A Framework for Detecting System Performance Anomalies Using Tracing Data Analysis

Advances in technology and computing power have led to the emergence of complex and large-scale software architectures in recent years. However, they are prone to performance anomalies due to various reasons, including software bugs, hardware failures, and resource contentions. Performance metrics represent the average load on the system and do not help discover the cause of the problem if abnormal behavior occurs during software execution. Consequently, system experts have to examine a massive amount of low-level tracing data to determine the cause of a performance issue. In this work, we propose an anomaly detection framework that reduces troubleshooting time, besides guiding developers to discover performance problems by highlighting anomalous parts in trace data. Our framework works by collecting streams of system calls during the execution of a process using the Linux Trace Toolkit Next Generation(LTTng), sending them to a machine learning module that reveals anomalous subsequences of system calls based on their execution times and frequency. Extensive experiments on real datasets from two different applications (e.g., MySQL and Chrome), for varying scenarios in terms of available labeled data, demonstrate the effectiveness of our approach to distinguish normal sequences from abnormal ones.     

基于ESO的装甲车辆稳瞄系统积分滑模控制

针对装甲车辆稳瞄系统中存在摩擦力矩、参数漂移等非线性扰动因素造成系统性能下降的问题,设计一种基于扩张状态观测器（ESO）的积分滑模控制策略。在基于状态变量的滑模面中引入了误差积分补偿项,有利于降低系统的稳态误差,同时突破了常规滑模控制中被跟踪信号的各阶导数均需已知的限制;利用ESO对系统内外扰动进行观测补偿,减小了滑模控制所需要的切换增益,削弱滑模控制容易出现的抖振现象。仿真及实验结果表明,跟踪精度保持在0.5％以内,系统最大稳定误差小于0.1 mrad,该控制策略能够很好地抑制各种非线性扰动因素的影响,有效地改善系统的控制性能。     

Multiscale modelling of precipitation in concentrated alloys: from atomistic Monte Carlo simulations to cluster dynamics I thermodynamics

In a recent paper, the authors showed how the clusters free energies are constrained by the coagulation probability, and explained various anomalies observed during the precipitation kinetics in concentrated alloys. This coagulation probability appeared to be a too complex function to be accurately predicted knowing only the cluster distribution in Cluster Dynamics (CD). Using atomistic Monte Carlo (MC) simulations, it is shown that during a transformation at constant temperature, after a short transient regime, the transformation occurs at quasi-equilibrium. It is proposed to use MC simulations until the system quasi-equilibrates then to switch to CD which is mean field but not limited by a box size like MC. In this paper, we explain how to take into account the information available before the quasi-equilibrium state to establish guidelines to safely predict the cluster free energies.     

A bit-level image encryption algorithm based on spatiotemporal chaotic system and self-adaptive

This paper proposes a bit-level image encryption algorithm based on spatiotemporal chaotic system which is self-adaptive. We use a bit-level encryption scheme to reduce the volume of data during encryption and decryption in order to reduce the execution time. We also use the adaptive encryption scheme to make the ciphered image dependent on the plain image to improve performance. Simulation results show that the performance and security of the proposed encryption algorithm can encrypt plaintext effectively and resist various typical attacks.     

Coherent Population Trapping and Partial Decoherence in the Stochastic Limit

We use the stochastic limit technique to predict a new phenomenon concerning a two-level atom with degenerate ground state interacting with a quantum field. We show, that the field drives the state of the atom to a stationary state, which is non-unique, but depends on the initial state of the system through some conserved quantities. This non uniqueness follows from the degeneracy of the ground state of the atom, and when the ground subspace is two-dimensional, the family of stationary states will depend on a one-dimensional parameter. Only one of the stationary states in this family is a pure state and it coincides with the known trapped state. This means that by controlling the initial state (input) we can control the final state (output). The quantum Markov semigroup obtained in the limit admits an invariant pure state, but it is not true that all the extremal invariant states are pure. This is an interesting phenomenon also from mathematical point of view and its meaning will be discussed in a future paper. PACS numbers: 31.15.-p, 31.15.Gy, 32.80.Pj, 32.80.Qk     

单晶硅微纳构件加工表面性能的时变性研究

采用蒙特卡罗方法和分子动力学方法相结合, 模拟单晶硅微纳构件加工表面的时效过程, 研究其对加工表面质量和构件力学性能的影响. 模拟结果表明: 在时效过程中, 单晶硅微纳构件加工变质层的有序度显著提高, 残余应力大幅降低, 表面粗糙度略有增加, 此外还发现加工变质层中非晶硅原子在时效过程中大幅减少, 部分非晶硅出现了再结晶现象, 其中部分BCT5-Si以及金属相(Si-Ⅱ)结构原子转化为金刚石结构(Si-I). 时效作用对加工后单晶硅微纳构件表面性能具有重要的影响, 同时可以提高微纳构件的拉伸力学性能. 关键词： 蒙特卡罗方法 纳米加工 表面性能 时变性     

Stress aging in the electron glass

A new protocol for an aging experiment is studied in the electron-glass phase of indium-oxide films. In this protocol, the sample is exposed to a non-Ohmic electric field F for a waiting time t(w) during which the system attempts to reach a steady state (rather than relax towards equilibrium). The relaxation of the excess conductance Delta G after Ohmic conditions are restored exhibits simple aging as long as F is not too large.     

