Guaranteeing stable electricity demand forecasting is paramount for the conservation of material resources. However, because electricity consumption data are often made up of complex and unstable series, it is very hard for a simple single method to always obtain accurate predictions. To improve electricity demand forecasting robustness and accuracy, a hybrid empirical mode decomposition and state space model are proposed, for which the empirical mode decomposition is applied to decompose the total time series (noise filtering), and the state space model is employed to forecast every sub-series (feature extraction), with the state space model parameters being optimized using maximum likelihood via a Kalman filter. Compared with autoregressive integrated moving average model and artificial neural networks, the proposed model had more stable and accurate forecasting. This method could be broadly applied to not only forecast electricity demand, being a key step for developing electricity generation plans and formulating energy policy, but also forecast any similar time series data with noise and substantive latent features, making a new step toward solving such a problem.
HeinemannGTNordmianDAPlantEC.The relationship between summer weather and summer loads – a regression analysis. IEEE Trans Power Appar Syst1966;
11: 1144–1154.
2.
HobbsBFJitprapaikulsarnSKondaS, et al.
Analysis of the value for unit commitment of improved load forecasts. IEEE Trans Power Syst1999;
14: 1342–1348.
3.
JiangPLiuFSongY.A hybrid forecasting model based on date-framework strategy and improved feature selection technology for short-term load forecasting. Energy2017;
119: 694–709.
4.
KhuntiaSRRuedaJLvan der MeijdenMA.Forecasting the load of electrical power systems in mid- and long-term horizons: a review. IET Gener Transm Distrib2016;
10: 3971–3977.
5.
GuoHChenQXiaQ, et al.
A monthly electricity consumption forecasting method based on vector error correction model and self-adaptive screening method. Int J Electr Power Energy Syst2018;
95: 427–437.
6.
YangALiWYangX. Short-term electricity load forecasting based on feature selection and least squares support vector machines. Knowledge-Based Syst2019; 163: 159–173.
7.
QiuXSuganthanPNAmaratungaGAJ.Short-term electricity price forecasting with empirical mode decomposition based ensemble kernel machines. Proc Comput Sci2017;
108: 1308–1317.
8.
ShaoZChaoFYangSL, et al.
A review of the decomposition methodology for extracting and identifying the fluctuation characteristics in electricity demand forecasting. Renew Sustain Energy Rev2017;
75: 123–136.
9.
QiuXRenYSuganthanPN, et al.
Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Appl Soft Comput2017;
54: 246–255.
10.
PapalexopoulosADHesterbergTC.A regression-based approach to short-term system load forecasting. IEEE Trans Power Syst1990;
5: 1535–1547.
11.
MbamaluGEl-HawaryM.Load forecasting via suboptimal seasonal autoregressive models and iteratively reweighted least squares estimation. IEEE Trans Power Syst1993;
8: 343–348.
12.
ChenJWangWHuangC.Analysis of an adaptive time-series autoregressive moving-average (ARMA) model for short-term load forecasting. Electr Power Syst Res1995;
34: 187–196.
LynchCO’MahonyMJGuineeRA.Electrical load forecasting using an expanded Kalman filter bank methodology. IFAC Papers Online2016;
49: 358–365.
15.
TarsitanoAAmeriseIL.Short-term load forecasting using a two-stage sarimax model. Energy2017;
133: 108–114.
16.
KouhiSKeyniaF.A new cascade NN based method to short-term load forecast in deregulated electricity market. Energy Convers Manage2013;
71: 76–83.
17.
HongWC.Application of chaotic ant swarm optimization in electric load forecasting. Energy Policy2010;
38: 5830–5839.
18.
Van der MeerDSheperoMSvenssonA, et al.
Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian processes. Appl Energy2018;
213: 195–207.
19.
WangQLiSLiR.Forecasting energy demand in china and India: using single-linear, hybrid-linear, and non-linear time series forecast techniques. Energy2018;
161: 821–831.
20.
XieNMYuanCQYangYJ.Forecasting Chinas energy demand and self-sufficiency rate by grey forecasting model and Markov model. Int J Electr Power Energy Syst2015;
66: 1–8.
