This study acknowledges the common problem of partial shading in the PV systems. The problem of partial shading occurs due to unequal reception of solar irradiation on PV panels. It can be caused by many reasons like the sudden occurrence of clouds, tall builds or trees, etc. Due to this condition, the PV panel experiences power loss and hotspots can arise on the panel. These hotspots can seriously degrade the life of the PV panels. Therefore, to counteract this problem many methods are developed. Recently a lot of work is being on utilizing machine learning methods for partial shading problems in PV systems.

In this thesis, two supervised machine learning algorithms based on a neural network known as a nonlinear autoregressive exogenous model (NARX) and long short-term memory (LSTM) are used for parameter estimation of the power converter and prediction of the shaded panel location in PV system, respectively. These methods are used in this thesis because they are simple to implement, provides high generalization performance, and helps in mitigating vanishing gradient problem. The model was trained on MATLAB Simulink and tested on experimental setup data. Both these methods provided satisfying performance in terms of accuracy and validation loss. This research successfully predicts the shading panel location, which provides an advantage for solving problems in the field, such as finding the shading location when repairing, which makes repair costs expensive. Besides, this research can also predict the existing electronic components useful in monitoring and repairing the system.

REFERENCE
[1] G. Shaddick, M. L. Thomas, P. Mud, G. Ruggeri and S.gumy, “Half the world population are exposed to increasing air pollution,” npj Climate and Atmospheric Science, 2020. [Online]. Available: https://www.nature.com/articles/s41612-020-0124-2#citeas
[2] A. Haque and Zaheeruddin, “Research on solar photovoltaic (pv) energy conversion system: An overview,” in Third International Conference on Computational Intelligence and Information Technology (CIIT 2013), 2013, pp. 605 611.
[3] A. Jager-Waldau, PV Status Report 2019, 2019.
[4] I. S. Millah, R. K. Subroto, Y. W. Chang, K. L. Lian, and B. R. Ke, “Investigation of maximum power point tracking of different kinds of solar panels under partial shading conditions,” IEEE Transactions on Industry Applications, vol. 57, no. 1, pp. 17 25, 2021.
[5] M. L. K. Parimita Mohanty,Tariq Muneer, “Solar Photovoltaic System Applications: A Guidebook for Off-Grid Electrification. Springer International Publishing, 2016. [Online].Available:https://www.springer.com/gp/book/
[6] M. H. Radhi, E. J. Mahdi, and A. K. Mftwol, “Design and performance analysis of solar pv system size 2.56 kwp,” in 2019 4th Scientific International Conference Najaf (SICN), 2019, pp. 70 73.
[7] V. V. Boldyrev, M. A. Gorkavyy, and D. B. Solovev, “Designing an adaptive software and hardware complex for converting solar energy,” in 2019 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon), 2019, pp. 1 4.
[8] A. A. S. Mohamed, A. Berzoy, and O. A. Mohammed, “Design and hardware implementation of fl-mppt control of pv systems based on ga and small-signal analysis,” IEEE Transactions on Sustainable Energy, vol. 8, no. 1, pp. 279 290, 2017.
[9] S. Park, S. Kim, S. Jang, G. Kim, H. Seo, M. Park, and I. Yu, “Hardware implementation of optimization technique based sensorless mppt method for grid-connected pv generation system,” in 2009 International Conference on Electrical Machines and Systems, 2009, pp. 1 6.
[10] C. Y. Liao, R. K. Subroto, I. S. Millah, K. L. Lian, and W. Huang, “An improved bat algorithm for more efficient and faster maximum power point tracking for a photovoltaic system under partial shading conditions,” IEEE Access, vol. 8, pp. 96378 96390, 2020.
[11] B. H. Wijaya, R. K. Subroto, K. L. Lian, and N. Hariyanto, “A maximum power point tracking method based on a modified grasshopper algorithm combined with incremental conductance,” energies, vol. 13, no. 17, 2020.
