Using Weather Patterns to Forecast Electricity Consumption in Sri Lanka: An ARDL Approach

Anuradha Priyadarshana, Ravindra Lokupitiya, Duminda Kuruppuarachchi, Erandathie Lokupitiya


It is crucial to plan the electricity supply to match the future demand since electricity has become a dominant utility. Sri Lanka as a developing country, has over 98% of households electrified, which sometimes suffer from interruptions in supply. This study aims at forecasting monthly electricity consumption in Sri Lanka by considering the influence of weather patterns. Rainfall, humidity, and temperature are the three main weather parameters found to affect the electricity demand. We compared eight forecasting approaches including four econometric models and four algorithmic forecasting methods in forecasting monthly electricity consumption. Twenty meteorological stations were considered to spatially interpolate the weather data using the Inverse Distance Weighted (IDW) interpolation method. Results revealed that Autoregressive Distributed Lag (ARDL) model which incorporates the weather patterns as predictors outperforms in forecasting the monthly electricity consumption compared with all other forecasting approaches.


Autoregressive distributed lag model; Electricity consumption forecasting; Inverse distance weighted interpolation; Missing value imputation; Weather impact

Full Text:



De Silva G.V. and L. Samaliarachchi. 2013. Peak electricity demand prediction model for Sri Lanka power system. Engineer: Journal of the Institution of Engineers, Sri Lanka 46(4).

Ceylon Electricity Board, 2019. Energy Generation, Retrieved from the World Wide Web:

Bambaravanage T., Kumarawadu S. and Rodrigo A., 2016. Comparison of three under-frequency load shedding schemes referring to the power system of Sri Lanka. Engineer: Journal of the Institution of Engineers, Sri Lanka 49(1).

Papalexopoulos A.D. and T.C. Hesterberg, 1990. A regression-based approach to short-term system load forecasting. IEEE Transactions on Power Systems 5(4): 1535-1547.

Ceylon Electricity Board, 2017, Sales and Generation Data Book. Retrieved from the World Wide Web:

Mirasgedis S., Sarafidis Y., Georgopoulou E., Lalas D.P., Moschovits M., Karagiannis F. and Papakonstantinou D., 2006. Models for mid-term electricity demand forecasting incorporating weather influences. Energy 31(2-3): 208-227.

Hor C.L., Watson S.J. and Majithia S., 2005. Analyzing the impact of weather variables on monthly electricity demand. IEEE Transactions on Power Systems 20(4): 2078-2085.

Alabbas N. and J. Nyangon. 2016, October. Weather-based long-term electricity demand forecasting model for Saudi Arabia: a hybrid approach using end-use and econometric methods for comprehensive demand analysis. In Implications of North American energy self-sufficiency, 34th USAEE/IAEE North American Conference, Oct 23-26, 2016. International Association for Energy Economics.

Jovanović S., Djordjević Z., Bojić M. and Stepanović S.S.B., 2012, November. Weather conditions impact on electricity consumption. In 1st International Scientific Conference: 28-30.

Lou C.W. and M.C. Dong. 2015. A novel random fuzzy neural networks for tackling uncertainties of electric load forecasting. International Journal of Electrical Power & Energy Systems 73: 34-44.

Fan G.F., Peng L.L., Hong W.C. and Sun F., 2016. Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing 173: 958-970.

Zhang Z. and W.C. Hong. 2019. Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm. Nonlinear Dynamics 98(2): 1107-1136.

Sen P., Roy M. and Pal P., 2016. Application of ARIMA for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing organization. Energy 116: 1031-1038.

Yang D., Sharma V., Ye Z., Lim L.I., Zhao L. and Aryaputera A.W., 2015. Forecasting of global horizontal irradiance by exponential smoothing, using decompositions. Energy 81: 111-119.

Li Y., Jiang X., Zhu H., He X., Peeta S., Zheng T. and Li Y., 2016. Multiple measures-based chaotic time series for traffic flow prediction based on Bayesian theory. Nonlinear Dynamics 85(1): 179-194.

Takeda H., Tamura Y. and Sato S., 2016. Using the ensemble Kalman filter for electricity load forecasting and analysis. Energy 104: 184-198.

Lebotsa M.E., Sigauke C., Bere A., Fildes R. and Boylan J.E., 2018. Short term electricity demand forecasting using partially linear additive quantile regression with an application to the unit commitment problem. Applied Energy 222: 104-118.

Kelo S. and S. Dudul. 2012. A wavelet Elman neural network for short-term electrical load prediction under the influence of temperature. International Journal of Electrical Power & Energy Systems 43(1): 1063-1071.

Hernández L., Baladrón C., Aguiar J.M., Carro B., Sánchez-Esguevillas A. and Lloret J., 2014. Artificial neural networks for short-term load forecasting in microgrids environment. Energy 75: 252-264.

