Modeling of environmental monitoring data processing  in a cloud infrastructure

by

A.V. Skatkov, V.I. Shevchenko,  E.N. Mashchenko, O.V. Chengar

 Sevastopol State University, RF, Sevastopol, Universitetskaya St., 33

E-mail: maschenko@sevsu.ru

DOI: 10.33075/2220-5861-2021-3-79-88

UDC 004.94  

Abstract:

   A model of a cloud-based system for processing environmental monitoring data is proposed. The model takes into account the multi-tier web applications and the heterogeneity of the input flow of applications. As a characteristic of the efficiency of the data processing system, an additive criterion is chosen that takes into account the volume of processed requests and the load on the resources of the cloud infrastructure, as well as restrictions on the response time of the system to the user requests specified in the Service Level Agreement (SLA). The following data processing scenarios are implemented in the model: 1) priority servicing of functional data processing tasks; 2) applications are serviced on a first-come, first-served basis according to the FIFO principle (provision of a buffer for storing data of unlimited capacity); 3) a data processing system with failures in the absence of free virtual machines. The simulation model calculates the following performance characteristics: average load of nodes in the cloud infrastructure of environmental monitoring; the average amount of memory occupied by data; the average number of requests processed during the working day; the average number of requests that were denied due to non-compliance with the SLA. A number of parametric experiments have been  carried out, according to the results of which it is found that with an increase in the intensity of the arrival of tasks, the strategy of increasing the storage buffer gives greater efficiency.

   The approach under consideration will allow creating a basis for modeling the processes occurring in natural-technical systems (NTS), analyze data processing processes during monitoring of key performance indicators of NТS and ensure that these indicators meet the requirements specified in SLA agreements through the use of alternative data processing strategies. The developed model can be used as an element of a decision support system for organizing effective management of resource allocation in cloud computing environments when solving problems of environmental monitoring data processing.

Keywords: environmental monitoring, modeling of complex systems, cloud computing, big data, data mining.

To quote:

Full text in PDF(RUS)

REFERENCES

  1. Belikova M.Ju., Karanina S.Ju., Karanin A.V. and Glebova A.V. Vizualizacija i analiz dannyh seti WWLLN na territorii Altae-Sajanskogo regiona sredstvami veb-GIS // Kibernetika i programmirovanie. 2019. No 2,1–8.
  2. Kadochnikov A.A. Instrumenty sbora dannyh dlja geoinformacionnoj sistemy monitoringa okruzhajushhej prirodnoj sredy // Reshetnevskie chtenija. 2018. No 2, 269–270.
  3. Koshkarev A.V., Rjahovskij V.M. and Serebrjakov V.A. Infrastruktura raspredelennoj sredy hranenija, poiska i preobrazovanija prostranstvennyh dannyh. // Otkrytoe obrazovanie. 2010. No 5, 61–73.
  4. Titov A.G., Okladnikov I.G.and Gordov E.P. Razrabotka Veb-GIS na osnove servisov obrabotki i vizualizacii prostranstvennyh dannyh dlja analiza i prognozirovanija regional’nyh klimaticheskih izmenenij // Informacionnye i matematicheskie tehnologii v nauke i upravlenii. 2016. No 4-2, 96–109.
  5. Voronin D., Shevchenko V., Chengar O, Mashchenko E. Conceptual Big Data processing model for the tasks of Smart Cities environmental monitoring // DTGS 2019: Digital Transformation and Global Society. Communications in Computer and Information Science. Cham: Springer. 2019. Vol. 1038, 212–222
  6. Vysokoproizvoditel’nyye tekhnologii ekstrennykh vychisleniy dlya predotvrashcheniya ugrozy navodneniy / A.V. Bukhanovskiy, A. N. Zhitnikov, S. G. Petrosyan [i dr.] // Izv. vuzov. Priboro-stroyeniye. 2011. Vol. 54, No 10, 14–20.
  7. Uzhinskiy A., Ososkov G., Frontas’yeva M. Upravleniye dannymi monitoringa okruzhayushchey sredy // Otkrytyye sistemy. SUBD.   No 4,  pp. 42–43.
  8. Arkhipova O.Ye., Surkov F.A. Predstavleniye bol’shikh dannykh v zadachakh podderzhki prinyatiya resheniy po obespecheniyu ustoychivogo razvitiya regiona // Matematicheskiye metody raspoznavaniya obrazov. 2017. Vol. 18. No 1, 78–79.
  9. Ob utverzhdenii Koncepcii postroenija i razvitija APK «Bezopasnyj gorod», utv. Rasporjazheniem Pravitel’stva Rossijskoj Federacii 03.12.2014. No 2446-r. [Jelektronnyj resurs]. Rezhim dostupa: http://14.mchs.gov.ru/document /2632303 (data obrashhenija: 23.07.2021).
  10. Skatkov A.V., Brjuhoveckij A.A. and Shishkin Ju.E. Razrabotka intellektual’noj tehnologii obnaruzhenija anomalij jekosistem akvatorii g. Sevastopolja // Sistemy kontrolja okruzhajushhej sredy. 2019. Vol. 1 (35), 27–34.
  11. NIST Special Publication 1500-1r1 NIST Big Data Interoperability Framework: Volume 1, Definitions. NIST Big Data Public Working Group Definitions and Taxonomies Subgroup Version 2, June 2018. URL: https://doi.org/10.6028/NIST.SP.1500-1r1. (data obrashhenija: 22.07.2021).
  12. NIST Special Publication 1500-6r1. NIST Big Data Interoperability Framework: Volume 6, Reference Architecture NIST Big Data. Public Working Group Reference Architecture Subgroup, Version 2, June 2018. URL: https://doi.org/10.6028/NIST.SP.1500-6r1. (data obrashhenija: 22.07.2021).
  13. Shevchenko D.D., Chengar O.V. and Shevchenko V.I. Ispol’zovanie diskretno-sobytijnogo podhoda dlja modelirovanija processov obrabotki dannyh v oblachnyh korporativnyh sistemah // Sbornik statej Vserossijskoj nauchno-tehnicheskoj konferencii «INFOTEH-2019». 2019, pp. 34–38.
  14. Boyev V. D. Imitatsionnoye modelirovaniye system.   : Izdatel’stvo Yurayt, 2017. 253 p.
  15. Andrei Borshchev, Ilya Grigoryev. The Big Book of Simulation Modeling. Multimethod Modeling with AnyLogic. https://www.anylogic.ru/rsources/books/big-book-of-simulation-modeling/ (data obrashhenija: 07.2021).

Loading