Seyed-Masoud BARAKATI, Ali Akbar GHARAVEISI, Seyed Mohammad Reza RAFIEI

Short-term load forecasting using mixed lazy learning method

A novel short-term load forecasting method based on the lazy learning (LL) algorithm is proposed. The LL algorithm's input data are electrical load information, daily electricity consumption patterns, and temperatures in a specified region. In order to verify the ability of the proposed method, a load forecasting problem, using the Pennsylvania-New Jersey-Maryland Interconnection electrical load data, is carried out. Three LL models are proposed: constant, linear, and mixed models. First, the performances of the 3 developed models are compared using the root mean square error technique. The best technique is then selected to compete with the state-of-the-art neural network (NN) load forecasting models. A comparison is made between the performances of the proposed mixed-model LL as the superior LL model and the radial basis function and multilayer perceptron NN models. The results reveal significant improvements in the precision and efficiency of the proposed forecasting model when compared with the NN techniques.

Anahtar Kelimeler:

Lazy learning, radial basis function, multilayer perceptron, neural networks, mixed model lazy learning, electric power load forecasting

Short-term load forecasting using mixed lazy learning method

Keywords:

Lazy learning, radial basis function, multilayer perceptron, neural networks, mixed model lazy learning, electric power load forecasting,

PDF

___

Table Detailed values of different load forecasting methods on the first day of January 2007.
The simulation results show a significant improvement in both reduced RMSE and computational speed.
An overall 5% improvement in the accuracy of load forecasting using the MLL technique compared with the
RBF and MLP NN techniques has been achieved. A further improvement is observed in the computation rate
of the proposed MLL technique. It is 5 times faster than the MLP NN technique.
Box GEP, Jenkins GM. Time Series Analysis-Forecasting and Control. San Francisco, CA, USA: Holden-Day, 1970.
Kandil MS, El-Debeiky SM, Hasanien NE. Long-term load forecasting for fast developing utility using a knowledge
based expert system. IEEE T Power Syst 2002; 17: 491–496.
Xiao Z, Zhong SYB, Sun C. BP neural networks with rough set for short term load forecasting. Expert Syst Appl 2009; 36: 273–279.
Xia C, Wang J, Menery KM. Short, medium and long term load forecasting model and virtual load forecaster based
on redial bases function neural network. Int J Elec Power 2010; 32: 743–750.
Ho KL, Hsu YY, Yang CC. Short-term load forecasting using a multilayer neural network with an adaptive learning
algorithm. IEEE T Power Syst 1992; 7: 141–149.
Chen ST, Yu DC, Moghaddamjo AR. Weather sensitive short-term load forecasting using non-fully connected
artificial neural network. IEEE T Power Syst 1992; 7: 1098–1105.
Hippert HS, Pedreira CE, Souza RC. Neural networks for short-term load forecasting: a review and evaluation.
IEEE T Power Syst 2001; 16: 44–55.
Al-Kamdari AM, Soliman SA, Al-Hawary ME. Fuzzy short-term electrical load forecasting. Int J Elec Power 2004; 26: 111–122.
Pai PF. Hybrid ellipsoidal fuzzy systems in forecasting regional electricity loads. Energ Convers Manage 2006; 47: 2283–2289.
Chuangxin BY, Cao GY. Short-term load forecasting using a new fuzzy modeling strategy. In: 5th World Congress on Intelligent Control and Automation Conference; June 2004; Hangzhou, China. pp. 5045–5049.
Gao RG, Soukalas LHT. Neural-wavelet methodology for load forecasting. J Intell Robot Syst 2001; 10: 149–157.
Bashir Z, El-Hawary ME. Short-term load forecasting by using wavelet neural networks. In: Canadian Electrical
and Computer Engineering Conference; March 2000; Halifax, Canada. pp. 163–166.
Tao D, Xiuli W, Xifan W. A combined model of wavelet and neural network for short term load forecasting. In: International Conference on Power System Technology; October 2002. pp. 2331–2335.
Liang RH, Cheng CC. Short-term load forecasting by a neuro-fuzzy approach. Int J Elec Power 2002; 24: 103–111.