Lusis P., Khalilpour K.R., Andrew L. and Liebman A., 2017. Short-term residential load forecasting: Impact of calendar effects and forecast granularity. Applied Energy 205: 654-669.

Duan Q., Liu J. and Zhao D., 2017. Short term electric load forecasting using an automated system of model choice. International Journal of Electrical Power & Energy Systems 91: 92-100.

Zhang W., Zhang S. and Zhang S., 2018. Two-factor high-order fuzzy-trend FTS model based on BSO-FCM and improved KA for TAIEX stock forecasting. Nonlinear Dynamics 94(2): 1429-1446.

Hua J.C., Noorian F., Moss D., Leong P.H. and Gunaratne G.H., 2017. High-dimensional time series prediction using kernel-based Koopman mode regression. Nonlinear Dynamics 90(3): 1785-1806.

Fan G.F., Wei X., Li Y.T. and Hong W.C., 2020. Forecasting electricity consumption using a novel hybrid model. Sustainable Cities and Society 61: 102320.

Fan G.F., Guo Y.H., Zheng J.M. and Hong W.C., 2020. A generalized regression model based on hybrid empirical mode decomposition and support vector regression with back‐propagation neural network for mid‐short‐term load forecasting. Journal of Forecasting 39(5): 737-756.

Hong W.C. and G.F. Fan. 2019. Hybrid empirical mode decomposition with support vector regression model for short term load forecasting. Energies 12(6): 1093.

Fan G.F., Peng L.L. and Hong W.C., 2018. Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model. Applied Energy 224: 13-33.

Fan G.F., Qing S., Wang H., Hong W.C. and Li H.J., 2013. Support vector regression model based on empirical mode decomposition and auto regression for electric load forecasting. Energies 6(4): 1887-1901.

Engle R.F., Granger C.W., Rice J. and Weiss A., 1986. Semiparametric estimates of the relation between weather and electricity sales. Journal of the American statistical Association 81(394): 310-320.

Chikobvu D. and C. Sigauke. 2013. Modelling influence of temperature on daily peak electricity demand in South Africa. Journal of Energy in Southern Africa 24(4): 63-70.

Fahad M.U. and N. Arbab. 2014. Factor affecting short term load forecasting. Journal of Clean Energy Technologies, 2(4): 305-309.

Fan S. and R.J. Hyndman. 2011. Short-term load forecasting based on a semi-parametric additive model. IEEE Transactions on Power Systems 27(1): 134-141.

Benli T.O., 2016. A comparison of various electricity tariff price forecasting techniques in turkey and identifying the impact of time series periods. arXiv preprint arXiv:1610.08415.

Faraway J. and C. Chatfield. 1998. Time series forecasting with neural networks: a comparative study using the airline data. Journal of the Royal Statistical Society: Series C (Applied Statistics) 47(2): 231-250.

Bildirici M.E., 2013. The analysis of relationship between economic growth and electricity consumption in Africa by ARDL method. Energy Economics Letters 1(1): 1-14.

Saviozzi M., Massucco S. and Silvestro F., 2019. Implementation of advanced functionalities for Distribution Management Systems: Load forecasting and modeling through Artificial Neural Networks ensembles. Electric Power Systems Research 167: 230-239.

Wu H., Zhou Y., Luo Q. and Basset M.A., 2016. Training feedforward neural networks using symbiotic organisms search algorithm. Computational intelligence and neuroscience, 2016.

Lin K., Lin Q., Zhou C. and Yao J., 2007, August. Time series prediction based on linear regression and SVR. In Third International Conference on Natural Computation (ICNC 2007) 1: 688-691. IEEE.

Young P.C., Pedregal D.J. and Tych W., 1999. Dynamic harmonic regression. Journal of Forecasting, 18(6): 369-394.

Fung D.S., 2006. Methods for the estimation of missing values in time series. MS Thesis, Edith Cowan University Edith Cowan University, Perth, Western Australia.

Abeyratne P.G.V., Featherstone W.E. and Tantrigoda D.A., 2010. On the geodetic datums in Sri Lanka. Survey Review 42(317): 229-239.

Sluiter R., 2009. Interpolation methods for climate data: literature review. KNMI intern rapport, Royal Netherlands Meteorological Institute, De Bilt.

Taylor J.W. and R. Buizza. 2003. Using weather ensemble predictions in electricity demand forecasting. International Journal of Forecasting 19(1): 57-70.

Zhang Z., Ding S. and Sun Y., 2020. A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task. Neurocomputing 410: 185-201.

Diebold F.X. and R.S. Mariano. 2002. Comparing predictive accuracy. Journal of Business & economic statistics 20(1): 134-144.

Derrac J., García S., Molina D. and Herrera F., 2011. A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation 1(1): 3-18.

Montgomery D.C. and Runger G.C., 2010. Applied statistics and probability for engineers. John Wiley & Sons.