Skip to main content
SpringerLink
Log in

Evolutionary approaches to signal decomposition in an application service management system

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

The increased demand for autonomous control in enterprise information systems has generated interest on efficient global search methods for multivariate datasets in order to search for original elements in time-series patterns, and build causal models of systems interactions, utilization dependencies, and performance characteristics. In this context, activity signals deconvolution is a necessary step to achieve effective adaptive control in Application Service Management. The paper investigates the potential of population-based metaheuristic algorithms, particularly variants of particle swarm, genetic algorithms and differential evolution methods, for activity signals deconvolution when the application performance model is unknown a priori. In our approach, the Application Service Management System is treated as a black- or grey-box, and the activity signals deconvolution is formulated as a search problem, decomposing time-series that outline relations between action signals and utilization-execution time of resources. Experiments are conducted using a queue-based computing system model as a test-bed under different load conditions and search configurations. Special attention was put on high-dimensional scenarios, testing effectiveness for large-scale multivariate data analyses that can obtain a near-optimal signal decomposition solution in a short time. The experimental results reveal benefits, qualities and drawbacks of the various metaheuristic strategies selected for a given signal deconvolution problem, and confirm the potential of evolutionary-type search to effectively explore the search space even in high-dimensional cases. The approach and the algorithms investigated can be useful in support of human administrators, or in enhancing the effectiveness of feature extraction schemes that feed decision blocks of autonomous controllers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

Notes

  1. A signal as a time-series defines continuing flow of information, measured metrics or any other quantity that changes in time.

  2. Threads sleeps and resources waits form interesting situations. Although both sleeps and waits impact directly action execution times (an action does nothing as defined in the code) and active thread count, their relation to other resources utilization is very different. Whilst waits for resources are included in the resources utilization and queue lengths metrics, sleeps have minimal effect on CPU, Disk or other physical resources utilization.

  3. As a rule of thumb a fair level of denoising is achieved when SMA aggregates values following the width of the longest action.

  4. In engineering practice in most of the cases action executions are assigned at the time the action started.

  5. The execution count can very often cause software or hardware resources utilization regardless of the execution time.

  6. After applying a simulation-based data generator, the speed increased by a factor of approximately 600–800 (that practically allows running 24-h load simulation in about 2–3 min, depending on the count of the load sources.

  7. The load pattern gives a precise way for configuring variability in the expected intensity of the frequency of incoming calls for a given action. This parameter is very helpful to define special test cases, such as actions interference using the same resource, receiving temporarily higher load to observe effects of spikes in resources consumption, or short reoccurring load changes to analyze any “delay” impacting the strength of the ASM-SD.

  8. A Particle Swarm Optimization (PSO) implementation consistent with the standard PSO 2007/2011 of Maurice Clerc et al. (Bendtsen 2012), version 1.0.3 (2012-09-02).

  9. Genetic Algorithm (GA) optimization package for real-based and permutation-based problems, version 1.1 (2013-03-24).

  10. The DEoptim package implements the Differential Evolution (DE) algorithm for global optimization of a real-valued function of a real-valued parameter vector, version 2.2-2 (2014-12-17).

References

  • Aksanli B, Venkatesh J, Zhang L, Rosing T (2012) Utilizing green energy prediction to schedule mixed batch and service jobs in data centers. ACM SIGOPS Oper Syst Rev 45(3):53–57

    Article  Google Scholar 

  • Ardia D, Boudt K, Carl P, Mullen KM, Peterson BG (2011) Differential evolution with DEoptim. R Journal 3(1):27–34

    Google Scholar 

  • Banks J, Carson J, Nelson B, Nicol DM (2000) Discrete-Event System Simulation. Prentice Hall, Englewood Cliffs, NJ

  • Bartolini DB, Sironi F, Sciuto D, Santambrogio MD (2012) Aninfrastructure to instrument applications and measure performance inselfadaptive computing. In: Workshop on self-awareness in reconfigurable computing systems (SRCS), pp 44–47

  • Becker S, Koziolek H, Reussner R (2009) The Palladio component model for model-driven performance prediction. J Syst Softw 82(1):3–22

    Article  Google Scholar 

  • Bélisle CJ (1992) Convergence theorems for a class of simulated annealing algorithms on R\(^d\). J Appl Probab pp 885–895

  • Bell AJ, Sejnowski TJ (1995) An information-maximization approach to blind separation and blind deconvolution. Neural Comput 7(6):1129–1159

    Article  Google Scholar 

  • Beloglazov A, Abawajy J, Buyya R (2012) Energy-aware resource allocation heuristics for efficient management of data centers for cloud computing. Future Gener Comput Syst 28(5):755–768

    Article  Google Scholar 

  • Beloglazov A, Buyya R (2010) Energy efficient resource management in virtualized cloud data centers. Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster. IEEE Computer Society, Cloud and Grid Computing, pp 826–831

  • Bendtsen C (2012) PSO: Particle Swarm Optimization, {pso}, R Documentation. http://cran.r-project.org/web/packages/pso/

