ParDeeB: A graph framework for load forecasting based on parallel DeepNet branches

Document Type : Article


1 Department of Industrial Engineering, Meybod University, Yahyazadeh Blvd., Khorramshahr Blvd., Meybod, Yazd, Iran

2 Department of Computer Engineering, Meybod University, Yahyazadeh Blvd., Khorramshahr Blvd., Meybod, Yazd, Iran

3 Department of Industrial Engineering , Sharif University of Technology, Azadi Ave, Tehran, Iran


Recently, energy demand forecasting has emerged as a signi cant area of research
because of its prominent impact on greenhouse gases (GHGs) emission
and global warming.The problems of load forecasting are characterized by complex
and nonlinear nature and also long-term historical dependency. Up to now,
several approaches from statistical to computational intelligent have been applied
in this research led. The literature agrees with the fact that deep learning
approach is more capable in dealing with these characteristics among existing
approaches. However, the recent state-of-the-art deep network models are not
robust against di erent historical dependency. In this study, we propose a graph
framework based on parallel DeepNet branches to tackle this challenge. This
framework consists of multi parallel branches in which di erent kind of networks
can be incorporated. The parallel recurrent branches represent the historical dependency
of determinants individually and this leads to better performance in
case of di erent historical dependency in data. In this case study, the performance
of the proposed model is examined through a comparison study with
the state-of-the-art deep network models. The comparison resulted in that the
proposed framework can improve the load forecasting by a signi cant margin
on average.


