Runtime Estimation Research Articles

A fast pseudo-stochastic sequential cipher generator based on RBMs

Based on Restricted Boltzmann machines, an improved pseudo-stochastic sequential cipher generator is proposed. It is effective and efficient because of the two advantages: this generator includes a stochastic neural network that can perform the calculation in parallel, that is to say, all elements are calculated simultaneously; unlimited number of sequential ciphers can be generated simultaneously for multiple encryption schemas. The periodicity and the correlation of the output sequential ciphers meet requirements for the design of encrypting sequential data. In the experiment, the generated sequential cipher is used to encrypt images, and better performance is achieved in terms of the key space analysis, the correlation analysis, the sensitivity analysis and the differential attack. To evaluate the efficiency of our method, a comparative study is performed with a prevalent method called “logistic map.” Our approach achieves a better performance on running time estimation. The experimental results are promising as the proposed method could promote the development of image protection in computer security.

Providing Privateness via Transaction Splitting Using PFP Growth Algorithm

Frequent itemset mining is one of the most necessary problems in data extraction. The chance of devious a discrepancy private frequent itemset mining algorithm which can not only accomplish high data usefulness and a high level of secrecy, but also offer high time effectiveness. To this end, offer a discrepancy frequent itemset mining algorithm based on the Frequent Pattern-growth algorithm, which is referred to as Private Frequent Pattern-growth. The Private frequent Pattern -growth algorithm consists of a preprocessing phase and a mining phase. To improve the utility and secrecy tradeoff, a innovative smart splitting method is proposed to change the database in preprocessing phase. It needs to be performed only once for a given database. To compensate the information loss caused by transaction splitting, To estimate the definite support of itemsets in the original database in mining segment utilize run time estimation method. In accumulation, develop a dynamic reduction method to dynamically reduce the amount of noise added to guarantee privacy during the extracting process by leveraging the downward closure property. Private common pattern-growth algorithm is shown it is e-differentially private through formal privacy analysis; explain that PFP-growth algorithm is e- discrepancy secrecy. Extensive experiments on real datasets exemplify that our PFP-growth algorithm considerably outperforms the state-of-the-art techniques.

Differentially Private Utility Item Mining

In today's business world there is excess of available data & a great need to make good use of it. Data mining is art of extracting pattern and knowledge from large amount of data. Frequent itemset plays essential role in many Data Mining tasks that try to find out interesting patterns from database such as association rules. Association rule mining is a finding association among large databases variables. Mining of frequent itemset is most popular problem in data mining. The frequent itemsets recognition is valuable for economic & research purpose. But valuable discovered frequent itemsets should not only assure security but also achieve high data utility & offer time efficiency. The frequent itemsets are patterns or items like itemset, substructures or subsequences that comes out in data set frequently. There are several Frequent Item mining algorithms for frequent item mining such as Apriori, Frequent Pattern growth, Eclat, Utility Pattern growth algorithms. To provide security or privacy here we use differentially private Utility Item mining algorithm using Utility Pattern- growth algorithm. It consists of Preprocessing & mining phase. In preprocessing phase, to enhance utility & privacy advance smart splitting method is proposed to transform database. For given Database preprocessing phase should be performed only once. In mining phase run time estimation & dynamic reduction performed. To cover the information loss by smart splitting, we contrive run time estimation to calculate actual support of itemsets in original database. For privacy we have added noise in the database, we put forward dynamic reduction method to reduce the noise dynamically which guarantees privacy during mining process. In this paper we proposed new algorithm for mining high utility itemsets called as UP growth which consider not only frequency of itemset but also utility associated with the itemset. Keywords— Frequent Item Mining, є- differential privacy, FP- growth, UP-growth.

Automatic generation of efficient accelerators for reconfigurable hardware

Acceleration in the form of customized datapaths offer large performance and energy improvements over general purpose processors. Reconfigurable fabrics such as FPGAs are gaining popularity for use in implementing application-specific accelerators, thereby increasing the importance of having good high-level FPGA design tools. However, current tools for targeting FPGAs offer inadequate support for high-level programming, resource estimation, and rapid and automatic design space exploration. We describe a design framework that addresses these challenges. We introduce a new representation of hardware using parameterized templates that captures locality and parallelism information at multiple levels of nesting. This representation is designed to be automatically generated from high-level languages based on parallel patterns. We describe a hybrid area estimation technique which uses template-level models and design-level artificial neural networks to account for effects from hardware place-and-route tools, including routing overheads, register and block RAM duplication, and LUT packing. Our runtime estimation accounts for off-chip memory accesses. We use our estimation capabilities to rapidly explore a large space of designs across tile sizes, parallelization factors, and optional coarse-grained pipelining, all at multiple loop levels. We show that estimates average 4.8% error for logic resources, 6.1% error for runtimes, and are 279 to 6533 times faster than a commercial high-level synthesis tool. We compare the best-performing designs to optimized CPU code running on a server-grade 6 core processor and show speedups of up to 16.7×.

