LSTM预测驱动的软件系统主动自适应方法

doi:10.3969/j.issn.0255-8297.2023.01.010

摘要/Abstract

摘要： 针对反应式自适应软件系统调整滞后的问题，提出了一种基于长短期记忆（long short-term memory，LSTM）网络预测驱动的主动自适应方法。该方法将LSTM神经网络预测技术嵌入监测-分析-决策-执行-知识控制模型的分析环节，利用自适应环境、质量及目标相关的运行数据和历史数据进行分类预测，形成自适应预警机制，在减小传统自适应决策滞后性影响的同时有效提高了软件系统的主动自适应能力。为了说明所提方法的主动性、鲁棒性、有效性，在经典的分布式远程辅助系统上对该方法进行实验评估。结果表明：该方法能够针对自适应需求提前预警，推动软件系统在必要时进行主动的自适应调整。

关键词: 软件自适应, 主动自适应, 预测驱动, 自适应预警

Abstract: Aiming at the adjustment lag problem of reactive self-adaptive software systems, a proactive self-adaptive approach based on long short-term memory (LSTM) prediction driven is proposed. In this approach, LSTM neural network prediction technology is embedded in the analysis phase of monitor-analyze-plan -execute-knowledge (MAPE-K) control model; Operating data relating to self-adaptive environments, self-adaptive qualities, and self-adaptive goals, and historical data are used for classification prediction to form a self-adaptive early warning mechanism, which can effectively improve the proactive selfadaptive ability of software systems and reduce the lag influence of reactive self-adaptive decision-making at the same time. In order to illustrate the initiative, robustness and effectiveness of this approach, evaluation on the classic distribution tele-assistance system (dTAS) platform is carried out. Experimental results show that the proposed approach can provide early warning to self-adaptive demand, and enable software systems to complete proactive self-adaptive adjustment when necessary.

Key words: software self-adaptation, proactive self-adaptation, prediction driven, selfadaptive early warning

中图分类号:

TP311

谢生龙, 王璐, 刘瑞佳, 溥颖, 刘潇. LSTM预测驱动的软件系统主动自适应方法[J]. 应用科学学报, 2023, 41(1): 121-140.

XIE Shenglong, WANG Lu, LIU Ruijia, PU Ying, LIU Xiao. Proactive Self-Adaptive Approach Driven by LSTM Prediction for Software System[J]. Journal of Applied Sciences, 2023, 41(1): 121-140.

