Accurate electricity price forecasting is a key area in the electricity market. This paper proposes a hybrid model, Evolutionary-Improved Cuckoo Search Extreme Learning Machine (E-ICSELM) for day and week ahead prediction of a highly volatile financial time series data i.e. electricity price for six different energy markets such as Hourly Ontario Electricity Price(HOEP), Pennsylvania Jersey Maryland (PJM), New England, Nord Pool, California and Spain. In this model, Improved Cuckoo Search (ICS), a meta-heuristic, population based optimization techniques used to select input weights and hidden biases and Moore-Penrose (MP) generalized inverse to analytically determine the output weights. Experimental results show the superiority of the proposed E-ICSELM model when it is compared with simple ELM and Evolutionary-Cuckoo Search based ELM (E-CSELM).
PatwardhanA.P., PatidarR. and GeorgeN.V., On a cuckoo search optimization approach towards feedback system identification, Digital Signal Processing, Elsevier32 (2014), 156-163.
2.
KhosraviA., NahavandiS. and CreightonD., Quantifying uncertainties of neural network based electricity price forecasts, Applied Energy, Elsevier112 (2013), 120-129.
3.
LoraA.T., SantosJ.M.R., ExpositoA.G., RamosandJ.L.M., SantosJ.C.R., Electricity market price forecasting based on weighted nearest neighbors techniques, IEEE Transaction on Power Systems22(3) (2007), 1294-1301.
4.
ConejoA.J., NogalesF.J. and ArroyaJ.M., Price-taker bidding strategy under price uncertainty, IEEE Transaction on Power Systems17(4) (2002), 1081-1088.
5.
Bueno-CrespoA., García-LaencinaP.J. and Sancho-GómezJ.-L., Neural architecture design based on extreme learning machine, Neural Networks, Elsevier48 (2013), 19-24.
6.
GrigorievskiyA., MicheY., VenteläA.-M., SéverinE. and LendasseA., Long-term time series prediction using op-elm, Neural Networks, Elsevier51 (2014), 50-56.
7.
Garcia-MartosC., RodriguezG. and SanchazM.J., Mixed models for short-run forecasting of electricity prices: Application for the Spanish market, IEEE Transaction on Power Systems22(2) (2007).
8.
ChenY., YangB. and DongJ., Time series prediction using a local linear wavelet neural network, Neurocomputing, Elsevier69 (2006), 449-465.
9.
NiuD., LiuD. and WuD.D., A soft computing system for day-ahead electricity price forecasting, Applied Soft Computing, Elsevier10 (2010), 868-875.
10.
ValianE., TavakoliS., MohannaS. and HaghiA., Improved cuckoo search for reliability optimization problems, Computers and Industrial Engineering, Elsevier64 (2013), 459-468
11.
ValianE., MohannaS. and TavakoliS., Improved cuckoo search algorithm for feed forward neural network training, International Journal of Artificial Intelligence and Applications2(3) (2011), 36-43.
12.
ValianE., MohannaS. and TavakoliS., Improved cuckoo search algorithm for global optimization, International Journal of Communications and Information Technology, IJCIT1(1) (2011).
13.
KeyniaF., A new feature selection algorithm and composite neural network for electricity price forecasting, Engineering Applications of Artificial IntelligenceElsevier25 (2012), 1687-1697.
14.
HanF., YaoH.-F. and LingQ.-H., An improved evolutionary extreme learning machine based on particle swarm optimization, NeurocomputingElsevier116 (2013), 87-93,
15.
NogalesF.J. and JoC., Electricity price forecasting through transfer function models, Journal of Operational Research Society57 (2006), 350-356.
16.
HuangG.-B., ZhuQ.-Y. and SiewC.-K., Extreme learning machine: A new learning scheme of feed forward neural networks, International Joint Conference on Neural Networks (IJCNN'2004), Budapest, Hungary, (2004), 985-990.
17.
HuangG.-B., WangD.H. and LanY., Extreme learning machines: A survey, International Journal of Machine Learning and Cybernetics2(2) (2011), 107-122.
18.
ZhaoG., ShenZ. and ManZ., Robust input weight selection for well-conditioned extreme learning machine, International Journal of Information Technology17(1) (2011).
19.
ZhaoG., ShenZ. and ManZ., On improving the conditioning of extreme learning machine: A linear case, ICICS, IEEE, (2009).
20.
