Sürdürülebilir enerji yönetimi için yapay sinir ağları ve ARIMA metotları kullanılarak melez tahmin modelinin tasarlanması ve geliştirilmesi: Tütün endüstrisinde vaka çalışması

Yıl 2020, , 1129 - 1140, 07.04.2020

Hamdi Giray Reşat

https://doi.org/10.17341/gazimmfd.591248

Cited By: 6

Öz

Çalışma kapsamında enerji yönetim
sistemlerinde önemli bir yere sahip olan kısa vadeli enerji tahminleme
süreçleri için ARIMA ve yapay sinir ağları kullanılarak geliştirilen melez bir
tahmin modeli ortaya konulmuştur. Bu model kapsamında tütün endüstrisinde
üretim yapan bir firmadan elde edilen gerçek hayat verisi ile uygulama
çalışmaları yapılarak sistemin güvenilirliği test edilmiştir. ARIMA yönteminden
elde edilen sonuçlar doğrultusunda elektrik tüketimini etkileyen faktörlerden
bazıları göz önüne alınarak yapay sinir ağı modeline girdi verisi olarak eklenmiştir.
Ele alınan veri setlerinde güneş enerjisi üretimi, çalışma saatleri, üretim
miktarları ve geçmiş elektrik tüketim verileri arasındaki korelasyona bakılarak,
çeşitli nöron sayıları ve farklı eğitim algoritmaları denenerek planlaması
yapılmak istenilen şirket için en uygun sistemin tasarlanması yapılmıştır. Elde
edilen bilgiler ışığında geliştirilen melez tahmin modeli, sadece ARIMA modeli
ile yapılan tahmin verilerine göre %39,9’lik bir iyileştirme sağlamaktadır.

Anahtar Kelimeler

Yapay sinir ağları, enerji, tahminleme

Kaynakça

• [1] Enerjinin etkin kullanımı ve enerji tasarrufu ile ilgili teknolojiler - alt grup raporu (2017) http://www.inovasyon.org/pdf/eek.bolum5.3.pdf Erişim Tarihi:11/01/2019
• [2] Debnath KB, Mourshed M. Forecasting methods in energy planning models. Renewable and Sustainable Energy Reviews. 2018 May 1;88:297-325.
• [3] Kim M, Choi W, Jeon Y, Liu L. A Hybrid Neural Network Model for Power Demand Forecasting. Energies. 2019 Jan;12(5):931.
• [4] Tso GK, Yau KK. Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks. Energy. 2007 Sep 1;32(9):1761-8.
• [5] Meng M, Niu D, Sun W. Forecasting monthly electric energy consumption using feature extraction. Energies. 2011 Oct;4(10):1495-507.
• [6] Zahan M, Kenett RS. Modeling and Forecasting Energy Consumption in the Manufacturing Industry in South Asia. International Journal of Energy Economics and Policy. 2012 Dec 13;3(1):87-98.
• [7] Es HA, Kalender FY, Hamzacebi C. Forecasting the net energy demand of Turkey by artificial neural networks. Journal of the Faculty of Engineering and Architecture of Gazi University. 2014 Jan 1;29(3):495-504.
• [8] Zhang F, Deb C, Lee SE, Yang J, Shah KW. Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique. Energy and Buildings. 2016 Aug 15;126:94-103.
• [9] Rahman A, Srikumar V, Smith AD. Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Applied energy. 2018 Feb 15;212:372-85.
• [10] Tahmassebi A, Gandomi AH. Building energy consumption forecast using multi-objective genetic programming. Measurement. 2018 Mar 1;118:164-71.
• [11] Singh, P., & Dwivedi, P. Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem. Applied energy, 2018 217, 537-549.
• [12] Mohan N, Soman KP, Kumar SS. A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model. Applied energy. 2018 Dec 15;232:229-44.
• [13] Ruiz LG, Rueda R, Cuéllar MP, Pegalajar MC. Energy consumption forecasting based on Elman neural networks with evolutive optimization. Expert Systems with Applications. 2018 Feb 1;92:380-9.
• [14] Anvari S, Tuna S, Canci M, Turkay M. Automated Box–Jenkins forecasting tool with an application for passenger demand in urban rail systems. Journal of Advanced Transportation. 2016 Jan;50(1):25-49.
• [15] Katsatos AL, Moustris KP. Application of Artificial Neuron Networks as energy consumption forecasting tool in the building of Regulatory Authority of Energy, Athens, Greece. Energy Procedia. 2019 Jan 1;157:851-61.
• [16] Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003 Jan 1;50:159-75.
• [17] Demirel Ö, Kakilli A, Tektaş M. Anfis ve arma modelleri ile elektrik enerjisi yük tahmini. Journal of the Faculty of Engineering and Architecture of Gazi University. 2010;25(3).
• [18] Khashei M, Bijari M. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Applied Soft Computing. 2011 Mar 1;11(2):2664-75.
• [19] Babu CN, Reddy BE. A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data. Applied Soft Computing. 2014 Oct 1;23:27-38.
• [20] Khandelwal I, Adhikari R, Verma G. Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science. 2015 Jan 1;48:173-9.
• [21] de Oliveira JF, Ludermir TB. A hybrid evolutionary decomposition system for time series forecasting. Neurocomputing. 2016 Mar 5;180:27-34.
• [22] Başoğlu B, Bulut M. Kısa dönem elektrik talep tahminleri için yapay sinir ağları ve uzman sistemler tabanlı hibrit sistem geliştirilmesi. Journal of the Faculty of Engineering & Architecture of Gazi University. 2017 Apr 1;32(2).
• [23] Xiao J, Li Y, Xie L, Liu D, Huang J. A hybrid model based on selective ensemble for energy consumption forecasting in China. Energy. 2018 Sep 15;159:534-46.
• [24] Karadede Y, Ozdemir G, Aydemir E. Breeder hybrid algorithm approach for natural gas demand forecasting model. Energy. 2017 Dec 15;141:1269-84.
• [25] Li J, Wang R, Wang J, Li Y. Analysis and forecasting of the oil consumption in China based on combination models optimized by artificial intelligence algorithms. Energy. 2018 Feb 1;144:243-64.
• [26] Zhang Y, Ma F, Shi B, Huang D. Forecasting the prices of crude oil: An iterated combination approach. Energy Economics. 2018 Feb 1;70:472-83.
• [27] de Oliveira EM, Oliveira FL. Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods. Energy. 2018 Feb 1;144:776-88.
• [28] Wang D, Wang Y, Song X, Liu Y. Coal overcapacity in China: multiscale analysis and prediction. Energy Economics. 2018 Feb 1;70:244-57.
• [29] Gavin H. The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems. Department of Civil and Environmental Engineering, Duke University. 2011 Sep 28:1-5.
• [30] Aşkın D, İskender İ, Mamızadeh A. Farklı yapay sinir ağları yöntemlerini kullanarak kuru tip transformatör sargısının termal analizi. Journal of The Faculty of Engineering and Architecture of Gazi University. 2011;26(4):905-13.
• [31] Møller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural networks. 1993 Jan 1;6(4):525-33.