[12] D. A. Nugraha, K. L. Lian, and Suwarno, “A novel mppt method based on cuckoo search algorithm and golden section search algorithm for partially shaded pv system,” Canadian Journal of Electrical and Computer Engineering, vol. 42, no. 3, pp. 173 182, 2019.
[13] S. Kurtz, “Reliability and durability of pv modules,” pp. 491 501,[Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/ 9781118927496.ch44
[14] A. Azizi, P.-O. Logerais, A. Omeiri, A. Amiar, A. Charki, O. Riou, F. Delaleux, and J.-F. Durastanti, “Impact of the aging of a photovoltaic module on the performance of a grid-connected system,” Solar Energy, vol. 174, pp. 445 454, 2018. [Online]. Available: http://www.sciencedirect.com/science/article/ pii/S0038092X18308934
[15] M. S. Arani and M. S. A. and, “The comprehensive study of electrical faults in pv arrays,” Journal of electrical and computer engineering, 2016. [Online]. Available: https://www.hindawi.com/journals/jece/2016/8712960/
[16] A. Mellit, G. Tina, and S. Kalogirou, “Fault detection and diagnosis methods for photovoltaic systems: A review,” Renewable and Sustainable Energy Reviews, vol. 91, pp. 1-17, 2018. [Online]. Available: http: //www.sciencedirect.com/science/article/pii/S1364032118301370
[17] P. Bauwens and J. Doutreloigne, “Reducing partial shading power loss with an integrated smart bypass,” Solar Energy, vol. 103, pp. 134-142,2014. [Online]. Available: http://www.sciencedirect.com/science/article/pii/ S0038092X14000693
[18] Amin, Hajizadeh and Jishnu, Warrier Anil Kumar, “Parameter identification and effect of partial shading on a photovoltaic system,” E3S Web Conf., vol. 64, p. 06006, 2018. [Online]. Available: https://doi.org/10.1051/e3sconf/ 20186406006
[19] Qi Zhang, Xiangdong Sun, Yanru Zhong, and Mikihiko Matsui, “A novel topology for solving the partial shading problem in photovoltaic power generation system,” in 2009 IEEE 6th International Power Electronics and Motion Control Conference, 2009, pp. 2130 2135.
[20] Guichun Huang and Baina Heand Fanyu Meng, “Evaluation of a multi-objective model in energy generation under the influence of different hydrological conditions based on moth search algorithm,” International Journal of Ambient Energy, p. 1, 2020. [Online]. Available: https://www.spiedigitallibrary.org/journals/journal-of-photonics-for-energy/volume-10/issue-04/042004/Improving-performance-of-photovoltaic-panel-by-recongurability-in-partial-shading/10.1117/1.JPE.10.042004.full?SSO=1&tab=ArticleLinkCited
[21] F. P. D. Eduardo Nieto, Ruiz, “Characterization of electric faults in photovoltaic array systems,” DYNA, vol. 86, pp. 54 63, 12 2019. [Online]. Available: http://www.scielo.org.co/scielo.php?script=sci_arttext&
[22] T. Pei and X. Hao, “A Fault Detection Method for Photovoltaic Systems Based on Voltage and Current Observation and Evaluation,” energies, 2019. [Online]. Available: https://www.mdpi.com/1996-1073/12/9/1712#cite
[23] M. Pau, R. Mahalakshmi, M. Karuppasamypandiyan, A. Bhuvanesh, and R. J. Ganesh, “Classification and detection of faults in grid connected photovoltaic system,” 2016.
[24] H. Zhang, X. Li, and J. Harlim,” A parameter estimation method using linear response statistics: Numerical scheme,” Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 29, no. 3, p. 033101, 2019. [Online]. Available: https://doi.org/10.1063/1.5081744
[25] E. M. Cimpoesu, B. D. Ciubotaru, and D. Stefanoiu, “Fault detection and diagnosis using parameter estimation with recursive least squares,” in 2013 19th
International Conference on Control Systems and Computer Science, 2013, pp.
18-23.
[26] P. Savsani, R. L. Jhala, and V. J. Savsani, “Comparative study of different metaheuristics for the trajectory planning of a robotic arm,” IEEE Systems Journal, vol. 10, no. 2, pp. 697 708, June 2016.