21.
BurgerEMMouraSJ.Gated ensemble learning method for demand-side electricity load forecasting. Energy Build2015;
109: 23–34.
22.
TakedaHTamuraYSatoS.Using the ensemble Kalman filter for electricity load forecasting and analysis. Energy2016;
104: 184–198.
23.
CheJWangJWangG.An adaptive fuzzy combination model based on self-organizing map and support vector regression for electric load forecasting. Energy2012;
37: 657–664.
24.
ZhangJWeiYLiD, et al.
Short term electricity load forecasting using a hybrid model. Energy2018;
158: 774–781.
25.
NowotarskiJLiuBWeronR, et al.
Improving short term load forecast accuracy via combining sister forecasts. Energy2016;
98: 40–49.
26.
XiaoLShaoWYuM, et al.
Research and application of a combined model based on multi-objective optimization for electrical load forecasting. Energy2017;
119: 1057–1074.
27.
BarakSSadeghSS.Forecasting energy consumption using ensemble ARIMACANFIS hybrid algorithm. Int J Electr Power Energy Syst2016;
82: 92–104.
28.
WangQLiSLiR.China’s dependency on foreign oil will exceed 80% by 2030: developing a novel NMGM-ARIMA to forecast china’s foreign oil dependence from two dimensions. Energy2018;
163: 151–167.
29.
WangQSongXLiR.A novel hybridization of nonlinear grey model and linear ARIMA residual correction for forecasting US shale oil production. Energy2018;
165: 1320–1331.
30.
LiSGoelLWangP.An ensemble approach for short-term load forecasting by extreme learning machine. Appl Energy2016;
170: 22–29.
31.
RiosRAMelloRFD.Improving time series modeling by decomposing and analyzing stochastic and deterministic influences. Signal Process2013;
93: 3001–3013.
32.
FanGFPengLLHongWC, et al.
Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing2016;
173: 958–970.
33.
LiuNTangQZhangJ, et al.
A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids. Appl Energy2014;
129: 336–345.
34.
XiongTBaoYHuZ.Interval forecasting of electricity demand: a novel bivariate EMD-based support vector regression modeling framework. Int J Electr Power Energy Syst2014;
63: 353–362.
35.
DordonnatVKoopmanSJOomsM, et al.
An hourly periodic state space model for modelling French national electricity load. Int J Forecast2008;
24: 566–587.
36.
HuangNEShenZLongSR, et al.
The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Math Phys Eng Sci1998;
454: 903–995.
37.
KalmanRE.A new approach to linear filtering and prediction problems. J Basic Eng1960;
82: 35–45.
38.
KoopmanSJOomsM.Forecasting daily time series using periodic unobserved components time series models. Comput Stat Data Anal2006;
51: 885–903.
39.
GolpeAACarmonaMCongregadoE.Persistence in natural gas consumption in the US: an unobserved component model. Energy Policy2012;
46: 594–600.
40.
MnifAT.Political uncertainty and behavior of Tunisian stock market cycles: structural unobserved components time series models. Res Int Bus Fin2017;
39: 206–214.
41.
PedregalDJYoungPC.Modulated cycles, an approach to modelling periodic components from rapidly sampled data. Int J Forecasting2006;
22: 181–194.
ShaikhFJiQ.Forecasting natural gas demand in China: logistic modelling analysis. Int J Electr Power Energy Syst2016;
77: 25–32.
44.
WilliamsHP.Model building in mathematical programming.
Hoboken, NJ:
Wiley, 2013.
45.
KhandelwalIAdhikariRVermaG.Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Proc Comput Sci2015;
48: 173–179.
46.
GnayME.Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: case of Turkey. Energy Policy2016;
90: 92–101.
47.
MoyoVSibandaK.Training set size for generalization ability of artificial neural networks in forecasting TCP/IP traffic trends. Int J Comput Sci Appl2015;
4: 9–17.
48.
FoodyGMMccullochMBYatesWB.The effect of training set size and composition on artificial neural network classification. Int J Remote Sens1995;
16: 1707–1723.
