Accurate short-term load forecasting plays a crucial role in electricity industry and market. In this study, a novel forecasting method based on Support Vector Machine (SVM) and Firefly Algorithm (FA) has been created to realize accurate and reliable load prediction. The performance of SVM highly depends on the selection of parameters, and Gaussian disturbance Firefly Algorithm (GDFA) proposed in this study can satisfy the necessary. Ensemble Empirical Mode Decomposition (EEMD) is employed to decompose the load data into sub-series with different frequency. This paper extracts daily maximum temperature, daily minimum temperature, wind speed, rainfall, day type, and the load one week before the forecasting day as input variables. Two cases are taken to verify the effective performance of GDFA compared with FA, as well as the superiority of EEMD-GDFA-SVM over other forecasting techniques in short-term load forecasting.
SousaJ.C., JorgeH.M., and NevesL.P., Short-term load forecasting based on support vector regression and load profiling, Int J of Energy Res38 (2014), 350–362.
2.
LiuK., SubbarayanS., ShoultsR.R., ManryM., KwanC., and LewisF.L., Comon of very short-term load forecasting technique, IEEE Trans Power Syst11 (1996), 877–882paris.
3.
Funar-TimofeiS., and KuruncziL., Reply to “Quantitative structure–affinity relationship study of azo dyes for cellulose fibers by multiple linear regression and artificial neural network”, Dyes and Pigment113 (2015), 325–326.
4.
Dimitriou-FakalouC., The auto-regression and the moving-average, J of Stat Plan & Inference140 (2010), 1739–1743.
5.
Kavousi-FardA., A new fuzzy-based feature selection and hybrid TLA-ANN modelling for short-term load forecasting, J of Exp & Theor Artif Intell25 (2013), 543–557.
6.
Akbari-ZadehM.R., A hybrid method based on wavelet, ANN and ARIMA model for short-term load forecasting, J of Exp & Theor Artif Intell26 (2014), 167–182.
7.
Kavousi-FardA., KhosraviA., and NahavandiS., A new fuzzy-based combined prediction interval for wind power forecasting, IEEE Trans Power Syst (2015), 1–9.
8.
XiaoZ., YeS.J., ZhongB., and SunC.X., BP neural network with rough set for short term load forecasting, Expert Syst with Appl36 (2009), 273–279.
9.
FengY., and XuX., A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network, Appl Energy134 (2014), 102–113.
10.
LeeC.M., and KoC.N., Time series prediction using RBF neural networks with a nonlinear time-varying evolution PSO algorithm, Neurocomputing73 (2009), 449–460.
11.
YaoY., LianZ., HouZ., and LiuW., An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction, Int J of Refrig29 (2006), 528–538.
12.
HwangH., Daily electric load forecasting based on RBF neural network models, Int J of Fuzzy Log & Int Syst13 (2013), 39–49.
13.
VapnikV., GolowichS.E., and SmolaA., Support vector method for function approximation, regression estimation, and signal processing, Adv in Neural Inf Process Syst9 (1970), 281–287.
14.
Kavousi-FardA., SametH., and MarzbaniF., A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting, Expert Syst with Appl41 (2014), 6047–6056.
15.
AvciE., Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm-support vector machines: HGASVM, Expert Syst with Appl36 (2009), 1391–1402.
16.
WautersM., and VanhouckeM., Support vector machine regression for project control forecasting, Autom in Constr47 (2014), 92–106.
17.
CheJ.X., and WangJ.Z., Short-term load forecasting using a kernel-based support vector regression combination model, Appl Energy132 (2014), 602–609.
18.
SelakovA., CvijetinovićD., MilovićL., MellonS., and BekutD., Hybrid PSO-SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank, Appl Soft Comput16 (2014), 80–88.
19.
LiR., XuH.R., and LuF.Y., A short-term load forecasting by considering meteorological factors based on hierarchical PSO-SVM model, J of North China Electr Power Univ37 (2010), 26–32.
20.
SunW., A novel hybrid GA based SVM short term load forecasting model, Int Symp on Knowl Acquis & Model IEEE Comput Soc (2009), 227–229.
21.
Kavousi-FardA., and Kavousi-FardF., A new hybrid correction method for short-term load forecasting based on ARIMA, SVR and CSA, J of Exper & Theor Artif Intel25 (2013), 559–574.
