Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers in Energy

ISSN 2095-1701

ISSN 2095-1698(Online)

CN 11-6017/TK

Postal Subscription Code 80-972

2018 Impact Factor: 1.701

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Energy    2016, Vol. 10 Issue (1) : 105-113    https://doi.org/10.1007/s11708-016-0393-y
RESEARCH ARTICLE
Day-ahead electricity price forecasting using back propagation neural networks and weighted least square technique
S. Surender REDDY1, Chan-Mook JUNG2(), Ko Jun SEOG3
1. Department of Railroad and Electrical Engineering, Woosong University, Daejeon 300718, Republic of Korea
2. Department of Railroad and Civil Engineering, Woosong University, Daejeon 300718, Republic of Korea
3. Korea Rail Network Authority, Daejeon 300718, Republic of Korea
 Download: PDF(602 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

This paper proposes the day-ahead electricity price forecasting using the artificial neural networks (ANN) and weighted least square (WLS) technique in the restructured electricity markets. Price forecasting is very important for online trading, e-commerce and power system operation. Forecasting the hourly locational marginal prices (LMP) in the electricity markets is a very important basis for the decision making in order to maximize the profits/benefits. The novel approach proposed in this paper for forecasting the electricity prices uses WLS technique and compares the results with the results obtained by using ANNs. To perform this price forecasting, the market knowledge is utilized to optimize the selection of input data for the electricity price forecasting tool. In this paper, price forecasting for Pennsylvania-New Jersey-Maryland (PJM) interconnection is demonstrated using the ANNs and the proposed WLS technique. The data used for this price forecasting is obtained from the PJM website. The forecasting results obtained by both methods are compared, which shows the effectiveness of the proposed forecasting approach. From the simulation results, it can be observed that the accuracy of prediction has increased in both seasons using the proposed WLS technique. Another important advantage of the proposed WLS technique is that it is not an iterative method.
Keywords day-ahead electricity markets      price forecasting      load forecasting      artificial neural networks      load serving entities     
Corresponding Author(s): Chan-Mook JUNG   
Just Accepted Date: 04 December 2015   Online First Date: 19 January 2016    Issue Date: 29 February 2016
 Cite this article:   
S. Surender REDDY,Chan-Mook JUNG,Ko Jun SEOG. Day-ahead electricity price forecasting using back propagation neural networks and weighted least square technique[J]. Front. Energy, 2016, 10(1): 105-113.
 URL:  
https://academic.hep.com.cn/fie/EN/10.1007/s11708-016-0393-y
https://academic.hep.com.cn/fie/EN/Y2016/V10/I1/105
(D–48)
(24,…,3,2,1)		 (D–47)
(24,…,3,2,1)		 (D–46)
(24,…,3,2,1)		 ... (D–2)
(24,…,3,2,1)		 (D–1)
(24,…,3,2,1)		 (D)
(24,…,3,2,1)
Training period for previous 24 days, and each day 48 intervals (i.e., 48 × 24= 1152 training data elements) Forecasting day
(24 h)
Tab.1  Training samples for the BPNN
Day 1 Day 2 Day 3 Day 4 Day 5 Day 6 Day 7 Target output at interval h
P h -145
P h -167
P h -168
L h -145
L h -168		 P h -121
P h -143
P h -144
L h -121
L h -144		 P h -97
P h -119
P h -120
L h -97
L h -120		 P h -73
P h -95
P h -96
L h -73
L h -96		 P h -49
P h -71
P h -72
L h -49
L h -72		 P h -25
P h -47
P h -48
L h -25
L h -48		 P h -1
P h -2
P h -3
P h -24
L h -1
L h-22		 P h
Tab.2  Input for the network from previous 7 days
Fig.1  Comparative analysis of forecasts of winter weeks considering forecasted price using ANN and WLS technique
Day MAPEday using ANN/% MAPEday using WLS technique/%
Monday 11.2631 6.7498
Tuesday 13.0575 9.3332
Wednesday 7.7891 3.6367
Thursday 11.1378 5.0567
Friday 9.335 5.1376
Saturday 8.2369 5.2374
Sunday 11.8989 6.469
Tab.3  Electricity price forecasting errors for winter weeks using ANN and WLS technique
Fig.2  Comparative analysis of forecasts of spring weeks considering forecasted price using ANN and WLS technique
Day MAPEday using ANN/% MAPEday using WLS technique/%
Monday 5.286021 5.294642
Tuesday 4.724082 2.398616
Wednesday 5.565748 2.444719
Thursday 4.369343 2.691123
Friday 4.584384 1.941516
Saturday 5.381143 2.430683
Sunday 4.4918 3.617798
Tab.4  Electricity price forecasting errors for spring weeks using ANN and WLS technique
Method MAPEweek (Winter) MAPEweek (Spring)
ANN 11.2631 4.904462
WLS technique 10.4529 2.853155
Tab.5  Electricity price forecasting errors for winter and spring weeks using ANN and WLS technique
  Structure of BPNN
A Rectangular matrix of size (m 1× n 1)
D Day
E Objective function
h Hour
l Load
L h Load demand at hth hour
m Number of training patterns
m 1 Number of measurements
n Total number of rows in weight matrix from input layer to output layer
n 1 Number of state variables or unknowns
N H Total number of hidden nodes
p Price
P h Electricity price at hth hour
p h actual Actual electricity price at hth hour
p h forecasted Forecasted electricity price at hth hour
p 1 h actual , 24 h Average actual electricity price for the day to avoid the adverse effect of electricity prices close to zero
X Vector of true values i.e., variables of size (n 1× 1)
Z Actual measured values of size (m 1× 1)
MAEday Daily mean average error
a Momentum rate/factor (or) proportionality constant
φ Vector of errors in the measurements of size (m 1× 1)
h Learning rate
  