Elastic resource provisioning for scientific workflow scheduling in cloud under budget and deadline constraints

With the popularization and development of cloud computing, lots of scientific computing applications are conducted in cloud environments. However, current application scenario of scientific computing is also becoming increasingly dynamic and complicated, such as unpredictable submission times of jobs, different priorities of jobs, deadlines and budget constraints of executing jobs. Thus, how to perform scientific computing efficiently in cloud has become an urgent problem. To address this problem, we design an elastic resource provisioning and task scheduling mechanism to perform scientific workflow jobs in cloud. The goal of this mechanism is to complete as many high-priority workflow jobs as possible under budget and deadline constraints. This mechanism consists of four steps: job preprocessing, job admission control, elastic resource provisioning and task scheduling. We perform the evaluation with four kinds of real scientific workflow jobs under different budget constraints. We also consider the uncertainties of task runtime estimations, provisioning delays, and failures in evaluation. The results show that in most cases our mechanism achieves a better performance than other mechanisms. In addition, the uncertainties of task runtime estimations, VM provisioning delays, and task failures do not have major impact on the mechanism's performance.

Study of ABC and PSO algorithms as optimised adaptive noise canceller for EEG/ERP

This paper explores the application of swarm intelligence techniques for optimisation of adaptive filters/noise cancellers used in field of biomedical signal processing. Working, application and results analysis with respect to electroencephalogram/event related potential (EEG/ERP) filtering have been presented from the tutorial perspective. Artificial bee colony (ABC) and particle swarm optimisation (PSO) algorithm have been selected to derive adaptive noise canceller, comparative study and analysis of performance is done among them. Variants of ABC and PSO such as modified rate ABC to control frequency of the perturbation, scaling factor ABC to control magnitude of the perturbation, constant weighted inertia PSO, linear decay inertia PSO, constriction factors inertia PSO, nonlinear inertia PSO, and dynamic inertia PSO has been used. Performance is measured in terms of signal-to-noise ratio, correlation, running time estimation and mean square error. Finally, the quality of resultant ERP is determined with kurtosis and skewness.

Online Task Resource Consumption Prediction for Scientific Workflows

Estimates of task runtime, disk space usage, and memory consumption, are commonly used by scheduling and resource provisioning algorithms to support efficient and reliable workflow executions. Such algorithms often assume that accurate estimates are available, but such estimates are difficult to generate in practice. In this work, we first profile five real scientific workflows, collecting fine-grained information such as process I/O, runtime, memory usage, and CPU utilization. We then propose a method to automatically characterize workflow task requirements based on these profiles. Our method estimates task runtime, disk space, and peak memory consumption based on the size of the tasks’ input data. It looks for correlations between the parameters of a dataset, and if no correlation is found, the dataset is divided into smaller subsets using a clustering technique. Task estimates are generated based on the ratio parameter/input data size if they are correlated, or based on the probability distribution function of the parameter. We then propose an online estimation process based on the MAPE-K loop, where task executions are monitored and estimates are updated as more information becomes available. Experimental results show that our online estimation process results in much more accurate predictions than an offline approach, where all task requirements are estimated prior to workflow execution.

Differentially Private Frequent Itemset Mining via Transaction Splitting

Recently, there has been a growing interest in designing differentially private data mining algorithms. Frequent itemset mining (FIM) is one of the most fundamental problems in data mining. In this paper, we explore the possibility of designing a differentially private FIM algorithm which can not only achieve high data utility and a high degree of privacy, but also offer high time efficiency. To this end, we propose a differentially private FIM algorithm based on the FP-growth algorithm, which is referred to as PFP-growth. The PFP-growth algorithm consists of a preprocessing phase and a mining phase. In the preprocessing phase, to improve the utility and privacy tradeoff, a novel smart splitting method is proposed to transform the database. For a given database, the preprocessing phase needs to be performed only once. In the mining phase, to offset the information loss caused by transaction splitting, we devise a run-time estimation method to estimate the actual support of itemsets in the original database. In addition, by leveraging the downward closure property, we put forward a dynamic reduction method to dynamically reduce the amount of noise added to guarantee privacy during the mining process. Through formal privacy analysis, we show that our PFP-growth algorithm is ε-differentially private. Extensive experiments on real datasets illustrate that our PFP-growth algorithm substantially outperforms the state-of-the-art techniques.

