1. <button id="qm3rj"><thead id="qm3rj"></thead></button>
      <samp id="qm3rj"></samp>
      <source id="qm3rj"><menu id="qm3rj"><pre id="qm3rj"></pre></menu></source>

      <video id="qm3rj"><code id="qm3rj"></code></video>

        1. <tt id="qm3rj"><track id="qm3rj"></track></tt>
            1. 2.765

              2022影響因子

              (CJCR)

              • 中文核心
              • EI
              • 中國科技核心
              • Scopus
              • CSCD
              • 英國科學文摘

              留言板

              尊敬的讀者、作者、審稿人, 關于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復。謝謝您的支持!

              姓名
              郵箱
              手機號碼
              標題
              留言內容
              驗證碼

              基于RUL和SVs-GFF的云服務器老化預測方法

              孟海寧 童新宇 謝國 張貝貝 黑新宏

              孟海寧, 童新宇, 謝國, 張貝貝, 黑新宏. 基于RUL和SVs-GFF的云服務器老化預測方法. 自動化學報, xxxx, xx(x): x?xx doi: 10.16383/j.aas.c211112
              引用本文: 孟海寧, 童新宇, 謝國, 張貝貝, 黑新宏. 基于RUL和SVs-GFF的云服務器老化預測方法. 自動化學報, xxxx, xx(x): x?xx doi: 10.16383/j.aas.c211112
              Meng Hai-Ning, Tong Xin-Yu, Xie Guo, Zhang Bei-Bei, Hei Xin-Hong. Cloud server aging prediction method based on RUL and SVs-GFF. Acta Automatica Sinica, xxxx, xx(x): x?xx doi: 10.16383/j.aas.c211112
              Citation: Meng Hai-Ning, Tong Xin-Yu, Xie Guo, Zhang Bei-Bei, Hei Xin-Hong. Cloud server aging prediction method based on RUL and SVs-GFF. Acta Automatica Sinica, xxxx, xx(x): x?xx doi: 10.16383/j.aas.c211112

              基于RUL和SVs-GFF的云服務器老化預測方法

              doi: 10.16383/j.aas.c211112
              基金項目: 國家自然科學基金(61602375, 61773313), 陜西省自然科學基礎研究計劃基金(2019JQ-749)資助
              詳細信息
                作者簡介:

                孟海寧:西安理工大學計算機科學與工程學院副教授. 主要研究方向為機器學習, 故障診斷與預測. 本文通信作者. E-mail: hnmeng@xaut.edu.cn

                童新宇:西安理工大學計算機科學與工程學院碩士研究生. 主要研究方向機器學習, 時間序列預測. E-mail: tongxinyu@stu.xaut.edu.cn

                謝國:西安理工大學教授. 主要研究方向為數據分析, 故障診斷. E-mail: guoxie@xaut.edu.cn

                張貝貝:西安理工大學計算機科學與工程學院講師. 主要研究方向為數據挖掘, 大數據技術. E-mail: bbzhang115@hotmail.com

                黑新宏:西安理工大學計算機科學與工程學院教授. 主要研究方向為機器學習, 安全性評估. E-mail: heixinhong@xaut.edu.cn

              Cloud Server Aging Prediction Method Based on RUL and SVs-GFF

              Funds: Supported by National Natural Science Foundation of China (61602375, 61773313) and Natural Science Basic Research Plan of Shaanxi Province (2019JQ-749)
              More Information
                Author Bio:

                MENG Hai-Ning Associate professor at the College of Computer Science and Engineering, Xi'an University of Technology. Her research interest covers machine learning and fault prognosis & prediction. Corresponding author of this paper

                TONG Xin-Yu Maser student at the College of Computer Science and Engineering, Xi'an University of Technology. His research interest covers machine learning and time series prediction

                XIE Guo Professor at Xi'an University of Technology. His research interest covers data analysis and fault diagnosis

                ZHANG Bei-Bei Lecturer at the College of Computer Science and Engineering, Xi'an University of Technology. His research interest covers data mining and big data technology

                HEI Xin-Hong Professor at the College of Computer Science and Engineering, Xi'an University of Technology. His research interest covers machine learning and security evaluation