1 V Vahidinasab, S Jadid, A Kazemi. Day-ahead price forecasting in restructured power systems using artificial neural networks. Electric Power Systems Research, 2008, 78(8): 1332–1342
2 F J Nogales, J Contreras, A J Conejo, R Espínola. Forecasting next-day electricity prices by time series models. IEEE Transactions on Power Systems, 2002, 17(2): 342–348
https://doi.org/10.1109/TPWRS.2002.1007902
3 J Contreras, R Espinola, F J Nogales, A J Conejo. ARIMA models to predict next-day electricity prices. IEEE Transactions on Power Systems, 2003, 18(3): 1014–1020
https://doi.org/10.1109/TPWRS.2002.804943
4 A J Conejo, M A Plazas, R Espinola, A B Molina. Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. IEEE Transactions on Power Systems, 2005, 20(2): 1035–1042
https://doi.org/10.1109/TPWRS.2005.846054
5 P Areekul, T Senjyu, H Toyama, A Yona. A Hybrid ARIMA and neural network model for short-term price forecasting in deregulated market. IEEE Transactions on Power Systems, 2010, 25(1): 524–530
https://doi.org/10.1109/TPWRS.2009.2036488
6 N Amjady. Day-ahead price forecasting of electricity markets by a new fuzzy neural network. IEEE Transactions on Power Systems, 2006, 21(2): 887–896
https://doi.org/10.1109/TPWRS.2006.873409
7 J P S Catalão, H M I Pousinho, V M F Mendes. Hybrid wavelet-PSO-ANFIS approach for short-term electricity prices forecasting. IEEE Transactions on Power Systems, 2011, 26(1): 137–144
https://doi.org/10.1109/TPWRS.2010.2049385
8 H Y Yamin, S M Shahidehpour, Z Li. Adaptive short-term electricity price forecasting using artificial neural networks in the restructured power markets. International Journal of Electrical Power & Energy Systems, 2004, 26(8): 571–581
9 D Singhal, K S Swarup. Electricity price forecasting using artificial neural networks. International Journal of Electrical Power & Energy Systems, 2011, 33(3): 550–555
10 R Weron, A Misiorek. Forecasting spot electricity prices: a comparison of parametric and semi-parametric time series models. International Journal of Forecasting, 2008, 24(4): 744–763
https://doi.org/10.1016/j.ijforecast.2008.08.004
11 J R Cancelo, A Espasa, R Grafe. Forecasting the Electricity Load from one day to one week ahead for the Spanish system operator. International Journal of Forecasting, 2008, 24(4): 588–602
https://doi.org/10.1016/j.ijforecast.2008.07.005
12 J P S Catalão, S J P S Mariano, V M F Mendes, L A F M Ferreira. Short-term electricity prices forecasting in a competitive market: a neural network approach. Electric Power Systems Research, 2007, 77(10): 1297–1304
https://doi.org/10.1016/j.epsr.2006.09.022
13 S K Aggarwal, L M Saini, A Kumar. Electricity price forecasting in deregulated markets: a review and evaluation. International Journal of Electrical Power & Energy Systems, 2009, 31(1): 13–22
14 S Anbazhagan, N Kumarappan. Day-ahead deregulated electricity market price forecasting using neural network input featured by DCT. Energy Conversion and Management 2014, 78: 711–719
15 Osório G J, Matias J C O , Catalão J P S . Electricity prices forecasting by a hybrid evolutionary-adaptive methodology. Energy Conversion and Management, 2014, 80(4): 363–373
16 Y Dong, J Wang, H Jiang, J Wu. Short-term electricity price forecast based on the improved hybrid model. Energy Conversion and Management, 2011, 52(8‒9): 2987–2995
https://doi.org/10.1016/j.enconman.2011.04.020
17 A Arabali, E Chalko, M Etezadi-Amoli, M S Fadali. Short-term electricity price forecasting. Proceedings of IEEE Power and Energy Society General Meeting. Vancouver, CA, 2013
18 N Amjady, A Daraeepour, F Keynia. Day-ahead electricity price forecasting by modified relief algorithm and hybrid neural network. IET Generation, Transmission and Distribution, 2010, 4(3): 432–444
https://doi.org/10.1049/iet-gtd.2009.0297
19 P Ray, S Sen, A K Barisal. Hybrid methodology for short-term load forecasting. IEEE International Conference on Power Electronics, Drives and Energy Systems, 1–6, 2014
20 S M Mahaei, M R Navayi. Power system state estimation with weighted linear least square. International Journal of Electrical and Computer Engineering, 2014, 4(2): 169–178
21 J Zhu. Power Flow Analysis. Wiley-IEEE Press, 2015
22 J Wan, K N Miu. Weighted least squares methods for load estimation in distribution networks. IEEE Transactions on Power Systems, 2003, 18(4): 1338–1345
https://doi.org/10.1109/TPWRS.2003.818588
23 PJM. Pennsylvania–New Jersey–Maryland market. 2015–03–21
24 A J Conejo, M A Plazas, R Espínola, A B Molina. Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. IEEE Transactions on Power Systems, 2005, 20(2): 1035–1042
https://doi.org/10.1109/TPWRS.2005.846054
25 A J Conejo , J Contreras, R Espínola, M A Plazas. Forecasting electricity prices for a day-ahead pool-based energy market. International Journal of Forecasting, 2005, 21(3): 435–462
https://doi.org/10.1016/j.ijforecast.2004.12.005
[1] Arunachalam VELMURUGAN,Marimuthu LOGANATHAN,E. James GUNASEKARAN. Prediction of performance, combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network[J]. Front. Energy, 2016, 10(1): 114-124.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed