Abstract
Electricity price is an important aspect in a restructured power market. Because of nonlinearity, nonstationary, and volatility of electricity price, it is highly essential to forecast the price on a short-term scale. This paper presents an efficient method based on a hybrid functional link dynamic neural network (DNN) trained by an adaptive robust unscented Kalman filter (UKF). The proposed method forecasts hourly prices for the day-ahead electricity market. The functional block helps to introduce nonlinearity by expanding the input space to higher-dimensional space through a basis function without using any hidden layer like multilayer perceptron structure. The DNN includes one or more infinite impulse response filters in the forward path providing feedback connections between outputs and inputs. This allows signal flow in both forward and backward directions, giving the network a dynamic memory useful to mimic dynamic systems. Also to improve the accuracy of the forecast, the noise covariance matrices of the UKF are adapted recursively. The proposed method is tested on PJM electricity market, and the residuals mean absolute error is compared with other forecasting methods, indicating the improved accuracy of the approach and its suitability to produce a real-time forecast. Further, to compare the accuracy of the forecast, an alternative UKF noise covariance optimization is attempted using differential evolution.
Similar content being viewed by others
References
Contreras J, Espinola R, Nogales F, Conejo A (2003) ARIMA models to predict next-day electricity prices. IEEE Trans Power Syst 18(3):1014–1020
Wu L, Shahidehpour M (2010) A hybrid model for day-ahead price forecasting. IEEE Trans Power Syst 25(3):1519–2010
Peter Zhang G (2003) Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, vol 50. Elsevier, pp 159–175
Amjady N, Daraeepour A, Keynia F (2010) Day-ahead electricity price forecasting by modified relief algorithm and hybrid neural network. IET Gen Transm Distrib 4(3):432–444
Tan Z, Zhang J, Wang J, Xu J (2010) Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. Appl Energy 87(11):3606–3610
Zareipour H, Canizares CA, Bhattacharya K, Thomson J (2006) Application of public-domain market information to forecast Ontario’s wholesale electricity prices. IEEE Trans Power Syst 21(4):1707–1717
Zhou M, Yan Z, Ni YX, Li G, Nie Y (2006) Electricity price forecasting with confidence-interval estimation through an extended ARIMA approach. Proc Inst Elect Eng Gen Transm Distrib 153(2):187–195
Shahidehpour M, Yamin H, Li ZY (2002) Market operations in electric power systems. Wiley, New York
Aggarwal SK, Saini LM, Kumar A (2009) Electricity price forecasting in deregulated markets: a review and evaluation. Elect Power Energy Syst 31(1):13–22
Mandal P, Senjyu T, Urasaki N, Funabshi T, Srivastava AK (2007) A novel approach to forecast electricity price for PJM using neural network and similar days method. IEEE Trans Power Syst 22(4):2058–2065
Lin WM, Gow HJ, Tsai MT (2010) An enhanced radial basis function network for short-term electricity price forecasting. Appl Energy 87:3226–3234
PJM Electricity Market Data [Online]. http://www.pjm.com
Li Y, Flynn PC (2004) Deregulated power prices: comparison of volatility. Energy Policy 32(14):1591–1601
Campolucci P, Uncini A, Piazza F, Rao BD (1999) On-line learning algorithms for locally recurrent neural networks. IEEE Trans Neural Netw 10(2):253–270
Xiong K, Zhang H, Liu L (2008) Adaptive robust extended Kalman filter for nonlinear stochastic systems. IET Control Theory Appl 2(3):239–250
Kaneda Y, Irizuki Y, Yamakita M (2013) Robust unscented Kalman filter via I1 regression and design method of its parameters. In: Proc. IEEE 2013 9th Asian control conference (ASCC), Istanbul, pp 1–6. doi:10.1109/ASCC.2013.660622
Mirzaee A, Salahshoor K (2012) Fault diagnosis and accommodation of nonlinear systems based on multiple-model adaptive unscented Kalman filter and switched MPC and H-infinity loop-shaping controller. J Process Control 22(3):626–634
Valverde G, Terzija V (2011) Unscented Kalman filter for power system dynamic state estimation. IET Gen Trans Distrib 5(1):29–37
Song Q, Han JD (2008) An adaptive UKF algorithm for the state and parameter estimations of a mobile Robot. Acta Autom Sin 34(1):72–79
Zhao L, Wangm X (2009) An adaptive UKF with noise statistic estimator. In: Proc. ICIEA 2009. 4th IEEE conference on industrial electronics and applications, Xi’an, pp 614–618. doi:10.1109/ICIEA.2009.5138274
Zhang J, Sanderson AC (2009) JADE: adaptive differential evolution with optional external archive. IEEE Trans Evol Comput 13(5):945–958
Qin AK, Huang VL, Suganthan PN (2008) Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans Evol Comput 13(2):398–417
Wang Y, Cai Z, Zhang Q (2011) Differential evolution with composite trial vector generation strategies and control parameters. IEEE Trans Evol Comput 15(1):55–66
Dash PK, Satpathy HP, Liew AC, Rahman S (1997) A real-time short-term load forecasting system using functional link networks. IEEE Trans Power Syst 12(2):675–680
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Dash, S.K., Bisoi, R. & Dash, P.K. A hybrid functional link dynamic neural network and evolutionary unscented Kalman filter for short-term electricity price forecasting. Neural Comput & Applic 27, 2123–2140 (2016). https://doi.org/10.1007/s00521-015-2011-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-2011-z