              • 摘要: 針對云服務器中存在軟件老化現象, 將造成系統性能衰退與可靠性下降的問題, 借鑒剩余使用壽命(Remaining useful life, RUL)概念, 提出基于支持向量(Support vectors, SVs)和高斯函數擬合(Gaussian function fitting, GFF)的老化預測方法(SVs-GFF). 首先, 提取云服務器老化數據的統計特征指標, 并采用支持向量回歸(Support vector regression, SVR) 對統計特征指標進行數據稀疏化處理, 得到支持向量序列數據; 然后, 建立基于密度聚類的高斯函數擬合模型, 對不同核函數下的支持向量序列數據進行老化曲線擬合, 并采用Fréchet距離優化算法選取最優老化曲線; 最后, 基于最優老化曲線, 評估系統到達老化閾值前的RUL, 以預測系統何時發生老化. 在OpenStack云服務器4個老化數據集上的實驗結果表明, 基于RUL和SVs-GFF的云服務器老化預測方法與傳統預測方法相比, 具有更高的預測精度和更快的收斂速度.
              • 圖  1  云服務器老化現象

                Fig.  1  Software aging phenomenon in a cloud server

                圖  2  云服務器老化預測框圖

                Fig.  2  Block diagram of cloud server aging prediction process

                圖  3  支持向量的空間分布

                Fig.  3  Spatial distribution of support vectors

                圖  4  實驗平臺

                Fig.  4  Test bed

                圖  5  OpenStack云服務器原始數據

                Fig.  5  Original data of OpenStack cloud server

                圖  6  原始數據的統計特征指標

                Fig.  6  Statistical characteristic index of origin data

                圖  7  基于Fréchet距離選取最優老化曲線

                Fig.  7  Select the optimal aging curve via Fréchet distance

                圖  8  老化曲線擬合對比

                Fig.  8  Comparison of aging curve fitting

                圖  9  云服務器老化預測結果

                Fig.  9  Cloud server aging prediction results

                圖  10  云服務器RUL預測結果

                Fig.  10  Cloud server RUL prediction results

                圖  11  云服務器RUL預測絕對誤差

                Fig.  11  Absolute error of cloud server RUL prediction results

                圖  12  云服務器老化預測結果

                Fig.  12  Cloud server aging prediction results

                圖  13  云服務器RUL預測結果

                Fig.  13  Cloud server RUL prediction results

                圖  14  云服務器RUL預測絕對誤差

                Fig.  14  Absolute error of cloud server RUL prediction results

                表  1  老化曲線擬合均方根誤差對比 (%)

                Table  1  Comparison of aging curve fitting RMSE (%)

                擬合方法 響應時間集 頁面傳輸速度集
                基于密度聚類的GFF 21.598 47.129
                SVR 57.334 114.239
                下載: 導出CSV

                表  2  不同預測方法的參數設置

                Table  2  Parameter setting of different prediction methods

                預測方法 參數設置
                SVs-GFF 高斯函數中$\alpha$、$\beta$、$\sigma$和$\gamma$的初始值為0, 尋優方法: 最小二乘法, SVR中正則化參數: 1.0, 距離閾值$\varepsilon$: 0.5, $MinPts$: 2
                SVR 正則化參數: 1, 核函數: RBF
                GFF 高斯函數中$\alpha$、$\beta$、$\sigma$和$\gamma$的初始值為0, 尋優方法: 最小二乘法
                PF 基于PF模型更新指數模型參數, 老化特征值$\alpha$: 1.979, 指數模型參數$b$: 0.00271, $c$: ?0.1697, 白噪聲標準差$d$: ?0.06942
                ANN 神經元數: [輸入層: 30, 隱藏層1: 64, 隱藏層2: 64, 隱藏層3: 32, 輸出層: 1], 激活函數: ReLU, 迭代次數: 100
                LSTM 神經元數: [輸入層: 10, 隱藏層1: 32, 隱藏層2: 32, 隱藏層3: 16, 輸出層: 1], 激活函數: ReLU, 迭代次數: 100
                Markov 基于Markov模型更新指數模型參數, 指數模型參數的初始值均為0
                下載: 導出CSV