Predictive modelling of running and dwell times in railway traffic

Accurate estimation of running and dwell times is important for all levels of planning and control of railway traffic. The availability of historical track occupation data with a high degree of granularity inspired a data-driven approach for estimating these process times. In this paper we present and compare the accuracy of several approaches to model running and dwell times in railway traffic. Three global predictive model approaches are presented based on advanced statistical learning techniques: LTS robust linear regression, regression trees and random forests. Also local models are presented for a particular train line, station or block section, based on LTS robust linear regression with some refinements. The models are validated and compared using a test set independent from the training set. The applicability of the proposed data-driven approach for real-time applications is proved by the accuracy of the obtained estimates and the low computation times. Overall, the local models perform best both in accuracy and computation time.

Scheduling parallel jobs with tentative runs and consolidation in the cloud

Since the success of cloud computing, more and more high performance computing parallel applications run in the cloud. Carefully scheduling parallel jobs is essential for cloud providers to maintain their quality of service. Existing parallel job scheduling mechanisms do not take the parallel workload consolidation into account to improve the scheduling performance. In this paper, after introducing a prioritized two-tier virtual machines architecture for parallel workload consolidation, we propose a consolidation-based parallel job scheduling algorithm. The algorithm employs tentative run and workload consolidation under such a two-tier virtual machines architecture to enhance the popular FCFS algorithm. Extensive experiments on well-known traces show that our algorithm significantly outperforms FCFS, and it can even produce comparable performance to the runtime-estimation-based EASY algorithm, though it does not require users to provide runtime estimation of the job. Moreover, our algorithm allows inaccurate CPU usage estimation and only requires trivial modification on FCFS. It is effective and robust for scheduling parallel workload in the cloud.

Flow‐sensitive runtime estimation: an enhanced hot spot detection heuristics for embedded Java just‐in‐time compilers

SummaryJava just‐in‐time compilers often compile only hot methods because the compilation overhead is a part of the running time. This requires precise and efficient hot spot detection, which includes distinguishing hot methods from cold ones, detecting them as early as possible, and paying a small detection overhead. Hot spot detection is especially important in embedded applications because they show more of a start‐up phase behavior of a regular application where methods are not executed heavily, so the hot methods are not definite. Because a long‐running method is likely to be a hot method, we can detect a hot method by measuring its running time during interpretation. However, precise measurement of the running time during execution is too expensive, especially in embedded systems, so many counter‐based heuristics have been proposed to estimate it such as Oracle's HotSpot heuristic. One problem is that although the overhead of these heuristics is low, they do not estimate the running time precisely, which may lead to imprecise hot spot detection.This paper proposes a new hot spot detection heuristic called flow‐sensitive runtime estimation, which can estimate the running time more precisely than others with a relatively low overhead. It only counts important bytecode instructions dynamically, but it can obtain the precise count of all interpreted bytecode instructions with a simple arithmetic calculation. We also propose a static analysis technique to predict those hot methods which spends a huge execution time once invoked, so as to compile them at their first invocation. Our experimental results show that these techniques can improve the performance by as much as an average of 7.4% compared with the HotSpot heuristic for the benchmarks when they run once, which is often regarded as showing the start‐up phase behavior. Even for real embedded Java applications such as the digital TV Java Xlet applications, our techniques can improve the user response time by an average of 7.1%. Copyright © 2015 John Wiley & Sons, Ltd.

Algorithms for cost- and deadline-constrained provisioning for scientific workflow ensembles in IaaS clouds

Large-scale applications expressed as scientific workflows are often grouped into ensembles of inter-related workflows. In this paper, we address a new and important problem concerning the efficient management of such ensembles under budget and deadline constraints on Infrastructure as a Service (IaaS) clouds. IaaS clouds are characterized by on-demand resource provisioning capabilities and a pay-per-use model. We discuss, develop, and assess novel algorithms based on static and dynamic strategies for both task scheduling and resource provisioning. We perform the evaluation via simulation using a set of scientific workflow ensembles with a broad range of budget and deadline parameters, taking into account task granularity, uncertainties in task runtime estimations, provisioning delays, and failures. We find that the key factor determining the performance of an algorithm is its ability to decide which workflows in an ensemble to admit or reject for execution. Our results show that an admission procedure based on workflow structure and estimates of task runtimes can significantly improve the quality of solutions.