Photonic Feshbach resonance

Feshbach resonance is a resonance for two-atom scattering with two or more channels,in which a bound state is achieved in one channel.We show that this resonance phenomenon not only exists during the collisions of massive particles,but also emerges during the coherent transport of massless particles,that is,photons confined in the coupled resonator arrays linked by a separated cavity or a tunable two level system(TLS).When the TLS is coupled to one array to form a bound state in this setup,the vanishing transmission appears to display the photonic Feshbach resonance.This process can be realized through various experimentally feasible solid state systems,such as the couple defected cavities in photonic crystals and the superconducting qubit coupled to the transmission line.The numerical simulation based on the finite-different time-domain(FDTD) method confirms our assumption about the physical implementation.     

Chaos in computer performance

Modern computer microprocessors are composed of hundreds of millions of transistors that interact through intricate protocols. Their performance during program execution may be highly variable and present aperiodic oscillations. In this paper, we apply current nonlinear time series analysis techniques to the performances of modern microprocessors during the execution of prototypical programs. Our results present pieces of evidence strongly supporting that the high variability of the performance dynamics during the execution of several programs display low-dimensional deterministic chaos, with sensitivity to initial conditions comparable to textbook models. Taken together, these results show that the instantaneous performances of modern microprocessors constitute a complex (or at least complicated) system and would benefit from analysis with modern tools of nonlinear and complexity science.     

CSNS的kicker电源闸流管触发特性分析

针对中国散裂中子源kicker电源的闸流管,研制了基于大电流脉冲预电离和高压脉冲点火原理的双脉冲触发器,提高了闸流管的触发导通稳定性;同时研究了氢流、灯丝电流及预点火电流等参数对闸流管状态的影响;针对闸流管误漏触发现象,研制了基于单稳态及逻辑门电路构成的误漏触发检测电路,能够对闸流管的状态进行准确分析及预判;最后对kicker脉冲电源系统进行了年度分析总结。     

Theoretical investigation on nonlinear absorption of multilevel organic molecular system in ns, ps and fs regime

The nonlinear absorption properties of organic materials in nanosecond (ns), picoseond (ps) and femtosecond (fs) regime were theoretically investigated by rate equations based on multilevel organic molecular system, respectively. The simulation results show that the RSA is mainly due to the absorption contribution of the triplet first excited state in the ns regime and that of the singlet first excited state in the ps regime, both of which are a third-order nonlinear phenomena. The RSA in fs regime is mainly due to the excited state absorption (ESA) induced by two-photon absorption (TPA), which is a fifth-order nonlinear phenomenon.     

分仓颗粒布居分聚现象的通量模型

置于以窗口连接的分隔仓中振动驱动的颗粒气体会出现颗粒在两仓中布居分聚现象,被形象地称为麦克斯韦妖现象.通量模型的建立是理解麦克斯韦妖现象的关键问题.Eggers以颗粒气体动力学为基础得出了简化的理论模型.该模型可以很好地得到分仓中颗粒的布居分聚现象,然而似乎无法用于预测两种颗粒在分仓体系中的布居振荡现象.通过实验研究,测量了颗粒气体的流通量曲线,改进了Eggers模型.改进的模型可以很好地得到两种颗粒在分仓体系中的布居振荡现象. 关键词： 颗粒气体 耗散 通量模型     

Influence of solute mobility on dislocation motion II. Application of the basic model

In many metals containing solute atoms the dynamic strain aging phenomena have been observed at suitable temperatures and strain rates. In this paper a new model of these phenomena based on the assumption that it is the friction stress which is influenced by the dynamic strain aging is developed. The model is used to analyze the flow stress dependence on the dislocation velocity, temperature and solute concentration. The occurence of the plateau stress, the appearance of jerky flow and anomalies in the stress dependence of the strain rate sensitivity are discussed.     