                表  3  預測性能比較

                Table  3  Comparison of prediction performance

                數據集名稱 評價指標 SVs-GFF GFF SVR PF ANN LSTM Markov
                響應時間集 ${\rm{CRA}}$ 0.904 0.769 0.891 0.841 0.737 0.901 0.858
                $C_{PE}$ 15.117 15.896 16.035 15.369 18.353 19.36 15.371
                頁面傳輸速度集 ${\rm{CRA}}$ 0.8790.6980.8610.8010.7210.7920.813
                $C_{PE}$16.48716.94516.98717.89719.54720.48717.881
                下載: 導出CSV
                1. <button id="qm3rj"><thead id="qm3rj"></thead></button>
                  <samp id="qm3rj"></samp>
                  <source id="qm3rj"><menu id="qm3rj"><pre id="qm3rj"></pre></menu></source>

                  <video id="qm3rj"><code id="qm3rj"></code></video>

                    1. <tt id="qm3rj"><track id="qm3rj"></track></tt>
                        亚洲第一网址_国产国产人精品视频69_久久久久精品视频_国产精品第九页
                      1. [1] Grottke M, Matias R, Trivedi K S. The fundament of software aging. In: Proceedings of the IEEE International Conference on Software Reliability Engineering Workshops. Seattle, USA: IEEE, 2008. 1?6
                        [2] Vizarreta P, Sieber C, Blenk A, Bemten A V, Trivedi K. Ares: a framework for management of aging and rejuvenation in softwarized networks. IEEE Transactions on Network and Service Management, 2021, 18(2): 1389-1400 doi: 10.1109/TNSM.2020.3030589
                        [3] Tai A T, Chau S N, Alkalaj L. On-board preventive maintenance: Analysis of effectiveness and optimal duty period. In: Proceedings of the 3rd International Workshop on Object Oriented Real-time Dependable Systems. Newport Beach, USA: IEEE, 1997. 40?47
                        [4] Xiang J, Weng C, Zhao D, Andrzejak A. Software aging and rejuvenation in android: new models and metrics. Software Quality Journal, 2020, 28(3): 85-106
                        [5] Grottke M, Li L, Vaidyanathan K, Trivedi K S. Analysis of software aging in a web server. IEEE Transactions on Reliability, 2006, 55(3): 411-420 doi: 10.1109/TR.2006.879609
                        [6] Pietrantuono R, Russo S. A survey on software aging and rejuvenation in the cloud. Software Quality Contro, 2020, 28(1): 7-38 doi: 10.1007/s11219-019-09448-3
                        [7] 施權, 胡昌華, 司小勝, 扈曉翔, 張正新. 考慮執行器性能退化的控制系統剩余壽命預測方法. 自動化學報, 2019, 45(5): 941-952

                        Shi Quan, Hu Chang-Hua, Si Xiao-Sheng, Hu Xiao-Xiang, Zhang Zheng-Xin. Remaining useful lifetime prediction method of controlled systems considering performance degradation of actuator. Acta Automatica Sinica, 2019, 45(5): 941-952
                        [8] Huang Y, Kintala C, Kolettis N, Fulton N D. Software rejuvenation: Analysis, module and applications. In: Proceedings of the 25th International Symposium on Fault-tolerant Computing. Pasadena, USA: IEEE, 1995. 381?390
                        [9] Andrade E, Machida F. Analysis of software aging impacts on plant anomaly detection with edge computing. In: Proceedings of the IEEE International Symposium on Software Reliability Engineering Workshops. Berlin, Germany: IEEE, 2019. 204?210
                        [10] Machida F, Maciel P R M. Markov chains and Petri nets for software rejuvenation systems. In: Proceedings of the IEEE International Symposium on Software Reliability Engineering Workshops. Coimbra, Portugal: IEEE, 2020. 325?326
                        [11] Dohi T, Goseva-Popstojanova K, Trivedi K S. Estimating software rejuvenation schedule in high assurance systems. The Computer Journal, 2001, 47: 473-485
                        [12] Machida F, Xiang J, Tadano K, Maeno Y. Lifetime extension of software execution subject to aging. IEEE Transactions on Reliability, 2017, 66(1): 123-134p doi: 10.1109/TR.2016.2615880
                        [13] Ning G, Zhao J, Lou Y. Optimization of two-granularity software rejuvenation policy based on the Markov regenerative process. IEEE Transactions on Reliability, 2016, 65(4): 1630-1646 doi: 10.1109/TR.2016.2570539
                        [14] Okamura. H, Dohi T. Performance-aware software rejuvenation strategies in a queueing system. In: Proceedings of the IEEE Second International Workshop on Software Aging and Rejuvenation. San Jose, USA: IEEE, 2010. 1?6
                        [15] Levitin G, Xing L, Xiang Y. Cost minimization of real-time mission for software systems with rejuvenation. Reliability Engineering & System Safety, 2020, 193: 106593.1-106593.12
                        [16] Zheng Z, Trivedi K S. Guest editorial: Special issue on modeling and mitigation techniques for software aging. Software Quality Journal, 2020, 28(1): 3-5 doi: 10.1007/s11219-020-09496-0
                        [17] Vaidyanathan K, Trivedi K S. A comprehensive model for software rejuvenation. IEEE Transactions on Dependable and Secure Computing, 2005, 2(2): 124-137 doi: 10.1109/TDSC.2005.15
                        [18] Yan Y, Guo P. A practice guide of software aging prediction in a web server based on machine learning. China Communications, 2016, 13(6): 225-235 doi: 10.1109/CC.2016.7513217
                        [19] Pereira P, Araujo J, Matos R. Software rejuvenation in computer systems: An automatic forecasting approach based on time series. In: Proceedings of the 37th IEEE International Performance Computing and Communications Conference. Orlando, USA: IEEE, 2018. 1?8
                        [20] Cotroneo D, Natella R, Pietrantuono R. Software aging analysis of the Linux operating system. In: Proceedings of the IEEE 21st International Symposium on Software Reliability Engineering. San Jose, USA: IEEE, 2010. 71?80
                        [21] Matos R, Araujo J, Maciel P. Software rejuvenation in eucalyptus cloud computing infrastructure: A method based on time series forecasting and multiple thresholds. In: Proceedings of the IEEE 3rd International Workshop on Software Aging and Rejuvenation. Hiroshima, Japan: IEEE, 2011. 38?43
                        [22] 鄭鵬飛, 齊勇, 陳鵬飛. 軟件老化的多元時間序列分析方法. 計算機科學與探索, 2012, 6(2):33-41

