In this paper, a new feature selection and forecast engine is presented for day ahead prediction of electricity prices, which are so valuable for both producers and consumers in the new competitive electric power markets. In a competitive electricity market, forecast of energy prices is a key information for the market participants. However, price signal usually has a complex behavior due to its nonlinearity, non-stationary, and time variance. Also, an appropriate feature selection is crucial for accurate forecasting. In this paper, a two-step approach that identifies a set of candidate features based on the data characteristics proposed and then selects a subset of them using correlation and instance-based feature selection methods, applied in a systematic way. Then, a combination of wavelet transform (WT) and a hybrid forecast method is presented based on neural network (NN) and an optimization algorithms. The proposed method is examined on PJM electricity market and compared with some of the most recent price forecast methods. These comparisons illustrate effectiveness of the proposed strategy.
ShahidehpourM., YaminH. and LiZ., Market Operations in Electric Power Systems, New York: Wiley, 2002.
2.
WuL. and ShahidehpourM., A hybrid model for day-ahead price forecasting, power systems, IEEE Transactions on Power System25(3) (2010), 1519–1530.
3.
KouP., LiangD., GaoL. and LouJ., Probabilistic electricity price forecasting with variational heteroscedastic Gaussian process and active learning, Energy Conversion and Management89 (2015), 298–308.
4.
HafeziaR., ShahrabiJ. and HadavandiE., A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price, Applied Soft Computing29 (2015), 196–210.
5.
CheJ. and WangJ., Short-term electricity prices forecasting based on support vector regression and Auto-regressive integrated moving average modeling, Energy Conversion and Management51(10) (2010), 1911–1917.
6.
FirouzM.H. and GhadimiN., Concordant controllers based on FACTS and FPSS for solving wide-area in multi-machine power system, Journal of Intelligent & Fuzzy Systems30(2) (2016), 845–859.
7.
NogalesF.J., ContrerasJ., ConejoA.J. and EspinolaR., Forecasting next-day electricity prices by time series models, IEEE Trans on Power Systems17 (2002), 342–348.
8.
MorsaliR., et al., A new multiobjective procedure for solving nonconvex environmental/economic power dispatch, Complexity20(2) (2014), 47–62.
9.
ContrerasJ., EspinolaR., NogalesF.J. and ConejoA.J., ARIMA models to predict next-day electricity prices, IEEE Trans On Power Systems18 (2003), 1014–1020.
10.
AbediniaO., AmjadyN., Shafie-khahM. and CatalãoJ.P.S., Electricity price forecast using combinatorial neural network trained by a new stochastic search method, Energy Conversion and Management105 (2015), 642–654.
11.
Bolouck AzariJ. and GhadimiN., Firefly technique based on optimal congestion management in an electricity market, International Journal of Information, Security and Systems Management3(2) (2014), 333–344.
12.
GuoJ.J. and LuhP.B., Improving market clearing price prediction by using a committee machine of neural networks, IEEE Trans on Power Systems19 (2004), 1867–1876.
13.
GonzalezA.M., San RoqueA.M. and GonzalezJ.G., Modeling and forecasting electricity prices with input/output hidden markov models, IEEE Trans On Power Systems20 (2005), 13–24.
14.
ZhangL. and LuhP.B., Neural network-based market clearing price prediction and confidence interval estimation with an improved extended kalman filter method, IEEE Trans On Power Systems20 (2005), 59–66.
15.
RodriguezC.P. and AndersG.J., Energy price forecasting in the ontario competitive power system market, IEEE Transactions on Power Systems19 (2004), 366–374.
16.
MandalP., SenjyuT., UrasakiN., FunabashiT., SrivastavaA.K., A novel approach to forecast electricity price for PJM using neural network and similar days method, IEEE Transactions on Power Systems22(4) (2007), 2058–2065.
17.
PedregalD.J. and TraperoJ.R., Electricity prices forecasting by automatic dynamic harmonic regression models, Energy Conversion And Management48(5) (2007), 1710–1719.
18.
GhadimiN., An adaptive neuro-fuzzy inference system for islanding detection in wind turbine as distributed generation, Complexity21(1) (2015), 10–20.
19.
AbediniaO. and AmjadyN., Short-term wind power prediction based on hybrid neural network and chaotic shark smell optimization, International Journal of Precision Engineering and Manufacturing-Green Technology2(3) (2015), 245–254.
20.
ConejoA.J., PlazasM.A., EspinolaR. and MolinaA.B., Day-ahead electricity price forecasting using the wavelet transform and ARIMA models, IEEE Trans on Power Systems20 (2005), 1035–1042.
21.
CroneS. and KourentzesN., Input-variable specification for neural networks – an analysis of forecasting low and high time series frequency, in: Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2009.
22.
VlachogiannisJ.G. and LeeK.Y., Multi-objective based on parallel vector evaluated particle swarm optimization, Expert Systems with Applications36 (2009), 10802–10808.
23.
AfsharA., ShafiiM. and Bozorg HaddadO., Optimizing multi-reservoir operation rules: An improved HBMO approach, Journal of Hydro Informatics13(1) (2010), 121–139.
24.
DarbellayG.A. and SlamaM., Forecasting the short-term demand for electricity – do neural networks stand a better chance?Int J Forecast16 (2000), 71–83.
25.
HaghM.T. and GhadimiN., Multisignal histogram-based islanding detection using neuro-fuzzy algorithm, Complexity21(1) (2015), 195–205.
26.
HallM.A., Correlation-based feature selection for discrete and numeric class machine learning, in: Proceedings of the International Conference on Machine Learning (ICML), 2000, pp. 359–366.
27.
Robnik-SikonjaM. and KononenkoI., Theoretical and empirical analysis of ReliefF and RReliefF, Mach Learn53 (2003), 23–69.
28.
KiraK. and RendellL., A practical approach to feature selection, in: Proceedings of the 9th International Conference on Machine Learning (ICML), 1992.
29.
AbediniaO., AmjadyN., GhasemiA. and HejratiZ., Solution of economic load dispatch problem via hybrid PSO-TVAC and BFA techniques, European Transaction on Electrical Power23(8) (2013), 1504–1522.
30.
AmjadyN., Short-term bus load forecasting of power systems by a new hybrid method, IEEE Trans on Power Systems22 (2007), 333–341.
31.
GarciaM.P. and KirschenD.S., Forecasting system imbalance volumes in competitive electricity markets, IEEE Trans On Power Systems21 (2006), 240–248.
32.
CatalãoJ.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 System Research77 (2007), 1297–1304.
