. The system consists of fault sensor unit(s), fully redundant load manager units, fully redundant central state repository unit(s), and an array of Linux-based machines acting as firewall nodes under the data parallel scheme. Adding more units into the system can scale every component up. Consistent Disjoint-subset Hashing and Stateless Load balancing algorithms, chosen for their superior computing overhead, provide high performance, flexibility and scalability. Centralized State Repository further enhances reliability and scalability. Actual deployment statistics confirm that the combination of centralized state repository and on-demand state restoration largely reduces the number of state synchronization transactions when the number of firewall nodes fluctuates. Therefore, the high-scalability and load balancing are gained with minimal state replications.