1. UJIT
  2. All Volumes and Issues
  3. Volume 3 · Number 1
  4. SELECTION OF THE OPTIMAL STRUCTURE OF HIDDEN LAYERS OF THE ARTIFICIAL NEURAL NETWORK FOR ENERGY EFFICIENCY ANALYSIS

SELECTION OF THE OPTIMAL STRUCTURE OF HIDDEN LAYERS OF THE ARTIFICIAL NEURAL NETWORK FOR ENERGY EFFICIENCY ANALYSIS

UJIT.
2021;
Volume 3, Number 1
: 30-36
https://doi.org/10.23939/ujit2021.03.030
Received: March 19, 2021
Accepted: June 01, 2021

Цитування за ДСТУ: Казарян А. Г., Теслюк В. М., Казимира І. Я. Вибір оптимальної структури прихованих шарів штучної нейрон­ної мережі для аналізу ефективності енергоспоживання. Український журнал інформаційних технологій. 2021, т. 3, № 1. С. 30–36.

Citation APA: Kazarian, A. G., Teslyuk, V. M., & Kazymyra, I. Ya. (2021). Selection of the optimal structure of hidden layers of the artificial neural network for energy efficiency analysis. Ukrainian Journal of Information Technology, 3(1), 30–36. https://doi.org/10.23939/ujit2021.03.030

Authors:
  1. A. G. Kazarian
  2. Vasyl Teslyuk
  3. I. Ya. Kazymyra
1
Lviv Polytechnic National University, Lviv, Ukraine
2
Lviv Polytechnic National University, Lviv, Ukraine
3
Lviv Polytechnic National University, Lviv, Ukraine

A method for optimal structure selection of hidden layers of the artificial neural network (ANN) is proposed. Its main idea is the practical application of several internal structures of ANN and further calculation of the error of each hidden layer structure using identical data sets for ANN training. The method is based on the alternate comparison of the expected result values and the actual results of the feedforward artificial neural networks with a different number of inner layers and a different number of neurons on each layer. The method afforces searching the optimal internal structure of ANN for usage in the development of "smart" house systems and for calculation of the optimal energy consumption level in accordance with current conditions, such as room temperature, presence of people, and time of the day. The usage of the presented method allows to reduce the time spent on choosing the effective structure of the artificial neural network at the initial stages of research and to pay more attention to the relationship between the input and output data, as well as to such important parameters of the ANN learning process, as a number of training iterations, minimal training error, etc. The software has been developed that allows to carry out the processes of training, testing, and obtaining the output results of the algorithm of the artificial neural network, such as the expected value of power consumption and operating time of each individual appliance. The disadvantage of the approach used in finding the optimal internal structure of the artificial neural network is that each subsequent structure is created on the basis of the most efficient of the previously created structures without analyzing other structures that showed worse results with fewer hidden layers. It was found that to improve the solution of this problem it is necessary to create a mechanism which will be based on the analysis of input data, output data, will analyze the internal relationships between parameters and will optimize the network structure at each stage using certain logical rules according to the results obtained in the previous step. It is established that this problem is a nonlinear programming problem that can be solved in the further development of this study.