Channel estimation and transmit power control in wireless body area networks

Wireless body area networks have recently received much attention because of their application to assisted living and remote patient monitoring. For these applications, energy minimisation is a critical issue since, in many cases, batteries cannot be easily replaced or recharged. Reducing energy expenditure by avoiding unnecessary high transmission power and minimising frame retransmissions is therefore crucial. In this study, a transmit power control scheme suitable for IEEE 802.15.6 networks operating in beacon mode with superframe boundaries is proposed. The transmission power is modulated, frame-by-frame, according to a run-time estimation of the channel conditions. Power measurements using the beacon frames are made periodically, providing reverse channel gain and an opportunistic fade margin, set on the basis of prior power fluctuations, is added. This approach allows tracking of the highly variable on-body to on-body propagation channel without the need to transmit additional probe frames. An experimental study based on test cases demonstrates the effectiveness of the scheme and compares its performance with alternative solutions presented in the literature.

Estimation of State of Charge of a Lead Acid Battery Using Support Vector Regression

Abstract Estimation of State of Charge (SOC) of batteries plays a vital role in Battery Management Systems(BMS). It is important to enhance the lifetime of a battery and give the user an accurate estimation of available runtime. This study aims to estimate the battery SOC based on current through and voltage across a battery using Support Vector Regression (SVR). Tests are run on SIMULINK using a 6 V, 4.5 Ah Lead Acid battery. Hyper parameters that decide the accuracy of SVR are estimated using Grid Search and Particle Swarm Optimization (PSO). The SVR maintains a high level of accuracy, with a Mean Squared Error (MSE) of 0.45% for PSO and 0.95% for GS.

Isotopic equivalence by Bézier curve subdivision for application to high performance computing

For an arbitrary degree Bézier curve B, we first establish sufficient conditions for its control polygon to become homeomorphic to B via subdivision. This is extended to show a subdivided control polygon that is ambient isotopic to B. We provide closed-form formulas to compute the corresponding number of iterations for equivalence under homeomorphism and ambient isotopy. The development of these a priori values was motivated by application to high performance computing (HPC), where providing estimates of total run time is important for scheduling.

OptQC: An optimized parallel quantum compiler

The software package Qcompiler (Chen and Wang 2013) provides a general quantum compilation framework, which maps any given unitary operation into a quantum circuit consisting of a sequential set of elementary quantum gates. In this paper, we present an extended software OptQC, which finds permutation matrices P and Q for a given unitary matrix U such that the number of gates in the quantum circuit of U=QTPTU′PQ is significantly reduced, where U′ is equivalent to U up to a permutation and the quantum circuit implementation of each matrix component is considered separately. We extend further this software package to make use of high-performance computers with a multiprocessor architecture using MPI. We demonstrate its effectiveness in reducing the total number of quantum gates required for various unitary operators. Program summaryProgram title: OptQCCatalogue identifier: AEUA_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEUA_v1_0.htmlProgram obtainable from: CPC Program Library, Queen’s University, Belfast, N. IrelandLicensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.htmlNo. of lines in distributed program, including test data, etc.: 178435No. of bytes in distributed program, including test data, etc.: 491574Distribution format: tar.gzProgramming language: Fortran, MPI.Computer: Any computer with Fortran compiler and MPI library.Operating system: Linux.Classification: 4.15.Nature of problem: It aims to minimize the number of quantum gates required to implement a given unitary operation.Solution method: It utilizes a threshold-based acceptance strategy for simulated annealing to select permutation matrices P and Q for a given unitary matrix U such that the number of gates in the quantum circuit of U=QTPTU′PQ is minimized, where U′ is equivalent to U up to a permutation. The decomposition of a unitary operator is performed by recursively applying the cosine–sine decomposition.Running time: Running time increases with the size of the unitary matrix, as well as the prescribed maximum number of iterations for qubit permutation selection and the subsequent simulated annealing algorithm. Running time estimates are provided for each example in Section 4. All simulation results presented in this paper are obtained from running the program on the Fornax supercomputer managed by iVEC@UWA with Intel Xeon X5650 CPUs.