  • Bertoli M, Casale G, Serazzi G (2009) JMT: performance engineering tools for system modeling. ACM SIGMETRICS Perform Eval Rev 36(4):10–15

    Article  Google Scholar 

  • Bertoli M, Casale G, Serazzri G (2006) Java modelling tools: an open source suite for queueing network modelling andworkload analysis. In: Quantitative Evaluation of Systems, 2006. QEST 2006. Third International Conference on, IEEE, pp 119–120

  • Buyya R, Murshed M (2002) GridSim: A toolkit for the modeling and simulation of distributed resource management and scheduling for grid computing. Concurr Comput: Pract Exp 14(13–15):1175–1220

    Article  MATH  Google Scholar 

  • Buyya R, Ranjan R, Calheiros RN (2009) Modeling and simulation of scalable cloud computing environments and the CloudSim toolkit: Challenges and opportunities. In: High Performance Computing & Simulation, 2009. HPCS’09. International Conference on, IEEE, pp 1–11

  • Calheiros RN, Ranjan R, Beloglazov A, De Rose CA, Buyya R (2011) CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Softw: Pract Exp 41(1):23–50

    Google Scholar 

  • Chambers C (1992) The design and implementation of the self compiler, an optimizing compiler for object-oriented programming languages. Ph.D. thesis, Stanford University

  • Chen MY, Kiciman E, Fratkin E, Fox A, Brewer E (2002) Pinpoint: Problem determination in large, dynamic internet services. In: Dependable Systems and Networks, 2002. DSN 2002. Proceedings. International Conference on, IEEE, pp 595–604

  • Cichocki A, Amari S et al (2002) Adaptive blind signal and image processing. Wiley, Chichester

    Book  Google Scholar 

  • Clerc M (2010) Particle swarm optimization, Wiley, UK

  • Clerc M, et al (2011) Standard PSO 2011. Tech. rep., Technical Report [online]. http://www.particleswarm.info/, Particle Swarm Central

  • Clerc M, Kennedy J (2002) The particle swarm-explosion, stability, and convergence in a multidimensional complex space. Evol Comput, IEEE Trans 6(1):58–73

    Article  Google Scholar 

  • Cleveland WS, Grosse E, Shyu WM (1992) Local regression models. Statistical models in S pp 309–376

  • Cleveland WS (1979) Robust locally weighted regression and smoothing scatterplots. J Am Stat Assoc 74(368):829–836

    Article  MathSciNet  MATH  Google Scholar 

  • Cleveland W, Devlin S (1988) Locally weighted regression: an approach to regression analysis by local fitting. J Am Stat Assoc 83(403):596–610

    Article  MATH  Google Scholar 

  • DEoptim: Global optimization by differential evolution. http://cran.r-project.org/web/packages/DEoptim/ (2014a)

  • DESMO-J: A framework for discrete-event modeling and simulation. http://desmoj.sourceforge.net/ (2014b)

  • Emeakaroha VC, Brandic I, Maurer M, Breskovic I (2011) Sla-aware application deployment and resource allocation in clouds. In: Computer Software and Applications Conference Workshops (COMPSACW), 2011 IEEE 35th Annual, IEEE, pp 298–303

  • Feng G, Garg S, Buyya R, Li W (2012) Revenue maximization using adaptive resource provisioning in cloud computing environments. In: Proceedings of the 2012 ACM/IEEE 13th International Conference on Grid Computing, IEEE Computer Society, pp 192–200

  • Fitting linear models, lm stats, R Documentation. http://stat.ethz.ch/R-manual/R-patched/library/stats/html/lm.html (2014c)

  • Gehlsen B, Page B (2001) A framework for distributed simulation optimization. In: Proceedings of the 33nd conference on Winter simulation, IEEE Computer Society, pp 508–514

  • Göbel J, Joschko P, Koors A, Page B (2013) The discrete event simulation framework DESMO-J: Review, comparison to other frameworks and latest development. In: ECMS, pp 100–109

  • Grefenstette JJ (1986) Optimization of control parameters for genetic algorithms. Syst, Man Cybern, IEEE Trans 16(1):122–128

    Article  Google Scholar 

  • Grinshpan L (2012) Workload characterization and transaction profiling. Queuing Models to the Rescue, Solving Enterprise Applications Performance Puzzles, pp 57–94

  • Haines S (2006) Pro Java EE 5 performance management and optimization. Apress

  • Harchol-Balter M (2013) Performance Modeling and Design of Computer Systems: Queueing Theory in Action. Cambridge University Press

  • Hintze JL, Nelson RD (1998) Violin plots: a box plot-density trace synergism. Am Stat 52(2):181–184

    Google Scholar 

  • Ibrahim S, Jin H, Lu L, He B, Wu S (2011) Adaptive disk i/o scheduling for mapreduce in virtualized environment. In: Parallel Processing (ICPP), 2011 International Conference on, IEEE, pp 335–344

  • Katchabaw MJ, Howard SL, Lutfiyya HL, Marshall AD, Bauer MA (1999) Making distributed applications manageable through instrumentation. J Syst Softw 45(2):81–97

    Article  Google Scholar 

  • Keller A, Kar G (2000) Dynamic dependencies in application service management. IBM Research Report RC 21770(97933):

