ORIGINAL PAPER
Combined modelling for iron ore demand forecasting with intelligent optimization algorithms
1
Northeastern University
2
University of South China
Submission date: 2020-11-09
Final revision date: 2021-01-27
Acceptance date: 2021-02-19
Publication date: 2021-03-24
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2021;37(1)
KEYWORDS
TOPICS
Scientific background of mineral resource managementRational and efficient development and utilization of mineral resourcesEconomics of mineral industries
ABSTRACT
The stable supply of iron ore resources is not only related to energy security, but also to a country’s sustainable development. The accurate forecast of iron ore demand is of great significance to the industrialization development of a country and even the world. Researchers have not yet reached a consensus about the methods of forecasting iron ore demand. Combining different algorithms and making full use of the advantages of each algorithm is an effective way to develop a prediction model with high accuracy, reliability and generalization performance. The traditional statistical and econometric techniques of the Holt–Winters (HW) non-seasonal exponential smoothing model and autoregressive integrated moving average (ARIMA) model can capture linear processes in data time series. The machine learning methods of support vector machine (SVM) and extreme learning machine (ELM) have the ability to obtain nonlinear features from data of iron ore demand. The advantages of the HW, ARIMA, SVM, and ELM methods are combined in various degrees by intelligent optimization algorithms, including the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and simulated annealing (SA) algorithm. Then the combined forecast models are constructed. The contrastive results clearly show that how a high forecasting accuracy and an excellent robustness could be achieved by the particle swarm optimization algorithm combined model, it is more suitable for predicting data pertaining to the iron ore demand.
METADATA IN OTHER LANGUAGES:
Polish
Modelowanie do prognozowania popytu na rudę żelaza połączone z inteligentnymi algorytmami optymalizacji
zapotrzebowanie na rudę żelaza, model połączony, inteligentny algorytm optymalizacji, dokładność prognozowania
Stabilne dostawy zasobów rudy żelaza związane są nie tylko z bezpieczeństwem energetycznym, ale także ze zrównoważonym rozwojem kraju. Dokładna prognoza zapotrzebowania na rudę żelaza ma ogromne znaczenie dla rozwoju industrializacji kraju, a nawet świata. Naukowcy nie osiągnęli jeszcze konsensusu co do metod prognozowania popytu na rudę żelaza. Łączenie różnych algorytmów i pełne wykorzystanie zalet każdego algorytmu to skuteczny sposób na opracowanie modelu predykcyjnego o wysokiej dokładności i niezawodności. W tej publikacji, model Holta-Wintersa (HW) do wygładzania szeregów czasowych, w których występują wahania przypadkowe, jak również autoregresyjny zintegrowany model średniej ruchomej (ARIMA), a także maszyna wektorów nośnych (SVM) i maszyna do ekstremalnego uczenia się (ELM), zostały połączone w celu uchwycenia różnych relacji i charakterystyk na podstawie danych szeregów czasowych, aby dokładnie przewidzieć zapotrzebowanie na rudę żelaza. Zalety czterech algorytmów są w różnym stopniu łączone przez inteligentne algorytmy optymalizacji, w tym algorytm genetyczny, algorytm optymalizacji roju cząstek oraz algorytm symulowanego wyżarzania. Następnie konstruowane są połączone modele. Kontrastowe wyniki wyraźnie pokazują, w jaki sposób można osiągnąć wysoką dokładność prognozowania i doskonałą solidność za pomocą połączonego modelu algorytmu genetycznego. Model taki jest bardziej odpowiedni do przewidywania danych dotyczących zapotrzebowania na rudę żelaza. Opierając się na prognozowanych wynikach połączonego modelu algorytmu genetycznego, możemy stwierdzić, że oczekuje się, iż krajowy popyt na rudę żelaza będzie w przyszłości wykazywał tendencję rozwojową w postaci trwałego, ale powolnego wzrostu.
REFERENCES (28)
1.
Al-Fattah, S.M. 2020. A new artificial intelligence GANNATS model predicts gasoline demand of Saudi Arabia. Journal of Petroleum Science and Engineering 194.
2.
Al-Hnaity, B. and Abbod, M. 2016. Predicting Financial Time Series Data Using Hybrid Model. Intelligent Systems and Applications 650, pp. 19–41.
3.
Bates, J.M. and Granger, C.W.J. 1969. The combination of forecasts. Journal of the Operational Research Society 20(4), pp. 451–468.
4.
Bikcora et al. 2018 – Bikcora, C., Verheijen, L. and Weiland, S. 2018. Density forecasting of daily electricity demand with ARMA-GARCH, CAViaR, and CARE econometric models. Sustainable Energy Grids and Networks 13, pp. 148–156.