参考文献

[1] Aase K K. Elements of economics of uncertainty and time with recursive utility[J]. Discussion Papers, 2020. DOI:10.2139/SSRN.3725505.
[2] Huang G L, Zhang M, Montiel D, et al. Automated extraction of physical parameters from experimentally obtained thermal profiles using a machine learning approach[J]. Computational Materials Science, 2021, 194:110459. DOI:10.1016/j.commatsci.2021.110459.
[3] Padilla L M K, Powell M, Kay M, et al. Uncertain about uncertainty:how qualitative expressions of forecaster confidence impact decision-making with uncertainty visualizations[J]. Frontiers in Psychology, 2021, 11:579267.
[4] Moreno G A, Cámara J, Garlan D, et al. Proactive self-adaptation under uncertainty:a probabilistic model checking approach[C]//Joint Meeting on Foundations of Software Engineering, ACM, 2015:1-12.
[5] Ren J H, Liu F. Predicting software defects using self-organizing data mining[J]. IEEE Access, 2019, 99:1. DOI:10.1109/ACCESS.2019.2927489.
[6] Cámar A J, Moreno G A, Garlan D. Stochastic game analysis and latency awareness for self-adaptation[C]//International Symposium on Software Engineering for Adaptive & Selfmanaging Systems, 2014:155-164.
[7] Ehrig H, Ermel C, Golas U, et al. Modelling and static analysis of self-adaptive systems by graph transformation[M]. Berlin, Heidelberg:Springer, 2015:299-326.
[8] Bucchiarone A, Ehrig H, Ermel C, et al. Rule-based modeling and static analysis of selfadaptive systems by graph transformation[M]. Cham:Springer, 2015:582-601.
[9] Fuad M M, Deb D, Baek J. Static analysis, code transformation and runtime profiling for self-healing[J]. Journal of Computers, 2013, 8(5):1127-1135.
[10] Bodden E. Self-adaptive static analysis[C]//International Conference on Software Engineering:New Ideas and Emerging Results, 2018:45-48.
[11] Sayre D B. A runtime verification and validation framework for self-adaptive software[D]. Fort Lauderdale:Nova Southeastern University, 2017.
[12] Calinescu R, Ghezzi C, Kwiatkowska M, et al. Self-adaptive software needs quantitative verification at runtime[J]. Communications of the ACM, 2012, 55(9):69-72, 75-77.
[13] Gerasimou S, Calinescu R, Banks A. Efficient runtime quantitative verification using caching, lookahead, and nearly-optimal reconfiguration[M].[S.l.]:ACM, 2014.
[14] Cámara J, Muccini H, Vaidhyanathan K. Quantitative verification-aided machine learning:a tandem approach for architecting self-adaptive IoT systems[C]//2020 International Conference on Software Architecture, 2020:11-22.
[15] 熊伟, 李兵, 陈军, 等. 一种基于预测控制的SaaS系统自适应方法[J]. 计算机学报, 2016, 39(2):364-376. Xiong W, Li B, Chen J, et al. A self-adaptation approach based on predictive control for SaaS[J]. Chinese Journal of Computers, 2016, 39(2):364-376. (in Chinese)
[16] Esfahani N, Elkhodary A, Malek S. A learning-based framework for engineering featureoriented self-adaptive software systems[J]. IEEE Transactions on Software Engineering, 2013, 39(11):1467-1493.
[17] Hw A, Lei W, Qi Y C, et al. A proactive approach based on online reliability prediction for adaptation of service-oriented systems[J]. Journal of Parallel and Distributed Computing, 2018, 114:70-84.
[18] 王璐, 李青山, 吕文琪, 等. 基于事件关系保障识别质量的自适应分析方法[J]. 软件学报, 2021, 32(7):1978-1998. Wang L, Li Q S, Lü W Q, et al. Self-adaptation analysis method for recognition quality assurance using event relationships[J]. Journal of Software, 2021, 32(7):1978-1998. (in Chinese)
[19] Aschoff R R, Zisman A. Proactive adaptation of service composition[J]. Lecture Notes in Computer Science, 2012, 7084(11):1-10. DOI:10.1109/SEAMS.2012.6224385.
[20] Zhang X, Li B, Zhu J. A monitoring and prediction model of workflow based self-adaptive software system[C]//The Second International Conference on Advanced Cloud & Big Data, IEEE Computer Society, 2014:115-121.
[21] Babu G S, Zhao P, Li X L. Deep convolutional neural network based regression approach for estimation of remaining useful life[C]//International Conference on Database Systems for Advanced Applications. Cham:Springer, 2016:214-228.
[22] Li X, Ding Q, Sun J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering & System Safety, 2018, 172:1-11.
[23] Mei Y, Wu Y, Li L. Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network[C]//IEEE International Conference on Aircraft Utility Systems, 2016:135-140.
[24] Zhang Y. Aeroengine fault prediction based on bidirectional LSTM neural network[C]//2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, 2020:317-320.
[25] Nguyen K, Medjaher K. A new dynamic predictive maintenance framework using deep learning for failure prognostics[J]. Reliability Engineering System Safety, 2019, 188:251-262.
[26] Huang C G, Yin X, Huang H Z, et al. An enhanced deep learning-based fusion prognostic method for RUL prediction[J]. IEEE Transactions on Reliability, 2019, 99:1-13.
[27] 盛剑会, 肖冬荣, 郭伟, 等. 模型预测控制(MPC)系统仿真软件开发与实现[J]. 辽宁工程技术大学学报(自然科学版), 2004, 23(2):226-229. Sheng J H, Xiao D R, Guo W, et al. Development and implementation of simulating software of model predictive control (MPC) system[J]. Journal of Liaoning Technical University (Natural Science Edition), 2004, 23(2):226-229. (in Chinese)
[28] 赵天琪, 赵海燕, 张伟, 等. 基于模型的自适应方法综述[J]. 软件学报, 2018, 29(1):23-41 Zhao T Q, Zhao H Y, Zhang W, et al. Survey of model-based self-adaptation methods[J]. Journal of Software, 2018, 29(1):23-41. (in Chinese)
[29] 于少伟. 基于区间数的模糊隶属函数构建[J]. 山东大学学报(工学版), 2010, 40(6):32-35, 93. Yu S W. Construction of a fuzzy membership function based on interval number[J]. Journal of Shandong University (Engineering Science), 2010, 40(6):32-35, 93. (in Chinese)
[30] Gordieiev O, Kharchenko V, Fominykh N, et al. Evolution of software quality models in context of the standard ISO 25010[C]//Proceedings of the Ninth International Conference on Dependability and Complex Systems DepCoS-RELCOMEX, 2014:223-232.
[31] Chen T, Bahsoon R. Self-adaptive and online QoS modeling for cloud-based software services[J]. IEEE Transactions on Software Engineering, 2017:1.
[32] Magableh B. A framework for evaluating model-driven self-adaptive software systems[J]. International Journal of Information Technology and Computer Science, 2019:1-11.
[33] Weyns D. An introduction to self-daptive systems:a contemporary software engineering perspective[M]. UK:CPI Group, 2020.
[34] 蔺瑞管, 王华伟, 车畅畅, 等. 基于LSTM分类器的航空发动机预测性维护模型[J]. 系统工程与电子技术, 2022, 44(3):1052-1059. Lin R G, Wang H W, Che C C, et al. Predictive maintenance model of aeroengine based on LSTM classifier[J]. Systems Engineering and Electronics, 2022, 44(3):1052-1059. (in Chinese)
[35] Weyns D, Calinescu R. Tele assistance:a self-adaptive service-based system exemplar[C]//International Symposium on Software Engineering for Adaptive & Self-managing Systems, 2015:88-92.