selection method
hidden layers
"розумний" будинок
оптимізація енергоспоживання
Artificial Neural Network (ANN)
  1. Das, S., Dai, R., Koperski, M., Minciullo, L., Garattoni, L., & Francesca, G. (2019). Toyota Smarthome: Real-World Activities of Daily Living. IEEE/CVF International Conference on Computer Vision (ICCV), 27 Oct.-2 Nov. 2019, Seoul, Korea (South), 833–842. https://doi.org/10.1109/ICCV.2019.00092
  2. Ding, F., Song, A., Tong, E., & Li, J. (2016). A Smart Gateway Architecture for Improving Efficiency of Home Network Applications. Journal of Sensor 2016. https://doi.org/10.1155/2016/2197237
  3. Ge, M., Bangui, H., & Buhnova, B. (2018). Big Data for Internet of Things: A Survey. Future Generation Computer Systems, 87, 601–614. https://doi.org/10.1016/j.future.2018.04.053
  4. Izonin, I., Tkachenko, R., Kryvinska, N., Zub, K., Mishchuk, O., & Lisovych, T. Recovery of Incomplete IoT Sensed Data using High-Performance Extended-Input Neural-Like Structure. Procedia Computer Science, 160, 521–526.  https://doi.org/10.1016/j.procs.2019.11.054
  5. Kalaiprasath, R., & Sakthivel, C. (2016). A Comparative Review On Internet Protocol Version 6 (IPv6). International Journal of Advanced Research, 4(2), 1076–1078.
  6. Karansingh, C., Shreena, J., Dhrumin, T., Jitendra, R., Sudeep, T., & Mohammad, O. (2020). Automated Machine Learning: The New Wave of Machine Learning. 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 5–7 March 2020, Bangalore, India, 205–212. https://doi.org/10.1109/ICIMIA48430.2020.9074859
  7. Kazarian, A., Teslyuk, V., Tsmots, I., & Mashevska, M. (2017). Units and structure of automated "smart" house system using machine learning algotithms. Proceeding of the 14 th International Conference "The Experience of Designing and Application of Cad Systems in Microelectronics", CADSM2017, 21–25 February 2017, Polyana, Lviv, Ukraine, 364–366. https://doi.org/10.1109/CADSM.2017.7916151
  8. Kotsovsky, V., Geche, F., & Batyuk, A. (2015). Artificial complex neurons with half-plane-like and angle-like activation function. In Proceedings of the Xth International Scientific and Technical Conference "Computer Sciences and Information Technologies" (CSIT), Lviv, Ukraine, 2015, 57–59. https://doi.org/10.1109/STC-CSIT.2015.7325430
  9. Mao, J., Lin, Q., & Bian, J. (2018). Application of Learning Algorithms in Smart Home IoT System Security. American Institute of Mathematical Sciences. DOI: 10.3934/mfc.2018004. https://doi.org/10.3934/mfc.2018004
  10. Mishchuk, O., Tkachenko, R., Izonin, I. (2020). Missing Data Imputation Through SGTM Neural-Like Structure for Environmental Monitoring Tasks. In: Hu Z., Petoukhov S., Dychka I., He M. (eds) Advances in Computer Science for Engineering and Education II. ICCSEEA 2019. Advances in Intelligent Systems and Computing, 938, 142–151. Springer, Cham. https://doi.org/10.1007/978-3-030-16621-2_13
  11. Mokhtari, G., Anvari-Moghaddam, A., & Zhang, Q. (2019). A New Layered Architecture for Future Big Data-Driven Smart Homes. IEEE Access 2019, 7, 19002–19012. https://doi.org/10.1109/ACCESS.2019.2896403
  12. Seyedzadeh, S., Rahimian, F. P., Glesk, I., & Roper, M. (2018). Machine learning for estimation of building energy consumption and performance: a review. Visualization in Engineering, 6, 5. https://doi.org/10.1186/s40327-018-0064-7
  13. Su, W., & Huang, A.Q. (2013). Proposing A Electricity Market Framework for The Energy Internet. In Proceedings of the IEEE Power and Energy Society General Meeting, Vancouver, BC, Canada, 21–25 July 2013, 1–5.
  14. Sun, Q., Yu, W., Kochurov, N., Hao, Q., & Hu, F. (2013). A Multi-Agent-Based Intelligent Sensor andActuator Network Design for Smart House and Home Automation. Journal of Sensor and Actuator Networks, 2(3), 557–588. https://doi.org/10.3390/jsan2030557
  15. Take Control over Rising Energy Costs. (2021). Sunrun Sunrun. Retrieved from: https://sunrun.com
  16. Tsoukalas, L. H., Gao, R., & Lafayette, W. (2008). Inventing An Energy Internet the Role of Anticipation in Human-Centered Energy Distribution and Utilization. In Proceedings of the 2008 SICE Annual Conference, Tokyo, Japan, 20–22 August 2008, 399–403. https://doi.org/10.1109/SICE.2008.4654687