ZaraipourH., CanizaresC.A. and BhattacharyaK., Economic impact of electricity market price forecasting errors: A demand-side analysis, IEEE Transaction on Power Systems, 2009.
21.
GuirguisH.S. and FelderF.A., Further advances in forecasting day-ahead electricity prices using time series models, KIEE International Transactions on PE4(3) (2004), 159-166.
22.
YangH., YiJ., ZhaoJ. and DongZ., Extreme learning machine based genetic algorithm and its application in power system economic dispatch, NeurocomputingElsevier102 (2013), 154-162.
23.
FisterI., Jr., YangX.-S., FisterD. and FisterI., Cuckoo search: A brief literature review, Cuckoo Search and Firefly Algorithm, Springer, (2014), 49-62.
24.
ZhangJ. and TanZ., Day-ahead electricity price forecasting using WT, CLSSVM and EGARCH model, Electrical Power and Energy SystemsElsevier45 (2013), 362-368.
25.
ContrerasJ., EspinolaR., NogalesF.J. and ConejoA.J., ARIMA models to predict next-day electricity prices, IEEE Transaction on Power Systems18(3) (2003), 1014-1020.
26.
KimJ., ShinH.S., ShinK. and LeeM., Robust algorithm for arrhythmia classification in ecg using extreme learning machine, Biomed Eng Online8 (2009), 31.
27.
CatalaoJ.P.S., MarianoS.J.P.S., MendesV.M.F. and FerreiraL.A.F.M., Short-term electricity prices forecasting in a competitive market: A neural network approach, Electric Power Systems ResearchElsevier77 (2007), 1297-1304.
28.
YapK.S. and YapH.J., Daily maximum load forecasting of consecutive national holidays using oselm-based multi-agents system with weighted average strategy, NeurocomputingElsevier81 (2012), 108-112.
29.
PacificoL.D.S. and LudermirT.B., Improved evolutionary extreme learning machines based on particle swarm optimization and clustering approaches, International Journal of Natural Computing Research3(3) (2012), 1-20.
30.
ZhouM., YanZ., NiY.X., LiG. and NieY., Electricity price forecasting with confidence-interval estimation through an extended ARIMA approach, IEE Proc-Gener Transm Distrib153(2) (2006), 187-195.
31.
MarichelvamM., An improved hybrid cuckoo search (IHCS) meta-heuristics algorithm for permutation flow shop scheduling problems, International Journal of Bio-Inspired Computation4(4) (2012), 200-205.
32.
AmjadyN. and DaraeepourA., Design of input vector for day-ahead price forecasting of electricity markets, Expert Systems with ApplicationsElsevier36 (2009), 12281-12294.
33.
AmjadyN. and KeyniaF., A new prediction strategy for price spike forecasting of day-ahead electricity markets, Applied Soft ComputingElsevier11 (2011), 4246-4256.
34.
AmjadyN. and KeyniaF., Day ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method, Electrical Power and Energy SystemsElsevier30 (2008), 533-546.
35.
AmjadyN. and KeyniaF., Electricity market price spike analysis by a hybrid data model and feature selection technique, Electric Power Systems ResearchElsevier80 (2010), 318-327.
36.
AmjadyN. and KeyniaF., Application of a new hybrid neuro-evolutionary system for day-ahead price, forecasting of electricity markets, Applied Soft ComputingElsevier10 (2010), 784-792.
37.
AmjadyN. and KeyniaF., Day-ahead price forecasting of electricity markets by mutual information technique and cascaded neuro-evolutionary algorithm, IEEE Transaction on Power Systems34(1) (2009), 306-318.
38.
ShrivastavaN.A. and PanigrahiB.K., A hybrid wavelet-ELM based short term price forecasting for electricity markets, Electrical Power and Energy SystemsElsevier55 (2014), 41-50.
39.
ShrivastavaN.A. and PanigrahiB.K., Point and prediction interval estimation for electricity markets with machine learning techniques and wavelet transforms, NeurocomputingElsevier118 (2013), 301-310.
40.
CiviciogluP. and BesdokE., A conceptual comparison of the cuckoo-search, particle swarm optimization, differential evolution and artificial bee colony algorithms, Artificial Intelligence Review39(4) (2013), 315-346.
41.
LingQ.-H. and HanF., Improving the conditioning of extreme learning machine by using particle swarm optimization, International Journal of Digital Content Technology and Its Applications6(2) (2012), 85-93.