5.
Box, G.E.P. and Jenkins, G.M. 1976. Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco.
6.
Davies, N.J.P. and Petruccelli, J.D. 1988. An Automatic Procedure for Identification, Estimation and Forecasting Univariate Self Exiting Threshold Autoregressive Models. Journal of the Royal Statistical Society 37(2), pp. 199–204.
7.
D’Amico et al. 2020 – D’Amico, A., Ciulla, G., Tupenaite, L. and Kaklauskas, A. 2020. Multiple criteria assessment of methods for forecasting building thermal energy demand. Energy and Buildings 224.
8.
Eberhart, R. and Kennedy, J. 1995. A new optimizer using particle swarm theory. [In:] MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, pp. 39–43.
9.
Holland, J.M. 1975. Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor.
10.
Huang et al. 2006 – Huang, G.B., Zhu, Q.Y. and Siew, C.K. 2006. Extreme learning machine: theory and applications. Neurocomputing 70, pp. 489–501.
11.
Jia, L.W. and Xu, D.Y. 2014. Analysis and Prediction of the Demand for Iron Ore: Using Panel, Grey, Co-Integration and ARIMA Models. Resources Science 36(7), pp. 1382–1391.
12.
Kazemzadeh et al. 2020 – Kazemzadeh, M.R., Amjadian, A. and Amraee, T. 2020. A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting. Energy 204.
13.
Liu et al. 2016 – Liu, X.L., Moreno, B. and Garcia, A.S. 2016. A grey neural network and input-output combined forecasting model. Primary energy consumption forecasts in Spanish economic sectors. Energy 115, pp. 1042–1054.
14.
Ma et al. 2013 – Ma, W.M., Zhu, X.X. and Wang, M.M. 2013. Forecasting iron ore import and consumption of China using grey model optimized by particle swarm optimization algorithm. Resources Policy 38, pp. 613–620.
15.
Mi et al. 2018 – Mi, J., Fan, L., Duan, X. and Qiu, Y. 2018. Short-Term Power Load Forecasting Method Based on Improved Exponential Smoothing Grey Model. Mathematical Problems in Engineering 2018, pp. 1–11.
16.
National Bureau of Statistics of China. Output of Industrial Products. [Online] https://data.stats.gov.cn/easy... [Accessed: 2020-12-30].
17.
National Bureau of Statistics of China, 2018. Chinese Mining Yearbook. Beijing: China Statistics Press.
18.
Song et al. 2018 – Song, J.J., Wang, J.Z. and Lu, H.Y. 2018. A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting. Applied Energy 215, pp. 643–658.
19.
Vapnik, V.N. 1995. The Nature of Statistical Learning Theory. New York: Springer.
20.
Wang et al. 2018 – Wang, J., Luo, Y.Y., Tang, T.Y. and Peng, G. 2018. Modeling a combined forecast algorithm based on sequence patterns and near characteristics: An application for tourism demand forecasting. Chaos, Solitons and Fractals 108, pp. 136–147.
21.
Wang et al. 2012 – Wang, J.J., Wang, J.Z., Zhang, Z.G. and Guo, S.P. 2012. Stock index forecasting based on a hybrid model. Omega-International Journal of Management Science 40, pp. 758–766.
22.
Wang et al. 2010 – Wang, J.Z., Zhu, S.L., Zhang, W.Y. and Lu, H.Y. 2010. Combined modeling for electric load forecasting with adaptive particle swarm optimization. Energy 35, pp. 1671–1678.
23.
Wang et al. 2020 – Wang, Z.X., Zhao, Y.F. and He, L.Y. 2020. Forecasting the monthly iron ore import of China using a model combining empirical mode decomposition, non-linear autoregressive neural network, and autoregressive integrated moving average. Applied Soft Computing 94.
24.
Winters, P.R. 1960. Forecasting sales by exponentially weighted moving averages. Management Science 6(3), pp. 324–42.
25.
Zhang et al. 2019 – Zhang, S.H., Wang, J.Y. and Guo, Z.H. 2019. Research on combined model based on multi-objective optimization and application in time series forecast. Soft Computing 23, pp. 11493–11521.
26.
Zhang et al. 2017 – Zhang, Y., Li, C. and Li, L. 2017. Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods. Applied Energy 190, pp. 291–305.
27.
Zhou et al. 2019 – Zhou, Z., Si, G.Q., Zheng, K., Xu, X., Qu, K. and Zhang, Y.B. 2019. CMBCF: A Cloud Model Based Hybrid Method for Combining Forecast. Applied Soft Computing 85.
28.
Zhou, Z.H. 2016. Machine Learning. Beijing: Tsinghua University Press, 425 pp. (in Chinese).
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