                        Zheng Peng-Fei, Qi Yong, Chen Peng-Fei. Multivariate time series analysis of software aging. Journal of Frontiers of Computer Science & Technology, 2012, 6(2): 33-41
                        [23] Islam S, Keung J, Lee K. Empirical prediction models for adaptive resource provisioning in the cloud. Future Generation Computer Systems, 2012, 28(1): 155-162 doi: 10.1016/j.future.2011.05.027
                        [24] Yan Y, Guo P, Liu L. A practice of forecasting software aging in an IIS web server using SVM. In: Proceedings of the IEEE International Symposium on Software Reliability Engineering Workshops. Naples, Italy: IEEE, 2014. 443?448
                        [25] Qiao Y, Zheng Z, Fang Y. An empirical study on software aging indicators prediction in android mobile. In: Proceedings of the IEEE International Symposium on Software Reliability Engineering Workshops. Memphis, USA: IEEE, 2018. 271?277
                        [26] Padhy N, Panigrahi R, Neeraja K. Threshold estimation from software metrics by using evolutionary techniques and its proposed algorithms, models. Evolutionary Intelligence, 2021, 14(2): 315-329 doi: 10.1007/s12065-019-00201-0
                        [27] Yan Y. Software aging prediction using neural network with ridge. IET Software, 2020, 14(6): 517-524
                        [28] Liu J, Tan X, Wang Y. CSSAP: Software aging prediction for cloud services based on ARIMA-LSTM hybrid model. In: Proceedings of the IEEE International Conference on Web Services. Beijing, China: IEEE, 2019. 283?290
                        [29] 孟海寧, 童新宇, 石月開, 朱磊, 馮鍇, 黑新宏. 基于ARIMA-RNN組合模型的云服務器老化預測方法. 通信學報, 2021, 42(1): 163-171