  • Lazowska ED, Zahorjan J, Graham GS, Sevcik KC (1984) Quantitative system performance: computer system analysis using queueing network models. Prentice-Hall Inc

  • McGill R, Tukey JW, Larsen WA (1978) Variations of box plots. Am Stat 32(1):12–16

    Google Scholar 

  • Michalewicz Z (1996) Genetic algorithms+ data structures= evolution programs. Springer

  • Mullen KM, Ardia D, Gil DL, Windover D, Cline J (2011) DEoptim: An R package for global optimization by differential evolution. J Stat Softw 40(6):1–26

    Article  Google Scholar 

  • Nedjah N, Alba E, de Macedo Mourelle L (2006) Parallel Evolutionary Computations. Springer

  • Nelder JA, Mead R (1965) A simplex method for function minimization. Comput J 7(4):308–313

    Article  MATH  Google Scholar 

  • Neugebauer R, McAuley D (2001) Energy is just another resource: Energy accounting and energy pricing in the Nemesis OS. Hot Topics in Operating Systems, 2001. Proceedings of the Eighth Workshop on, IEEE, pp 67–72

  • Ostermann S, Plankensteiner K, Prodan R, Fahringer T (2011) GroudSim: An event-based simulation framework for computational grids and clouds. In: Euro-Par 2010 Parallel Processing Workshops, Springer, pp 305–313

  • Page B, Kreutzer W, Gehlsen B (2005) The Java simulation handbook: simulating discrete event systems with UML and Java. Shaker Verlag

  • Pedersen MEH (2010a) Good parameters for particle swarm optimization. Hvass Lab, Copenhagen, Denmark, Tech Rep HL1001

  • Pedersen MEH (2010b) Tuning & simplifying heuristical optimization. Ph.D. thesis, University of Southampton

  • Polo J, Castillo C, Carrera D, Becerra Y, Whalley I, Steinder M, Torres J, Ayguadé E (2011) Resource-aware adaptive scheduling for mapreduce clusters. In: Middleware 2011, Springer, pp 187–207

  • Pyle D (1999) Data preparation for data mining, vol 1. Morgan Kaufmann

  • Ruszczyński AP (2006) Nonlinear optimization, vol 13. Princeton University Press

  • Satman MH (2013) RCaller: A library for calling R from Java https://code.google.com/p/rcaller/

  • Satman MH (2014) RCaller: A software library for calling R from Java. Br JMath Comput Sci 4:2188–2196

    Article  Google Scholar 

  • Sikora TD, Magoulas GD (2014a) Finding relevant dimensions in application service management control. In: Intelligent Systems for Science and Information, Springer, pp 335–353

  • Sikora TD, Magoulas GD (2014b) Search-guided activity signals extraction in application service management control. In: Computational Intelligence (UKCI), 2014 14th UK Workshop on, IEEE, pp 1–8

  • Sikora TD, Magoulas GD (2013) Neural adaptive control in application service management environment. Evol Syst 4(4):267–287

    Article  Google Scholar 

  • Sironi F, Bartolini DB, Campanoni S, Cancare F, Hoffmann H, Sciuto D, Santambrogio MD (2012) Metronome: operating system level performance management via self-adaptive computing. In: Design Automation Conference (DAC), 2012 49th ACM/EDAC/IEEE, IEEE, pp 856–865

  • Storn R, Price K (1997) Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim 11(4):341–359

  • Sydor MJ (2010) APM Best Practices: Realizing Application Performance Management. Apress

  • Tenorio F, Tenorio MF (2013) Package gaoptim http://cran.r-project.org/web/packages/gaoptim/

  • Weng C, Liu Q, Yu L, Li M (2011) Dynamic adaptive scheduling for virtual machines. In: Proceedings of the 20th international symposium on High performance distributed computing, ACM, pp 239–250

  • Wickham H (2009) ggplot2: elegant graphics for data analysis. Springer

  • Wilkinson G, Rogers C (1973) Symbolic description of factorial models for analysis of variance. Applied Statistics pp 392–399

  • Wright S, Nocedal J (1999) Numerical optimization, vol 2. Springer New York

  • Yoo S, Kim S (2013) Sla-aware adaptive provisioning method for hybrid workload application on cloud computing platform. In: Proceedings of the international multiconference of engineers and computer scientists, IMECS 2013, international conference on computer science (IAENG), pp 203–207

Download references

Acknowledgments

This work was partially supported by Solid Software Solutions.

Author information

Authors and Affiliations

  1. Department of Computer Science and Information Systems, Birkbeck, University of London, Malet Street, WC1E 7HX, London, UK

    Tomasz D. Sikora & George D. Magoulas

Authors
  1. Tomasz D. Sikora
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. George D. Magoulas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tomasz D. Sikora.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Communicated by D. Neagu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sikora, T.D., Magoulas, G.D. Evolutionary approaches to signal decomposition in an application service management system. Soft Comput 20, 3063–3084 (2016). https://doi.org/10.1007/s00500-015-1936-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-015-1936-6

Keywords

Search

Navigation