HeQ., JinX., DuC., ZhuangF. and ShiZ., Clustering in extreme learning machine feature space, NeurocomputingElsevier128 (2014), 88-95.
44.
DashR., DashP.K. and BisoiR., A self adaptive differential harmony search based optimized extreme learning machine for financial time series prediction, Swarm and Evolutionary Computation, Elsevier, (2014).
45.
MajhiR., PandaG. and SahooG., Development and performance evaluation of FLANN based model for forecasting stock market, Expert Systems with Applications, Elsevier36 (2009), 6800-6808.
HusismanR. and MahieuR., Regime jumps in electricity prices, Energy Economics, Elsevier25 (2003), 425-434.
48.
PandaR., AgrawalS. and BhuyanS., Edge magnitude based multilevel thresholding using Cuckoo search technique, Expert Systems with Applications, Elsevier40 (2013), 7617-7628
49.
ZhangR., DongZ.Y., XuY., MengK. and WongK.P., Short-term load forecasting of australian national electricity market by an ensemble model of extreme learning machine, Generation, Transmission and Distribution, IET7(4) (2013), 391-397.
50.
VuceticS., TomsovicK. and ObradovicZ., Discovering price-load relationship in California's electricity market, IEEE Transaction on Power Systems16(2) (2001), 280-286.
51.
FletenS.-E. and LemmingJ., Constructing forward price curves in electricity markets, Energy EconomicsElsevier25 (2003), 409-424.
52.
ChakravartyS. and DashP.K., A PSO based integrated functional link net and interval Type-2 fuzzy logic system for predicting stock market indices, Applied Soft ComputingElsevier12 (2012), 931-941.
53.
ChakravartyS., DashP.K., Ravikumar PandiV. and PanigrahiB.K., An evolutionary functional link neural fuzzy model for financial time series forecasting, International Journal of Applied Evolutionary Computation (2011), 39-59.
54.
ChakravartyS. and DashP.K., Dynamic filter weights neural network model integrated with differential evolution for day-ahead price forecasting in energy market, Expert Systems with ApplicationsElsevier38 (2011), 10974-10982.
55.
NguyenT.T., VoD.N. and TruongA.V., Cuckoo search algorithm for short-term hydrothermal scheduling, Applied EnergyElsevier132 (2014), 276-287.
56.
TsekourasG.J., HatziargyriouN.D. and DialynasE.N., An optimized adaptive neural network for annual midterm energy forecasting, IEEE Trans on Power Syst21(1) (2006), 385-391.
57.
NiimuraT., KoH.-S. and OzzwaK., A day-ahead electricity price prediction based on a fuzzy-neuro autoregressive model in a deregulated electricity market, IEEE, 2002.
58.
YanX. and ChowdhuryN.A., Mid-term electricity market clearing price forecasting: A multiple SVM Approach, Electrical Power and Energy SystemsElsevier58 (2014), 206-214.
59.
YanX. and ChowdhuryN.A., Mid-term electricity market clearing price forecasting: A hybrid LSSVM and ARMAX approach, Electrical Power and Energy SystemsElsevier53 (2013), 20-26.
60.
YangX.S. and DebS., Multi-objective cuckoo search for design optimization, Computers and Operations ResearchElsevier40 (2013), 1616-1624.
YangX.S. and DebS., Cuckoo search via lévy flights, in: Nature and Biologically Inspired Computing, NaBIC 2009, World Congress on, IEEE, (2009) 210-214.
63.
YangX.S. and DebS., Engineering optimization by cuckoo search, International Journal of Mathematical Modeling and Numerical Optimization1(4) (2010), 330-343.
64.
YanX. and ChowdhuryN.A., Mid-term electricity market clearing price forecasting utilizing hybrid support vector machine and auto-regressive moving average with external input, Electrical Power and Energy SystemsElsevier63 (2014), 64-70.
65.
LiX.R., YuC.W., RenS.Y., ChiuC.H. and MengK., Day-ahead electricity price forecasting based on panel co-integration and particle filter, Electric Power Systems ResearchElsevier95 (2013), 66-76.
66.
SunZ.-L., ChoiT.-M., AuK.-F. and YuY., Sales forecasting using extreme learning machine with applications in fashion retailing, Decision Support SystemsElsevier46 (2008), 411-419.
67.
MustaffaZ., YusofY. and KamaruddinS.S., Enhanced artificial bee colony for training least squares support vector machines in commodity price forecasting, Journal of Computational Science, Elsevier5 (2014), 196-205.