[27] E.-G. Talbi, Metaheuristics: From Design to Implementation. Wiley Publishing, 2009.
[28] X.-S. Yang, “Metaheuristic optimization: Algorithm analysis and open problems,” in Experimental Algorithms, P. M. Pardalos and S. Rebennack, Eds.
Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 21 32.
[29] ---, Nature-Inspired Computation in Engineering - 2016. Wiley Publishing, 2016.
[30] A. A. Z. Diab, H. M. Sultan, T. D. Do, O. M. Kamel, and M. A. Mossa,”Coyote optimization algorithm for parameters estimation of various models of solar cells and pv modules,” IEEE Access, vol. 8, pp. 111102 111140, 2020.
[31] A. Aissaoui, N. Belhaouas, F. Hadjrioua, K. Bakria, and I. Aloui, “Parameter extraction of two-diode solar pv model using ann-ga approach,” in Artificial Intelligence and Renewables Towards an Energy Transition, M. Hatti, Ed. Cham:
Springer International Publishing, 2021, pp. 592 603.
[32] R. Isermann, “Process fault detection based on modeling and estimation methods a survey,” Automatica, vol. 20, no. 4, pp. 387 404, 1984. [Online]. Available: http://www.sciencedirect.com/science/article/pii/0005109884900980
[33] M. S. Z. Abidin, R. Yusof, M. Kahlid, and S. M. Amin, “Application of a model-based fault detection and diagnosis using parameter estimation and fuzzy inference to a dc-servomotor,” in Proceedings of the IEEE Internatinal Symposium on Intelligent Control, 2002, pp. 783 788.
[34] E. Garoudja, F. Harrou, Y. Sun, K. Kara, A. Chouder, and S. Silvestre, “Statistical fault detection in photovoltaic systems,” Solar Energy, vol. 150, pp. 485 499, 2017. [Online]. Available: http://www.sciencedirect.com/science/ article/pii/S0038092X17303377
[35] F. Salem and M. A. Awadallah, “Parameters estimation of photovoltaic modules: comparison of ann and anfis,” International Journal of Industrial Electronics and Drives, 2014.
[36] B. Basnet, H. Chun, and J. Bang, An Intelligent Fault Detection Model for Fault Detection in Photovoltaic Systems, 2020.
[37] E. I. Batzelis, S. A. Papathanassiou, and B. C. Pal, “Pv system control to provide active power reserves under partial shading conditions,” IEEE Transactions on Power Electronics, vol. 33, no. 11, pp. 9163 9175, 2018.
[38] R. K. Jones, A. Baras, A. A. Saeeri, A. Al Qahtani, A. O. Al Amoudi, Y. Al Shaya, M. Alodan, and S. A. Al-Hsaien, “Optimized cleaning cost and schedule based on observed soiling conditions for photovoltaic plants in central saudi arabia,” IEEE Journal of Photovoltaics, vol. 6, no. 3, pp. 730 738, 2016.
[39] F. Spertino, E. Chiodo, A. Ciocia, G. Malgaroli, and A. Ratclif, “Maintenance activity, reliability, availability, and related energy losses in ten operating photovoltaic systems up to 1.8 mw”, IEEE Transactions on Industry Applications, vol. 57, no. 1, pp. 83 93, 2021.
[40] F. Salem and M. A. Awadallah, “Detection and assessment of partial shading in photovoltaic arrays, “ Journal of Electrical Systems and Information Technology, vol. 3, no. 1, pp. 23 32, 2016. [Online]. Available:http://www.sciencedirect.com/science/article/pii/S2314717216300058
[41] O. Kulinich, N. N. Sadova, and A. A. Lisovskaya, “Analysis of the causes of field-effect and photovoltaic semiconductor device parameters degradation,” in Proceedings IECON 91: 1991 International Conference on Industrial Electronics, Control and Instrumentation, 1991, pp. 653 655 vol.1.