                        Meng Hai-Ning, Tong Xin-Yu, Shi Yue-Kai, Zhu Lei, Feng Kai, Hei Xin-Hong. Cloud server aging prediction method based on hybrid model of auto-regressive integrated moving average and recurrent neural network. Journal on Communications, 2021, 42(1): 163-171
                        [30] Nguyen H, Choi Y, Bui X N. Predicting blast-induced ground vibration in Open-Pit mines using vibration sensors and support vector regression-based optimization algorithms. Sensors, 2020, 20(1): 132
                        [31] Kwak M, Lkhagvasuren B, Sun X. An efficient method for fitting gaussian functions. Iranian Journal of Science and Technology, Transactions A: Science, 2021, 45(3): 1-14
                        [32] Guo L, Li N, Jia F. A recurrent neural network-based health indicator for remaining useful life prediction of bearings. Neurocomputing, 2017, 240(3): 98-109
                        [33] Cotroneo D, Natella R, Pietrantuono R, Russo S. A survey of software aging and rejuvenation studies. ACM Journal on Emerging Technologies in Computing Systems, 2014, 10(1): 1- 34
                        [34] Ahmed Fahim. K and starting means for K-means algorithm. Journal of Computational Science, 2021, 55(1): 101445
                        [35] Gudmundsson J, van Renssen A, Saeidi Z. Translation invariant Fréchet distance queries. Algorithmica, 2021, 83: 1-19 doi: 10.1007/s00453-020-00746-y
                        [36] Si X S, Wang W, Hu C H. A wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation. Mechanical Systems and Signal Processing, 2013, 35(1): 219-237
                        [37] Matias R, Barbetta P A, Trivedi K S. Accelerated degradation tests applied to software aging experiments. IEEE Transactions on Reliability, 2010, 59(1): 102-114 doi: 10.1109/TR.2009.2034292
                        [38] Engel Y, Mannor S, Meir R. The kernel recursive least-squares algorithm. IEEE Transaction on Signal Process, 2004, 52(8): 2275-2285 doi: 10.1109/TSP.2004.830985
                        [39] Qiu G, Gu Y, Chen J. Selective health indicator for bearings ensemble remaining useful life prediction with genetic algorithm and Weibull proportional hazards model. Measurement, 2020, 150: 107097 doi: 10.1016/j.measurement.2019.107097
                        [40] Aye S A, Heyns P S. An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission. Mechanical Systems and Signal Processing, 2017, 84: 485-498 doi: 10.1016/j.ymssp.2016.07.039
                        [41] Guo R, Sui J. Remaining useful life prognostics for the electrohydraulic servo actuator using Hellinger distance-based particle filter. IEEE Transactions on Instrumentation and Measurement, 2020, 69(4): 1148-1158 doi: 10.1109/TIM.2019.2910919
                        [42] Fauzi M F A M, Aziz I A, Amiruddin A. The prediction of remaining useful life (RUL) in oil and gas industry using artificial neural network (ANN) algorithm. In: Proceedings of the IEEE Conference on Big Data and Analytics. Milan, Italy: IEEE, 2019. 7?11
                        [43] Xia J, Feng Y W, Lu C. LSTM-based multi-layer self-attention method for remaining useful life estimation of mechanical systems. Engineering Failure Analysis, 2021, 125(12): 105385
                        [44] Wang T, Liu Z, Mrad N A. Probabilistic framework for remaining useful life prediction of bearings. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-12
                        [45] Saxena A, Celaya J, Saha B A. Metrics for offline evaluation of prognostic performance. International Journal of Prognostics & Health Management, 2010, 1(1): 2153-2648
                        [46] Wang B, Lei Y, Li N. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability, 2018: 1-12
                        [47] 張正新, 胡昌華, 司小勝, 張偉. 雙時間尺度下的設備隨機退化建模與剩余壽命預測方法. 自動化學報, 2017, 43(10): 1789-1798

                        Zhang Zheng-Xin, Hu Chang-Hua, Si Xiao-Sheng, Zhang Wei. Degradation modeling and remaining useful life prediction with bivariate time scale. Acta Automatica Sinica, 2017, 43(10): 1789-1798
                        [48] 裴洪, 胡昌華, 司小勝, 張正新, 杜黨波. 不完美維護下基于剩余壽命預測信息的設備維護決策模型. 自動化學報, 2018, 44(4): 719-729

                        Pei Hong, Hu Chang-Hua, Si Xiao-Sheng, Zhang Zheng-Xin, Du Dang-Bo. Remaining life prediction information-based maintenance decision model for equipment under imperfect maintenance. Acta Automatica Sinica, 2018, 44(4): 719-729
                      2. 加載中
                      3. 計量
                        • 文章訪問數:  194
                        • HTML全文瀏覽量:  66
                        • 被引次數: 0
                        出版歷程
                        • 收稿日期:  2021-11-24
                        • 錄用日期:  2022-04-28
                        • 網絡出版日期:  2023-06-29

                        目錄

                          /

                          返回文章
                          返回