Randomized Rumour Spreading: The Effect of the Network Topology

We consider the popular and well-studied push model, which is used to spread information in a given network with n vertices. Initially, some vertex owns a rumour and passes it to one of its neighbours, which is chosen randomly. In each of the succeeding rounds, every vertex that knows the rumour informs a random neighbour. It has been shown on various network topologies that this algorithm succeeds in spreading the rumour within O(log n) rounds. However, many studies are quite coarse and involve huge constants that do not allow for a direct comparison between different network topologies. In this paper, we analyse the push model on several important families of graphs, and obtain tight runtime estimates. We first show that, for any almost-regular graph on n vertices with small spectral expansion, rumour spreading completes after log2n + log n+o(log n) rounds with high probability. This is the first result that exhibits a general graph class for which rumour spreading is essentially as fast as on complete graphs. Moreover, for the random graph G(n,p) with p=c log n/n, where c > 1, we determine the runtime of rumour spreading to be log2n + γ (c)log n with high probability, where γ(c) = clog(c/(c−1)). In particular, this shows that the assumption of almost regularity in our first result is necessary. Finally, for a hypercube on n=2d vertices, the runtime is with high probability at least (1+β) ⋅ (log2n + log n), where β > 0. This reveals that the push model on hypercubes is slower than on complete graphs, and thus shows that the assumption of small spectral expansion in our first result is also necessary. In addition, our results combined with the upper bound of O(log n) for the hypercube (see [11]) imply that the push model is faster on hypercubes than on a random graph G(n, clog n/n), where c is sufficiently close to 1.

An Elastic Scheduling Algorithm For Resource Co-Allocation Based on System Generated Predictions With Priority

Resource Co-Allocation is basically used to execute multiple site jobs in a large scale computing environments with secure, faultless and in transparent manner. To be precise we are actually allocating multiple resources for different jobs taking into account the time parameter. Here we make use of the Scheduling queue and Resource Co-Allocation to reduce the Turn-around time with an advanced concept of System Generated Prediction based on Priority. In existing works we are scheduling the resource co-allocation request from user runtime estimation. As user runtime estimations are usually very imprecise that is not clear. In proposed work we are scheduling the resource co-allocation request based on system generated predictions through Discovery service & Priority (fairness and user experience) through topological sorting technique. The system generated predictions are better parameters than user runtime estimates for Resource co-Allocation scheduling, because System generated predictions reduce the scheduling time through proxy ser based discovery service technique. The proposed work consider priorities like advanced reservation, system Generated Predictions, Negotiation, Co-scheduling, policy (SLA, Price, Trust) for resource Co-Allocation. The system generated predictions are better than user runtime estimates for Resource co- Allocation scheduling, using the experimental data’s we proved this concept. End User doesn’t want the grid and resource knowledge only submit job to the portal. This proposed portal will take care of all knowledge about the resource collocation automatically with fast and efficient manner.

Towards Better Workflow Execution Time Estimation

Authors highlight the importance of estimating workflow execution time in the scheduling problem and in pricing models in Clouds. Claim that better approaches need to be developed to obtain precise estimates of execution time. Describe straightforward regression for stochastic execution time estimation. Propose a combination of Chebyshev-like distribution-free inequalities and distribution-based approaches to calculate better confidence bounds on runtime based on results of statistical tests. Finally, authors explain the need of developing better algorithm to compute workflow execution time based on stochastic estimates of tasks’ execution time. Explain the need of developing better workflow runtime estimation algorithm. Finally, authors present an approach to estimating workflow execution time based on stochastic estimates of tasks’ execution time.

Generic pole assignability, structurally constrained controllers and unimodular completion

In this paper we assume dynamical systems are represented by linear differential-algebraic equations (DAEs) of order possibly higher than one. We consider a structured system of DAEs for both the to-be-controlled plant and the controller. We model the structure of the plant and the controller as an undirected and bipartite graph and formulate necessary and sufficient conditions on this graph for the structured controller to generically achieve arbitrary pole placement. A special case of this problem also gives new equivalent conditions for structural controllability of a plant. Use of results in matching theory, and in particular, ‘admissibility’ of edges and ‘elementary bipartite graphs’, make the problem and the solution very intuitive. Further, our approach requires standard graph algorithms to check the required conditions for generic arbitrary pole placement, thus helping in easily obtaining running time estimates for checking this. When applied to the state space case, for which the literature has running time estimates, our algorithm is faster for sparse state space systems and comparable for general state space systems.The solution to the above problem also provides a necessary and sufficient condition for the following matrix completion problem. Given a structured rectangular polynomial matrix, when can it be completed to a unimodular matrix such that the additional rows that are added during the completion process are constrained to have zeros at certain locations.