[42] M. Malinowski, J. I. Leon, and H. Abu-Rub, “Solar photovoltaic and thermal energy systems: Current technology and future trends,” Proceedings of the IEEE, vol. 105, no. 11, pp. 2132 2146, Nov 2017.
[43] S. Modi, K. Kevin, and P. Usha, “Mathematical modeling, simulation and performance analysis of solar cell,” in 2018 International Conference on Power Energy, Environment and Intelligent Control (PEEIC), 2018, pp. 730 734.
[44] P. Guerriero, P. Tricoli, and S. Daliento, “A bypass circuit for avoiding the hot spot in pv modules,” Solar Energy, vol. 181, pp. 430 438, 2019. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0038092X19301355
[45] S. Daliento, F. D. Napoli, P. Guerriero, and V. dAlessandro, “A modified bypass circuit for improved hot spot reliability of solar panels subject to partial shading, “ Solar Energy, vol. 134, pp. 211 218, 2016. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0038092X16300810
[46] A. Chakri, R. Khelif, M. Benouaret, and X.-S. Yang, “New directional bat algorithm for continuous optimization problems, Expert Systems with Applications,” vol. 69, pp. 159 175, 2017. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0957417416305905
[47] O. Bingol and B. Ozkaya, “Analysis and comparison of different pv array con gurations under partial shading conditions,” Solar Energy, vol. 160, pp. 336 343, 2018. [Online]. Available: http://www.sciencedirect.com/science/ article/pii/S0038092X17310769
[48] M. A. Ghasemi, H. Mohammadian Foroushani, and M. Parniani, “Partial shading detection and smooth maximum power point tracking of pv arrays under psc,” IEEE Transactions on Power Electronics, vol. 31, no. 9, pp. 6281 6292, Sep. 2016.
[49] H. Li, D. Yang, W. Su, J. L, and X. Yu, “An overall distribution particle swarm optimization mppt algorithm for photovoltaic system under partial shading,” IEEE Transactions on Industrial Electronics, vol. 66, no. 1, pp. 265 275, Jan 2019.
[50] J. D. Navamani, M. L. Veena, A. Lavanya, and K. Vijayakumar, “Efficiency comparison of quadratic boost dc-dc converter in ccm and dcm,” in 2015 2nd International Conference on Electronics and Communication Systems (ICECS), 2015, pp. 1156 1161.
[51] B. C. Barry, J. G. Hayes, M. S. Ryiko, and J. W. Maslon, “Discontinuous conduction mode operation of the two-phase integrated-magnetic boost converter,” in 2014 IEEE Energy Conversion Congress and Exposition (ECCE), 2014, pp. 5782 5789.
[52] S. Das and M. J. Nene, “A survey on types of machine learning techniques in intrusion prevention systems,” in 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 2017, pp.
2296 2299.
[53] A. Singh, N. Thakur, and A. Sharma, “A review of supervised machine learning algorithms,” in 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), 2016, pp. 1310 1315.
[54] N. Amruthnath and T. Gupta, “A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance,” in 2018 5th International Conference on Industrial Engineering and Applications (ICIEA), 2018, pp. 355 361.
[55] W. Qiang and Z. Zhongli, “Reinforcement learning model, algorithms and its application,” in 2011 International Conference on Mechatronic Science, Electric Engineering and Computer (MEC), 2011, pp. 1143 1146.
[56] J. Hsu, J. Chang, M. Cho, Y. Wu, W. Chang, and C. Wang, “Development of regression models for prediction of electricity by considering prosperity and climate,” in 2016 3rd International Conference on Green Technology and Sustainable Development (GTSD), 2016, pp. 112 115.
[57] H. Alonso, H. Magalhaes, T. Mendonca, and P. Rocha, “A hybrid method for parameter estimation,” in IEEE International Workshop on Intelligent Signal Processing, 2005., 2005, pp. 304 309.
[58] F. Stoter, S. Chakrabarty, B. Edler, and E. A. P. Habets, “Classification vs.
regression in supervised learning for single channel speaker count estimation,” in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 436 440.