Xiao MW, Min BX, Shun ML. Short-term load forecasting with artificial neural network and fuzzy logic. In: International Conference on Power System Technology; October 2002. pp. 1101–1104.
Ansarimehr P, Barghinia S, Habibi H, Vafadar N. Short-term load forecasting for Iran National Power System
using artificial neural network and fuzzy expert system. In: International Conference on Power System Technology; October 2002. pp. 1082–1085.
Barzamini R, Menhaj MB, Khosravi A, Kamalvand SH. Short-term load forecasting for Iran National Power System and its regions using multilayer perceptron and fuzzy inference systems. In: IEEE International Joint Conference on Neural Networks; August 2005; Montreal, Canada. pp. 2619–2624.
Birattari M, Bontempi G, Bersini H. Lazy learning: a local method for supervised learning. In: Jain LC, Kacprzyk J, editors. New Learning Paradigms in Soft Computing. Heidelberg, Germany: Physica-Verlag GmbH, 1999. pp. 97–136.
Aha DW. Lazy Learning. Dordrecht, the Netherlands: Kluwer Academic Publishers, 1997.
Bertolissi E. Data-driven techniques for direct adaptive control: the lazy and the fuzzy approaches. Fuzzy Sets Syst 2001; 3: 3–14.
Bontempi GL. The local paradigm for modeling and control: from neuro-fuzzy to lazy learning. Fuzzy Set Syst 2001; 4: 59–71.
Bontempi GL. Lazy learning for control design. In: European Symposium on Artificial Neural Networks; April 1998; Bruges, Belgium. pp. 73–78.
Corani G. Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning.
Ecol Model 2005; 185: 513–529.
Sorjamaa A. Pruned Lazy Learning Models for Time Series Prediction. Helsinki, Finland: Helsinki University of Technology, 2007.
Aha DW, editor. Special issue on lazy learning. Artif Intell Rev 1997; 11: 1–6. Riverola FF, Iglesias EL, D´ıaz F, M´endez JR, Corchado JM. Spam hunting: an instance-based reasoning system for spam labelling and filtering. Decis Support Syst 2006; 43: 722–736.
Bontempi G, Birattari M, Bersini H. Local learning for iterated time-series prediction. In: International Conference on Machine Learning; 1999; San Francisco, CA, USA. pp. 32–38.
Capacity Adequacy Planning Department. PJM LOAD/ENERGY forecasting model. White paper. Valley Forge, PA, USA: PJM Interconnection, 2007.
Birattari M, Bontempi GL. Lazy Learning. Brussels, Belgium: Free University of Brussels, 1999.
Birattari M, Bontempi G. Lazy learning vs. speedy: a fast algorithm for recursive identification and recursive validation of local constant models. Technical report TR/IRIDIA/99-6. Brussels, Belgium: IRIDIA-ULB, 1999.
Maron O, Moore A. The racing algorithm: model selection for lazy learners. Artif Intell Rev 2006; 11: 193–225.
Goodwin GC, Sin KS. Adaptive Filtering Prediction and Control. Upper Saddle River, NJ, USA: Prentice Hall, 1984.
Ho KL, Hsu YY, Chen CF, Lee TE, Liang CC, Lai TS, Chen KK. Short term load forecasting of Taiwan power system using a knowledge-based expert system. IEEE T Power Syst 1990; 5: 1214–1221.
Goia A, May C, Fusai G. Functional clustering and linear regression for peak load forecasting. Int J Forecasting 2010; 26: 700–711.
Kariniotakis GN. Load forecasting using dynamic high-order neural networks. In: Proceedings of the IEEE 2nd International Forum on the Applications of Neural Networks to Power Systems; April 1993; Yokohoma, Japan. pp. 801–805.
Hippert HS, Tailor JW. An evaluation of Bayesian techniques for controlling model complexity and selecting inputs
in a neural network for short-term load forecasting. Neural Networks 2010; 23: 386–395.
Buhmann MD, Ablowitz MJ. Radial Basis Functions Theory and Implementations. Cambridge, UK: Cambridge University, 2003.
Chen S, Cowan CFN, Grant PM. Orthogonal least squares learning algorithm for radial basis function networks. IEEE T Neural Networ 1991; 2: 224–230.
Poggio T, Girosi F. Networks for approximation and learning. Proc IEEE 1990; 78: 1484–1487.
Jones RD, Lee YC, Barnes CW, Flake GW. Function approximation and time series prediction with neural networks.
In: International Joint Conference on Neural Networks; June 1990; San Diego, CA, USA. pp. 649–665.
Haykin S. Neural Networks: A Comprehensive Foundation. Upper Saddle River, NJ, USA: Prentice Hall, 1998.