A comparative study of long-term load forecasting techniques applied to Tunisian grid case

  • Sirine EssallahEmail author
  • Adel Khedher
Original Paper


The rapid development of population, economy and technology currently has led to the fast increase in electric consumption. Therefore, efficient energy management and load forecasting have been flagged as a very important need for electric networks planning and operation. Recently, different techniques have been developed to deal with load forecasting. However, the stochastic nature and uncertainty characteristics of the electric load make demand forecasting a challenging task for electric utilities where no technique can be identified as the most efficient one. It becomes therefore relevant to identify the technique that best fits a specific dataset. Thus, in this paper we propose a comparative study of four techniques for long-term load forecasting, namely Box–Jenkins, multiple linear regressions, MLR and nonlinear autoregressive neuronal networks with and without exogenous variables, NARX and NAR. The study is conducted on the Tunisian electric consumption, and the performance of different techniques is evaluated as a function of historical data and forecasting period’s variations. Quantitative and qualitative assessments of results are reported in this study in order to pinpoint the strengths and weaknesses of the different assessed forecasting techniques.


Forecasting Long-term Box–Jenkins NAR MLR NARX 

List of symbols


Auto-regression coefficients


Moving average coefficients


Random error


Output signal

wi, wo

Weights matrices with respect to the input and the output

bo, bi

Biases matrices with respect to the input and the output

wh1, wh1

Weights and biases matrices of the first hidden layer


Regression parameters


Input signal

dx, dy

Input and output time offsets


Constants of simple linear regressions


Autoregressive integrated moving average


Exports of goods and services


Gross domestic product


Imports of goods and services


Internet subscriptions


Mean absolute percentage error


Mobile cellular subscriptions


Multiple linear regression


Nonlinear autoregressive neuronal networks


Nonlinear autoregressive neuronal networks with exogenous variables


Secondary school enrollment rate


Fixed telephone lines



  1. 1.
    Conti J, Holtberg P, Diefenderfer J, LaRose A, Turnure JT, Westfall L (2016) International energy outlook 2016 with projections to 2040 (No. DOE/EIA-0484 (2016)). USDOE Energy Information Administration (EIA), Washington, DC (United States). Office of Energy AnalysisGoogle Scholar
  2. 2.
    Cancelo JR, Espasa A, Grafe R (2008) Forecasting the electricity load from one day to one week ahead for the Spanish system operator. Int J Forecast 24(4):588–602CrossRefGoogle Scholar
  3. 3.
    Dordonnat V, Pichavant A, Pierrot A (2016) GEFCom2014 probabilistic electric load forecasting using time series and semi-parametric regression models. Int J Forecast 32(3):1005–1011CrossRefGoogle Scholar
  4. 4.
    Singh AK, Khatoon S, Muazzam M, Chaturvedi DK (2012) Load forecasting techniques and methodologies: a review. In: The 2nd IEEE international conference on power, control and embedded systems (ICPCES), pp 1–10Google Scholar
  5. 5.
    Hong T, Wilson J, Xie J (2014) Long term probabilistic load forecasting and normalization with hourly information. IEEE Trans Smart Grid 5(1):456–462CrossRefGoogle Scholar
  6. 6.
    Suganthi L, Samuel AA (2012) Energy models for demand forecasting—a review. Renew Sustain Energy Rev 16(2):1223–1240CrossRefGoogle Scholar
  7. 7.
    Hong T, Fan S (2016) Probabilistic electric load forecasting: a tutorial review. Int J Forecast 32(3):914–938CrossRefGoogle Scholar
  8. 8.