Synchronization performance in time-delayed random networks induced by diversity in system parameter

Synchronization rhythm and oscillating in biological systems can give clues to understanding the cooperation and competition between cells under appropriate biological and physical conditions. As a result, the network setting is appreciated to detect the stability and transition of collective behaviors in a network with different connection types. In this paper, the synchronization performance in time-delayed excitable homogeneous random networks(EHRNs) induced by diversity in system parameters is investigated by calculating the synchronization parameter and plotting the spatiotemporal evolution pattern, and distinct impacts induced by parameter-diversity are detected by setting different time delays. It is found that diversity has no distinct effect on the synchronization performance in EHRNs with small time delay being considered. When time delay is increased greatly, the synchronization performance of EHRN degenerates remarkably as diversity is increased. Surprisingly, by setting a moderate time delay, appropriate parameter-diversity can promote the synchronization performance in EHRNs, and can induce the synchronization transition from the asynchronous state to the weak synchronization. Moreover, the bistability phenomenon, which contains the states of asynchronous state and weak synchronization,is observed. Particularly, it is confirmed that the parameter-diversity promoted synchronization performance in time-delayed EHRN is manifested in the enhancement of the synchronization performance of individual oscillation and the increase of the number of synchronization transitions from the asynchronous state to the weak synchronization. Finally, we have revealed that this kind of parameter-diversity promoted synchronization performance is a robust phenomenon.     

基于在线误差修正自适应SVR的非线性不确定分数阶混沌系统滑模控制

提出了一种基于在线误差修正自适应SVR的滑模控制方法, 用于解决一类非线性不确定分数阶混沌系统的控制问题. 分别通过对混沌系统非线性函数的离线SVR估计和基于增量学习的状态跟踪误差在线SVR预测, 解决了不确定分数阶混沌系统模型难以预测的问题. 同时根据Lyapunov稳定性理论设计出SVR权值自适应调整律. 本文以分数阶Arneodo 系统为例进行仿真, 仿真结果表明了, 对于带有外界噪声扰动的非线性不确定分数阶混沌系统, 该方法可以在有限时间内将系统稳定至期望状态, 提高对非线性函数的预测精度, 改善控制性能.     

A Coupling Framework for Multi-Domain Modelling and Multi-Physics Simulations

This paper describes a coupling framework for parallel execution of different solvers for multi-physics and multi-domain simulations with an arbitrary number of adjacent zones connected by different physical or overlapping interfaces. The coupling architecture is based on the execution of several instances of the same coupling code and relies on the use of smart edges (i.e., separate processes) dedicated to managing the exchange of information between two adjacent regions. The collection of solvers and coupling sessions forms a flexible and modular system, where the data exchange is handled by independent servers that are dedicated to a single interface connecting two solvers’ sessions. Accuracy and performance of the strategy is considered for turbomachinery applications involving Conjugate Heat Transfer (CHT) analysis and Sliding Plane (SP) interfaces.     

基于RBF神经网络的强流LIA故障诊断与性能评价技术

 用于流体动力学诊断的强流LIA是庞大而复杂的系统，其性能预测和评估是十分困难的。针对强流LIA大量的单次快脉冲非平稳信号，提出基于小波包分析与RBF神经网络技术相结合实现故障智能诊断和性能评价的方法。该方法以强流LIA高维信号的小波包结点能量提取的特征向量来表征信号平顶、脉宽以及暂态特性。在此基础上，建立了“神龙一号”加速器腔电压及注入器出口束流故障诊断与性能评价原型系统，该系统不仅可进行故障诊断和性能评价，还可探测到加速器运行参数的变化趋势，为加速器的精细维护提供预测信息。     

Kalman filter based initial guess estimation for digital image correlation

In applications digital image correlation based algorithms often present a basis for analysis of movement/deformation of bodies. The sequence of the obtained images is analyzed for this purpose. Especially, in cases when the body׳s movement/deformation between two successive images is significant, the initial guess can have a major influence on the execution speed of the algorithm. In the worst case it can even cause the divergence of the algorithm. This was the inspiration to develop a new and unique approach for an accurate and reliable determination of an initial guess for each image pixel. Kalman filter has been used for this purpose. It uses past measurements of observed variable(s) for calculations. Beside that it also incorporates state space model of the actual system. This is one of the most important advantages provided by Kalman filter. The determined initial guess by the proposed method is actually close to the true one and it enables fast convergence. Even more important property of this approach is the fact that it is not path-dependant because each image pixel, which is defined in ROI, is tracked through the sequence of images based on its own past measurements and general state space model. Consequently, the proposed method can be used to analyze tasks where discontinuities between image pixels are present. The applied method can be used to predict an initial guess where reference and deformed subsets are related by translational and rotational motion. The advantages mentioned above are verified with numerical and real experiments. The experimental validations are performed by NR (Newton–Raphson) approach which is the most widely used. Beside NR method the presented algorithm is applicable for other registration methods as well. It is used as an addition for calculation of initial guesses in a sequence of deformed images.     

Stochastic lattice model for bone remodeling and aging

We investigate the remodeling process of trabecular bone inside a human vertebral body using a stochastic lattice model, in which the ability of living bone to adapt to mechanical stimuli is incorporated. Our simulations show the emergence of a networklike structure similar to real trabecular bone. With time, the bone volume fraction reaches a steady state. The microstructure, however, coarsens with a typical length in the system following a power law. The simulation results suggest that a coarsening of the trabecular structure should occur as a natural aging phenomenon, not related to disease.