22.
YangX.S., Firefly algorithms for multimodal optimization, Stoch Algorithm Found & Appl5792 (2010), 169–178.
23.
YangX.S., HosseiniS.S.S., and GandomiA.H., Firefly algorithm for solving non-convex economic dispatch problems with valve loading effect, Appl Soft Comput12 (2012), 1180–1186.
24.
PoursalehiN., ZolfaghariA., MinuchehrA., and MoghaddamH., Continuous firefly algorithm applied to PWR core pattern enhancement, Nucl Eng & Des258 (2013), 107–115.
25.
BacaninN., and TubaM., Firefly algorithm for cardinality constrained mean-variance portfolio optimization problem with entropy diversity constraint, Sci World J2014 (2014), 435–451.
26.
ChS., SohaniS.K., KumarD., MalikA., ChaharB.R., NemaA.K., PanigrahiB.K., and DhimanR.C., A Support vector machine-firefly algorithm based forecasting model to determine malaria transmission, Neurocomputing129 (2014), 279–288.
27.
KazemA., SharifiE., HussainF.K., SaberiM., and HussainO.K., Support vector regression with chaos-based firefly algorithm for stock market price forecasting, Appl Soft Comput13 (2013), 947–958.
KonarP., and ChattopadhyayP., Bearing fault detection of induction motor using wavelet and support vector machines (SVMs), Appl Soft Comput11 (2011), 4203–4211.
30.
WangX., ZiY., and HeZ., Multiwavelet denoising with improved neighboring coefficients for application on rolling bearing fault diagnosis, Mech Syst & Signal Process25 (2011), 285–304.
31.
DelpratN., EscudieB., GuillemainP., Kronland-MartinetR., TchamitchianP., and TorrésaniB., Asymptotic wavelet and Gabor analysis: Extraction of instantaneous frequencies, IEEE Trans on Inf Theory38 (1992), 644–664.
32.
HuangN.E., ShenZ., LongS.R., WuM.C., ShihH.H., ZhengQ., YenN.C., TungC.C., and LiuH.H., The empirical mode decomposition and the Hilbert for nonlinear and non-stationary time series analysis, Proceed of the Royal Soc London A: Mathemat Phys & Eng Sci454 (1998), 903–995spectrum.
33.
MengL., XiangJ., WangY., JiangY., and GaoH., A hybrid fault diagnosis method using morphological filter-translation invariant wavelet and improved enble empirical mode decomposition, Mech Syst& Signal Processs50-51 (2015), 101–115sem.
34.
XueY.J., CaoJ.X., TianR.F., DuH.K., and ShuY.X., Application of the empirical mode decomposition and wavelet transform to seismic reflection frequency attenuation analysis, J Petroleum Sci & Eng122 (2014), 360–370.
35.
HuJ., WangJ., and ZengG., A hybrid forecasting approach applied to wind speed time series, Renew Energy60 (2013), 185–194.
36.
WuZ., and HuangN.E., Enble empirical mode decomposition: A noise-assisted data analysis method, Adv in Adapt Data Anal1 (2011), 1–41sem.
37.
HuangN.E., and WuZ., A review on Hilbert-Huang transform: Method and its applications to geophysical studies, Rev of Geophys46(2008) (2008).
38.
KimN.S., ChungK., AhnS., YuJ.W., and ChoiK., Denoising traffic collision data using Enble Empirical Mode Decomposition (EEMD) and its application for constructing Continuous Risk Profile (CRP), Accident Analysis & Prevention71 (2014), 29–37sem.
39.
TangL., YuL., WangS., LiJ., and WangS., A novel hybrid enble learning paradigm for nuclear energy consumption forecasting, Appl Energy93 (2012), 432–443sem.
40.
VapnikV., The nature of statistical learning theory: Springer Science & Business Media, 2000.
41.
ChenY., LinL.I., and QianL.I., Evaluation method for flight control law based on modified differential evolution algorithm, Acta Aeronaut Et Astronaut Sinic34 (2013), 1261–1268.
42.
LiuX., LiN., and HuY., Combining inferences on the common mean of several inverse Gaussian distributions based on confidence distribution, Stat & Probab Lett105 (2015), 136–142.
43.
FriggeM., and IglewiczB., Some implementations of the boxplot, Am Stat43 (1989), 50–54.