[59] Hai-Wen Chen, “Modeling and identification of parallel nonlinear systems:
structural classification and parameter estimation methods,” Proceedings of the IEEE, vol. 83, no. 1, pp. 39 66, 1995.
[60] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector machines,” IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18 28, 1998.
[61] D. R. Hush and B. G. Horne, “Progress in supervised neural networks,” IEEE Signal Processing Magazine, vol. 10, no. 1, pp. 8 39, 1993.
[62] S. Ghosh, A. Dasgupta, and A. Swetapadma, “A study on support vector machine based linear and non-linear pattern classification,” in 2019 International Conference on Intelligent Sustainable Systems (ICISS), 2019, pp. 24 28.
[63] M. S. Alam and S. T. Vuong, “Random forest classification for detecting android malware,” in 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, 2013, pp. 663 669.
[64] I. Povkhan and M. Lupei, “The algorithmic classification trees,” in 2020 IEEE
Third International Conference on Data Stream Mining Processing (DSMP), 2020, pp. 37 43.
[65] M. Kayri, I. Kayri, and M. T. Gencoglu, “The performance comparison of multiple linear regression, random forest and artificial neural network by using photovoltaic and atmospheric data,” in 2017 14th International Conference on Engineering of Modern Electric Systems (EMES), 2017, pp. 1 4.
[66] A. Aamoud and A. Hammouch, “Recurrent neural network based identification and parameters estimation of induction motor,” International Review on Modelling and Simulations (IREMOS), vol. 10, no. 2, 2017, doi:10.15866/iremos.v10i2.8360. [Online]. Available: http: //www.praiseworthyprize.org/jsm/index.php?journal=iremos&page=article& op=view&path%5B%5D=18499
[67] M. S. A. Mohamad, I. M. Yassin, A. Zabidi, M. N. Taib, and R. Adnan, “Comparison between pso and ols for narx parameter estimation of a dc motor,” in 2013 IEEE Symposium on Industrial Electronics Applications, 2013, pp. 27 32.
[68] Dan Wang, Kai-Yew Lum, and Guanghong Yang, “Parameter estimation of arx/narx model: a neural network based method,” in Proceedings of the 9th
International Conference on Neural Information Processing, 2002. ICONIP 02., vol. 3, 2002, pp. 1109 1113 vol.3.
[69] T. Baldacchino, S. R. Anderson, and V. Kadirkamanathan, “Structure detection and parameter estimation for narx models in a unifed em framework,” Automatica, vol. 48, no. 5, pp. 857 865, 2012. [Online].” Available: http://www.sciencedirect.com/science/article/pii/S0005109812000726
[70] Y. Wei, J. Zhou, Y. Wang, Y. Liu, Q. Liu, J. Luo, C. Wang, F. Ren, and L. Huang,” A review of algorithm hardware design for ai-based biomedical applications,” IEEE Transactions on Biomedical Circuits and Systems, vol. 14, no. 2, pp. 145 163, 2020.
[71] T. Linzen, E. Dupoux, and Y. Goldberg, “Assessing the ability of LSTMs to learn syntax-sensitive dependencies,” Transactions of the Association for Computational Linguistics, vol. 4, pp. 521 535, 2016. [Online]. Available: https://www.aclweb.org/anthology/Q16-1037
[72] M. Xu, R. Song, Y. Zhao, B. Song, and J. Tang, “Application of narx dynamic neural network in blood glucose prediction model,” in 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS), 2020, pp. 178 183.
[73] L. Banjanovic Mehmedovic, I. Butigan, M. Kantardziz, and S. Kasapovic, “Prediction of cooperative platooning maneuvers using narx neural network,” in International Conference on Smart Systems and Technologies (SST), 2016, pp. 287 292.
[74] L. Ghiormez, M. Panoiu, C. Panoiu, and C. Pop, “Electric current prediction for the nonlinear high power loads using narx neural networks,” in 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2017, pp. 128 133.
[75] A. A. Isqeel, S. M. Eyiomika, and T. B. Ismaeel, “Consumer load prediction based on narx for electricity theft detection,” in 2016 International Conference on Computer and Communication Engineering (ICCCE), 2016, pp. 294 299.