1. Amara, F., Agbossou, K., Dube, Y., et al. "A residual load modeling approach for household short-term load forecasting application", Energy and Buildings, 187, pp. 132-143 (2019).
2. Neshat, N. "An approach of artificial neural networks modeling based on fuzzy regression for forecasting purposes", International Journal of Engineering, 28(11), pp. 1651-1655 (2015).
3. Azadeh, A. and Faiz, Z. "A meta-heuristic framework for forecasting house- hold electricity consumption", Applied Soft Computing, 11(1), pp. 614-620 (2011).
4. Neshat, N., Amin-Naseri, M.R., and Danesh, F. "Energy models: Methods and characteristics", Journal of Energy in Southern Africa, 25(4), pp. 101-111 (2014).
5. Kamranrad, R. and Amiri, A. "Robust holt-winter based control chart for monitoring autocorrelated simple linear profiles with contaminated data", Scientia Iranica, 23(3), pp. 1345-1354 (2016).
6. Weron, R. and Misiorek, A. "Forecasting spot electricity prices: A compari- son of parametric and semiparametric time series models", International Journal of Forecasting, 24(4), pp. 744-763 (2008).
7. Misiorek, A., Trueck, S., and Weron, R. "Point and interval forecasting of spot electricity prices: Linear vs. non-linear time series models", Studies in Nonlinear Dynamics and Econometrics, 10(3) (2006).
8. Diongue, A.K., Guegan, D., and Vignal, B. "Forecasting electricity spot mar- ket prices with a k-factor gigarch process", Applied Energy, 86(4), pp. 505-510 (2009).
9. Garcia, R.C. Contreras, J. Van Akkeren, M., et al. "A garch forecasting model to predict day-ahead electricity prices", IEEE Transac-Tions on Power Systems, 20(2), pp. 867-874 (2005).
10. Knittel, C.R. and Roberts, M.R. "An empirical examination of restructured electricity prices", Energy Economics, 27(5), pp. 791-817 (2005).
11. Wang, C., Rao, C., Meng, Y., et al. "Research on impact of shenzhen-hong kong stock connect mechanism on the volatility of stock markets", Scientia Iranica, 29(1), pp. 372-386 (2022).
12. Yang, Z., Ce, L., and Lian, L. "Electricity price forecasting by a hybrid model, combining wavelet transform, arma and kernel-based extreme learning machine methods", Applied Energy, 190, pp. 291-305 (2017).
13. Vilar, J.M., Cao, R., and Aneiros, G. "Forecasting next-day electricity de- mand and price using nonparametric functional methods", International Journal of Electrical Power and Energy Systems, 39(1), pp. 48-55 (2012).
14. Jeong, K., Koo, C., and Hong, T. "An estimation model for determining the an- nual energy cost budget in educational facilities using sarima (seasonal autoregressive integrated moving average) and ann (artificial neural net- work)", Energy, 71, pp. 71-79 (2014).
15. Wang, Y., Wang, J., Zhao, G., et al. "Application of residual modifi- cation approach in seasonal arima for electricity demand forecasting: A case study of china", Energy Policy, 48, pp. 284-294 (2012).
16. Nogales, F.J., Contreras, J., and Conejo, A.J. "Forecasting next- day electricity prices by time series models", IEEE Transactions on Power Systems, 17(2), pp. 342-348 (2002).
17. Mbae, A.M. and Nwulu, N.I. "Day-ahead load forecasting using improved grey verhulst model", Journal of Engineering, Design and Technology, 18(5), pp. 1335-1348 (2020).
18. Kazemi, A., Modarres, M., Mehregan, M., et al. "A markov chain grey forecasting model: A case study of energy demand of industry sector in iran", In 3rd International Conference on Information and Financial Engineering IPEDR, 12 (2011).
19. Hashem-Nazari, M., Esfahanipour, A., and Fatemi Ghomi, S. "A basic form- focused modeling and a modified parameter estimation technique for grey prediction models", Scientia Iranica, 25(5), pp. 2867- 2880 (2018).
20. Ma, X., Wu, W., Wang, Y., et al. "Predicting primary energy consumption using ndgm (1, 1, k, c) model with simpson formula", Scientia Iranica, 6(6), pp. 3379- 3395 (2021).
21. Tan, Z., Zhang, J., Wang, J., et al. "Day-ahead electricity price forecasting using wavelet transform combined with arima and garch models", Applied Energy, 87(11), pp. 3606-3610 (2010).
22. Shahriari-kahkeshi, M. "Robust fault detection and isolation scheme using fuzzy wavelet network with a hybrid design algorithm", Scientia Iranica, 24(3), pp. 1467-1481 (2017).
23. Lee, C.-P., Lin, W.-C., and Yang, C.-C. "A strategy for forecasting option price using fuzzy time series and least square support vector regression with a bootstrap model", Scientia Iranica, 21(3), pp. 815-825 (2014).
24. Song, K.-B., Baek, Y.-S., Hong, D.H., et al. "Shortterm load forecast- ing for the holidays using fuzzy linear regression method", IEEE Transactions on Power Systems, 20(1), pp. 96-101 (2005).
25. Bilgili, M., Sahin, B., Yasar, A., et al. "Electric energy demands of turkey in residential and industrial sectors", Renewable and Sustainable Energy Reviews, 16(1), pp. 404-414 (2012).
26. Ghiassi, M., and Nangoy, S. "A dynamic artificial neural network model for forecasting nonlinear processes", Computers and Industrial Engineering, 57(1), pp. 287- 297 (2009).