    Ekonomou L, Oikonomou DS (2008) Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load. In: Proceedings of the 7th WSEAS international conference on artificial intelligence, knowledge engineering and data bases, Cairo, Egypt, pp 29–31Google Scholar
  9. 9.
    Khuntia SR, Rueda JL, van der Meijden MA (2016) Forecasting the load of electrical power systems in mid-and long-term horizons: a review. IET Gener Transm Distrib 10(16):3971–3977CrossRefGoogle Scholar
  10. 10.
    Ghods L, Kalantar M (2011) Different methods of long-term electric load demand forecasting, a comprehensive review. Iran J Electr Electron Eng 7(4):249–259Google Scholar
  11. 11.
    Hahn H, Meyer-Nieberg S, Pickl S (2009) Electric load forecasting methods: tools for decision making. Eur J Oper Res 199(3):902–907CrossRefGoogle Scholar
  12. 12.
    Metaxiotis K, Kagiannas A, Askounis D, Psarras J (2003) Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher. Energy Convers Manag 44(9):1525–1534CrossRefGoogle Scholar
  13. 13.
    Yildiz B, Bilbao J, Sproul A (2017) A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renew Sustain Energy Rev 73:1104–1122CrossRefGoogle Scholar
  14. 14.
    de Oliveira EM, Oliveira FLC (2018) Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods. Energy 144:776–788CrossRefGoogle Scholar
  15. 15.
    Mi J, Fan L, Duan X, Qiu Y (2018) Short-term power load forecasting method based on improved exponential smoothing grey model. Math Probl Eng 2018:11CrossRefGoogle Scholar
  16. 16.
    Mohammed J, Bahadoorsingh S, Ramsamooj N, Sharma C (2017) Performance of exponential smoothing, a neural network and a hybrid algorithm to the short term load forecasting of batch and continuous loads. In: 2017 IEEE Manchester PowerTech, pp 1–6Google Scholar
  17. 17.
    Pappas SS, Ekonomou L, Moussas VC, Karampelas P, Katsikas SK (2008) Adaptive load forecasting of the Hellenic electric grid. J Zhejiang Univ Sci A 9(12):1724–1730CrossRefGoogle Scholar
  18. 18.
    Ekonomou L (2010) Greek long-term energy consumption prediction using artificial neural networks. Energy 35(2):512–517CrossRefGoogle Scholar
  19. 19.
    Taylor JW (2010) Triple seasonal methods for short-term electricity demand forecasting. Eur J Oper Res 204(1):139–152CrossRefGoogle Scholar
  20. 20.
    Khan AR, Mahmood A, Safdar A, Khan ZA, Khan NA (2016) Load forecasting, dynamic pricing and dsm in smart grid: a review. Renew Sustain Energy Rev 54:1311–1322CrossRefGoogle Scholar
  21. 21.
    Tang N, Zhang D-J (2011) Application of a load forecasting model based on improved grey neural network in the smart grid. Energy Proc 12:180–184CrossRefGoogle Scholar
  22. 22.
    AlRashidi M, El-Naggar K (2010) Long term electric load forecasting based on particle swarm optimization. Appl Energy 87(1):320–326CrossRefGoogle Scholar
  23. 23.
    Kouhi S, Keynia F (2013) A new cascade NN based method to short-term load forecast in deregulated electricity market. Energy Convers Manag 71:76–83CrossRefGoogle Scholar
  24. 24.
    Ekonomou L, Christodoulou CA, Mladenov V (2016) A short-term load forecasting method using artificial neural networks and wavelet analysis. Int J Power Syst 1:64–68Google Scholar
  25. 25.
    Tang L, Wang X, Wang X, Shao C, Liu S, Tian S (2019) Long-term electricity consumption forecasting based on expert prediction and fuzzy Bayesian theory. Energy 167:1144–1154CrossRefGoogle Scholar
  26. 26.
    Shi ZB, Li Y, Yu T (2009) Short-term load forecasting based on LS-SVM optimized by bacterial colony chemotaxis algorithm. In: 2009 international conference on information and multimedia technology. IEEE, pp 306–309Google Scholar
  27. 27.
    Hong T, Fan S (2016) Probabilistic electric load forecasting: a tutorial review. Int J Forecast 32(3):914–938CrossRefGoogle Scholar