[76] M. R. Habibi, H. R. Baghaee, T. Dragi cevi c, and F. Blaabjerg, “Detection of false data injection cyber-attacks in dc microgrids based on recurrent neural networks,” IEEE Journal of Emerging and Selected Topics in Power Electronics, pp. 1 1, 2020.
[77] Le Duc-Hung, Pham Cong-Kha, Nguyen Thi Thien Trang, and Bui Trong Tu, Parameter extraction and optimization using levenberg-marquardt algorithm, in 2012 Fourth International Conference on Communications and Electronics (ICCE), 2012, pp. 434 437.
[78] H. Chun, J. Kim, J. Yu, and S. Han, “Real-time parameter estimation of an electrochemical lithium-ion battery model using a long short-term memory network, IEEE Access, vol. 8, pp. 81789 81799, 2020.
[79] M. Seyedmahmoudian, R. Rahmani, S. Mekhilef, A. Maung Than Oo, A. Stojcevski, T. K. Soon, and A. S. Ghandhari, “Simulation and hardware implementation of new maximum power point tracking technique for partially shaded pv system using hybrid depso method,” IEEE Transactions on Sustainable Energy, vol. 6, no. 3, pp. 850 862, July 2015.
[80] G. Fang and K. Lian, “A maximum power point tracking method based on multiple perturb-and-observe method for overcoming solar partial shaded problems, in 2017 6th International Conference on Clean Electrical Power (ICCEP), 2017, pp. 68 73.
[81] P. M. Meshram and R. G. Kanojiya, “Tuning of pid controller using Ziegler-nichols method for speed control of dc motor,” in IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012), 2012, pp. 117 122.
[82] G. Abbas, M. A. Samad, J. Gu, M. U. Asad, and U. Farooq, “Set-point tracking of a dc-dc boost converter through optimized pid controllers,” in 2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2016, pp. 1 5.
[83] M. S. H. Lipu, A. Hussain, M. H. M. Saad, A. Ayob, and M. A. Hannan, “Improved recurrent narx neural network model for state of charge estimation of lithium-ion battery using pso algorithm,” in 2018 IEEE Symposium on Computer Applications Industrial Electronics (ISCAIE), 2018, pp. 354 359.
[84] H. Liu and X. Song, “Nonlinear system identification based on narx network,” in 2015 10th Asian Control Conference (ASCC), 2015, pp. 1 6.
[85] C. Lv, Y. Xing, J. Zhang, X. Na, Y. Li, T. Liu, D. Cao, and F. Wang, “Levenberg marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber physical system,” IEEE Transactions on Industrial Informatics, vol. 14, no. 8, pp. 3436 3446, 2018.
[86] L. Sun, T. Su, S. Zhou, and L. Yu, “Gmu: A novel rnn neuron and its application to handwriting recognition, in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, 2017, pp. 1062 1067.
[87] N. Gorgolis, I. Hatzilygeroudis, Z. Istenes, and L. . G. Gyenne, “Hyperparameter optimization of lstm network models through genetic algorithm,” in 2019
10th International Conference on Information, Intelligence, Systems and Applications (IISA), 2019, pp. 1 4.
[88] S. Chen and C. Zhou, “Stock prediction based on genetic algorithm feature selection and long short-term memory neural network, IEEE Access, vol. 9, pp. 9066 9072, 2021.
[89] Y. Ma, Z. Zhang, and A. Ihler, “Multi-lane short-term traffic forecasting with convolutional lstm network,” IEEE Access, vol. 8, pp. 34629 34643, 2020.
[90] L. Wang, Q. Zhou, and S. Jin, “Physics-guided deep learning for power system state estimation,” Journal of Modern Power Systems and Clean Energy, vol. 8, no. 4, pp. 607 615, 2020.
[91] Haviluddin and R. Alfred, “Performance of modeling time series using nonlinear autoregressive with exogenous input (narx) in the network traffic forecasting,” in 2015 International Conference on Science in Information Technology (ICSITech), 2015, pp. 164 168.