27. Kazemi, A., Shakouri, H.G., Menhaj, M.B., et al. "A hierarchical artificial neural network for transport energy demand forecast: Iran case study", Neural Network World, 20(6), p. 761 (2010).
28. Neshat, N., Hadian, H., and Alangi, S.R. "Technological learning modelling towards sustainable energy planning", Journal of Engineering, Design and Technology, 18(1), pp. 84-101 (2020).
29. Neshat, N., Hadian, H., and Behzad, M."Nonlinear arimax model for long-term sectoral demand forecasting", Management Science Letters, 8(6), pp. 581-592 (2018).
30. Dudek, G. "Pattern-based local linear regression models for short-term load forecasting", Electric Power Systems Research, 130, pp. 139-147 (2016).
31. Tsekouras, G., Dialynas, E., Hatziargyriou, N., et al. "A non-linear multivariable regression model for midterm energy forecasting of power systems", Electric Power Systems Research, 77(12), pp. 1560-1568 (2007).
32. Azadeh, A., Neshat, N., Rafiee, K., et al. "An adaptive neural network-fuzzy linear regression approach for improved car ownership estimation and forecasting in complex and uncertain environments: the case of Iran", Transportation Planning and Technology, 35(2), pp. 221-240 (2012).
33. Huang, C.-H., Yang, F.-H., and Lee, C.-P. "The strategy of investment in the stock market using modified support vector regression model", Scientia Iranica, 25(3), pp. 1629-1640 (2018).
34. Kazemi, A., Shakouri, G., Menhaj, M., et al. "A multilevel artificial neural network for residential and commercial energy de- mand forecast: Iran case study", In International Conference on Man- agement Technology and Applications (ICMTA), pp. 24-28 (2010).
35. Khwaja, A., Zhang, X., Anpalagan, A., et al. "Boosted neural networks for improved short-term electric load forecasting", Electric Power Systems Research, 1, pp. 431-437 (2017).
36. Niu, D., Liu, D., and Wu, D.D. "A soft computing system for day-ahead electricity price forecasting", Applied Soft Computing, 10(3), pp. 868-875 (2010).
37. Yao, B., Yao, J., Zhang, M., et al. "Improved support vector machine re- gression in multi-step-ahead prediction for rock displacement surround- ing a tunnel", Scientia Iranica, Transaction A, Civil Engineering, 21(4), p. 1309 (2014).
38. Qiu, X., Ren, Y., Suganthan, P.N.G., et al. "Empirical mode decomposition based ensemble deep learning for load demand time series forecasting", Applied Soft Computing, 54, pp. 246-255 (2017).
39. Maleki, N., Nikoubin, A., Rabbani, M., et al. "Bitcoin price prediction based on other cryptocurrencies using machine learning and time series analysis, Scientia Iranica, 30(1), pp. 285-301 (2020).
40. Ekonomou, L. "Greek long-term energy consumption prediction using artificial neural networks", Energy, 35(2), pp. 512-517 (2010).
41. Kialashaki, A. and Reisel, J.R. "Development and validation of artificial neural network models of the energy demand in the industrial sector of the united states", Energy, 76, pp. 749-760 (2014).
42. Abedinia, O. and Amjady, N. "Short-term load forecast of electrical power system by radial basis function neural network and new stochastic search algorithm", International Transactions on Electrical Energy Systems, 26(7), pp. 1511-1525 (2016).
43. Gajowniczek, K. and Zabkowsk, T. "Electricity forecasting on the individual household level enhanced based on activity patterns", Plos One, 12(4), e0174098 (2017).
44. He, W. "Load forecasting via deep neural networks, Procedia Computer Science", 122, pp. 308-314 (2017).
45. Shi, H., Xu, M., Ma, Q., et al. "A whole system assessment of novel deep learning approach on shortterm load forecasting", Energy Procedia, 142, pp. 2791-2796 (2017).
46. Rahman, A., Srikumar, V., and Smith, A.D. "Predicting electricity consump- tion for commercial and residential buildings using deep recurrent neural networks", Applied Energy, 212, pp. 372-385 (2018).
47. Kong, W., Dong, Z.Y., Hill, D.J., et al. "Shortterm residential load forecasting based on resident behaviour learning", IEEE Transactions on Power Systems, 33(1), pp. 1087-1088 (2017).
48. Bedi, J. and Toshniwal, D. "Deep learning framework to forecast electricity demand", Applied Energy, 238, pp. 1312-1326 (2019).
49. Elamin, N. and Fukushige, M. "Modeling and forecasting hourly electricity demand by sarimax with interactions", Energy, 165, pp. 257-268 (2018).
50. Amezquita-Sancheza, J., Valtierra-Rodriguez, M., and Adeli, H. "Machine learning in structural engineering", Scientia Iranica, 27(6), pp. 2645-2656 (2020).
51. Neshat, N., Sardarizarchi, M., and Mahlooji, H. "Application of deep learn- ing models based on fullyconnected and recurrent neural networks tresidual peak load forecasting", Sharif Journal of Industrial Engineering and Management, 36(1.2), pp. 103-111 (2020).
52. Francois Chollet, F., Deep Learning with Python, Simon and Schuster, ISSN: 1638352046 (2021).