  28. 28.
    Ghods L, Kalantar M (2011) Different methods of long-term electric load demand forecasting; a comprehensive review. Iran J Electr Electron Eng 7(4):249–259Google Scholar
  29. 29.
    Hermias JP, Teknomo K, Monje JCN (2017) Short-term stochastic load forecasting using autoregressive integrated moving average models and Hidden Markov Model. In: 2017 international conference on information and communication technologies (ICICT), pp 131–137Google Scholar
  30. 30.
    Bonetto R, Rossi M (2016) Parallel multi-step ahead power demand forecasting through nar neural networks. In: 2016 IEEE international conference on smart grid communications (SmartGridComm). IEEE, pp 314–319Google Scholar
  31. 31.
    Hashmi MU, Arora V, Priolkar JG (2015) Hourly electric load forecasting using nonlinear autoregressive with exogenous (narx) based neural network for the state of Goa, india. In: 2015 international conference on industrial instrumentation and control (ICIC), pp 1418–1423Google Scholar
  32. 32.
    Di Piazza A, Di Piazza MC, Vitale G (2016) Solar and wind forecasting by narx neural networks. Renew Energy Environ Sustain 1:39CrossRefGoogle Scholar
  33. 33.
    Fu CW, Nguyen TT (2003) Models for long-term energy forecasting. In: Proceedings of IEEE power engineering society general meetingGoogle Scholar
  34. 34.
    Li Y, Niu D (2010) Application of principal component regression analysis in power load forecasting for medium and long term. In: Proceeding of the 3rd international conference on advanced computer theory and engineeringGoogle Scholar
  35. 35.
    Yildiz B, Bilbao J, Sproul A (2017) A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renew Sustain Energy Rev 73:1104–1122CrossRefGoogle Scholar
  36. 36.
    Amani P, Kihl M, Robertsson A (2011) Narx-based multi-step ahead response time prediction for database servers. In: 11th international conference on intelligent systems design and applications (ISDA), pp 813–818Google Scholar
  37. 37. Accessed 09 July 2018
  38. 38.
    Shahbaz M, Lean HH (2012) Does financial development increase energy consumption? The role of industrialization and urbanization in tunisia. Energy Policy 40:473–479CrossRefGoogle Scholar
  39. 39.
    Fallahi F (2011) Causal relationship between energy consumption (ec) and gdp: a markovswitching (ms) causality. Energy 36(7):4165–4170CrossRefGoogle Scholar
  40. 40.
    Hossain MS (2011) Panel estimation for CO2 emissions, energy consumption, economic growth, trade openness and urbanization of newly industrialized countries. Energy Policy 39(11):6991–6999CrossRefGoogle Scholar
  41. 41.
    Cederborg J, Snöbohm S (2016) Is there a relationship between economic growth and carbon dioxide emissions? Södertörn University, School of Social Sciences, EconomicsGoogle Scholar
  42. 42.
    Hagan MT, Menhaj MB (1994) Training feed forward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5:989–993CrossRefGoogle Scholar
  43. 43.
    Alwakeel M, Shaaban Z (2010) Face Recognition based on haar wavelet transform and principal component analysis via Levenberg–Marquardt backpropagation neural network. Eur J Sci Res 42:25–31Google Scholar
  44. 44.
    Kaboli SHA, Selvaraj J, Rahim NA (2016) Long-term electric energy consumption forecasting via artificial cooperative search algorithm. Energy 115:857–871CrossRefGoogle Scholar
  45. 45.
    Askarzadeh A (2014) Comparison of particle swarm optimization and other metaheuristics on electricity demand estimation: a case study of iran. Energy 72:484–491CrossRefGoogle Scholar
  46. 46.

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Université de Sousse, Ecole Nationale d’Ingénieurs de SousseLATIS- Laboratory of Advanced Technology and Intelligent SystemsSousseTunisia

Personalised recommendations