The article presents the usage of the SaaS cloud computing model in "intelligent house" systems for optimization of computation load between the client and server parts of the system. Also was developed artificial neural network model for detection of irrational electricity usage by devices of the "intellectual house".
Słowa kluczowe: SaaS, intelligent house, artificial neural network, machine learning, control system structure.
W artykule przedstawiono zastosowanie modelu przetwarzania w chmurze SaaS w systemach "inteligentnego domu" dо optymalizacji obciążenia obliczeniowego między klientem a elementami serwerowymi systemu. Opracowano także model sztucznej sieci neuronowej, aby wykryć nieracjonalne zużycie energii elektrycznej przez urządzenia "inteligentnego domu".
Keywords: automatyka domowa,.sieć neuronowa, uczenie maszynowe, struktura systemu kontroli
In our days there are typical problems arise in process of smart houses development regardless of the type and system functionality [1, 2]. These problems arise at all steps of development, as on design process of the system and on the processes of integration and support [3, 4]. These common problems consist of system fixing, scaling, and functionality updates, the high cost of integration and support. The key role in avoidance of these problems plays the right choice of architectural implementation and information model of the intelligent building . The usage of cloud computing SaaS (Software as a service) model creates the process of integration and support easier and cheaper. This solution is a complex combination of existing intelligent house control systems, where the main controller based on a microcomputer that controls all functions independently by itself and other systems that send sensor data parameters to the remote server and change intelligent house devices settings that are calculated on the server side according to current sensor parameters. Investigation of the scientific articles [6, 7, 8] give no results about scientific research of architecture optimization for the intelligent house systems that use artificial intelligence algorithms. It makes current theme very actual for reducing costs on intelligent house systems integration. SaaS model basis SaaS is the most popular model of cloud computing in the last years. The main idea of this model based on users access to ready to use software, that fully supported by the provider. The provider of this model supports the software by himself without user interactions, give the user access to the functions from client devices. The main benefit of the SaaS model for users is the absence of expenses for installation, upgrades, and support of the software. From the developer side, this service delivery model can effectively oppose to unlicensed use of software, [...]
 Biljana L. Risteska Stojkoska, Kire V. Trivodaliev, “A review of the Internet of Things for smart home: Challenges and solutions", Journal of Cleaner Production, Vol. 140, Part 3, 1 January 2017, pp.1454-1464.  Teslyuk V., Beregovskyi V., Denysyuk P., Teslyuk T., Lozynskyi A. Development and Implementation of the Technical Accident Prevention Subsystem for the Smart Home System // International Journal of Intelligent Systems and Applications(IJISA), Vol.10, No.1, 2018, pp.1-8. DOI: 10.5815/ijisa.2018.01.01.  Amit Badlani, Surekha Bhano, “Smart Home System Design based on Artificial Neural Networks", in Proceedings of the World Congress on Engineering and Computer Science 2011, San Francisco, USA, October 19-21, 2011, pp. 106-111.  Kazarian A., Teslyuk V., Tsmots I., Mashevska M. “Units and structure of automated “smart" house system using machine learning algorithms" in Proceeding of the 14th International Conference The Experience of Designing and Application of Cad Systems in Microelectronics, CADSM’2017, 21-25 February 2017, Polyana, Lviv, Ukraine. 2017. - P. 364 - 366.  Y. Liu, B. Qiu, X. Fan, H. Zhu, B. Han, “Review of Smart Home Energy Management Systems.", Energy Procedia, Vol. 104, pp. 504 - 508, 2016.  A. Veit, C. Goebel, R. Tidke, C. Doblander, “Household electricity demand forecasting: benchmarking state-of-the-art methods" in Proc. of the 5th international conference on Future energy systems. Cambridge, United Kingdom, pp. 233-234, June 11 - 13, 2014.  Jui-Sheng Chou, Dac-Khuong Bui, “Modeling heating and cooling loads by artificial intelligence for energy-efficient building design", Energy and Buildings Volume 82, pp. 437- 446, October 2014.  L. Magnier, F. Haghighat, “Multiobjective optimization of building design using TRNSYS simulations, genetic algorithm, and Artificial Neural Network", Building and Environment, Volume 45, Issue 3, pp. 739-746, March 2010.  G. Eason, B. Noble, and I.N. Sneddon, “On certain integrals of Lipschitz-Hankel type involving products of Bessel functions," Phil. Trans. Roy. Soc. London, vol. A247, pp. 529-551, April 1955.  J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68-73.  I.S. Jacobs and C.P. Bean, “Fine particles, thin films and exchange anisotropy," in Magnetism, vol. III, G.T. Rado and H. Suhl, Eds. New York: Academic, 1963, pp. 271-350.  Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, “Electron spectroscopy studies on magneto-optical media and plastic substrate interface," IEEE Transl. J. Magn. Japan, vol. 2, pp. 740-741, August 1987 [Digests 9th Annual Conf. Magnetics Japan, p. 301, 1982].  Magali, R.G., Meireles, P.E.M. and Marcelo, G.S. (2003) A Comprehensive Review for Industrial Applicability of Artificial Neural Networks. IEEE Transactions on Industrial Electronics, 50, 585-601.  Tobias Teich, Falko Roessler, Daniel Kretz, Susan Frank. “Design of a Prototype Neural Network for Smart Homes and Energy Efficiency" in Proceedings of 24th DAAAM International Symposium on Intelligent Manufacturing and Automation, Zwickau, Germany, 2013, pp.603-608.  Fadare, D. and Ofidhe, U. (2009) Artificial Neural Network Model for Prediction of Friction Factor in Pipe Flow. Journal of Applied Science Research, 5, 662-670.  Pushkar S., Sanghamitra S. “Arduino-based smart irrigation using water flow sensor, soil moisture sensor, temperature sensor and ESP8266 WiFi module", in Proceeding of Humanitarian Technology Conference (R10-HTC), 2016 IEEE Region 10.  Brkić, D. and Ćojbašić, Ž. (2016) Intelligent Flow Friction Estimation. Computer Intelligence and Neuroscience, 2016, Article ID: 5242596. http://dx.doi.org/10.1155/2016/5242596  D. A. Dornfield, “Neural Network Sensor Fusion for Tool Condition Monitoring," Annals CIRP, Vol. 39, No. 1, 1990, pp. 101-105. doi:10.1016/S0007-8506(07)61012-9  Lytvyn, V., Peleshchak, I., Peleshchak, R. The compression of the input images in neural network that using method diagonalization the matrices of synaptic weight connections. 2nd International Conference on Advanced Information and Communication Technologies, AICT 2017 - Proceedings. 2017.  Geche, F., Kotsovsky, V., Batyuk, A. Synthesis of the integer neural elements. Proceedings of the International Conference on Computer Sciences and Information Technologies, CSIT 2015. - Lviv, 2015. - P. 63 - 66.  P. Tymoshchuk and S. Shatnyi, “KWTA Neural Network Hardware Implementation Using FPGA for Signals Classification", in Proc. IX-th Int. Conf. “Perspective technologies and methods in MEMS design", Polyana- Svalyava, Ukraine, June 22-24, 2014, pp. 82-85.  Yazdi, M. and Bardi, A. (2011) Estimation of Friction Factor in Pipe Flow Using Artificial Neural Network. Canadian Journal on Automation, Control and Intelligent Systems, 2, pp. 52-56