Volume 16, Issue 1 (5-2019)                   JSDP 2019, 16(1): 41-56 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Kebriaei H, Kamalinejad H, Nadjar Araabi B. Short term load forecast by using Locally Linear Embedding manifold learning and a hybrid RBF-Fuzzy network. JSDP. 2019; 16 (1) :41-56
URL: http://jsdp.rcisp.ac.ir/article-1-776-en.html
College of Engineering, University of Tehran
Abstract:   (394 Views)
The aim of the short term load forecasting is to forecast the electric power load for unit commitment, evaluating the reliability of the system, economic dispatch, and so on. Short term load forecasting obviously plays an important role in traditional non-cooperative power systems. Moreover, in a restructured power system a generator company (GENCO) should predict the system demand and its corresponding price for efficient decision making.
The task of a forecasting engine is to find the relation of the inputs and outputs of the system and also predicts the outputs for a given inputs. Therefore, the accuracy of forecasting is highly affected by the inputs of the forecasting engine. This effect can be studied from two points of view; First, extracting the more informative inputs and second, reducing the dimension of input space, both make it possible to learn the forecasting network via more simple models with more generalization. As a result, a reduced informative input space leads to lower prediction error. In many previous load forecasting methods, the inputs have been selected empirically. In this manner, the more correlative factors with the load in the forecasting day have been chosen as the inputs. They are generally a combination of load history and weather conditions. Several researches are focused on mathematical approaches of the input selection which are mainly based on principal component analysis (PCA) method as well as some intelligent algorithms.
In this paper, a manifold learning method namely Locally Linear Embedding (LLE) is proposed, aiming to extract more informative inputs and to reduce the dimension of input space for short term load forecasting. Among all methods based on manifold learning, it can be seen that LLE performs very well in extracting the electric load curve features. The aim of this paper is to analyze the features of the load curve for estimating this curve in future. The extensive computational experiments show that the extracted features by LLE results in less prediction error than two other methods. Furthermore, LLE acts faster and makes input dimension lower than the two other methods. In the following section we will discuss the LLE method. The LLE method finds the nonlinear relationships among features by mapping a locally linear manifold in the feature space. Extracting the more informative inputs by extracting the combinational features by finding the nonlinear dependences of the features, results in reducing the dimension of input space. The resulted inputs from feature extraction and dimension reduction are utilized for load forecasting.
To examine the effect of the proposed feature extraction method on load prediction error, a hybrid prediction system is proposed which is a combination of a radial basis function (RBF) network and a fuzzy system. The RBF network is the core of the prediction engine and works with historical load data as its inputs. The fuzzy inference system is combined with the RBF network to incorporate the impact of temperature on load. The case studies are carried out on the real data of electric power load of Mazandaran area in Iran. The efficiency of the proposed forecasting engine is compared with three benchmarks, the artificial neural network, time series and neuro-fuzzy methods. Furthermore, the proposed input selection method (LLE) is compared with principal component analysis (PCA) and empirical selection of inputs. Simulation results with statistical significance analysis show that the LLE method with the proposed forecasting engine is superior to other input selection methods and forecasting engines in sense of lower input dimension and lower prediction error.
Full-Text [PDF 5658 kb]   (103 Downloads)    
Type of Study: Research | Subject: Paper
Received: 2017/09/5 | Accepted: 2018/05/7 | Published: 2019/06/10 | ePublished: 2019/06/10

1. [1] D. Liang, M. Zhichun, "Short-term load forecasting based on fuzzy neural network," Journal of University of Science and Technology Beijing, 4, pp. 46-49, 1997.
2. [2] K.H Kim, H.S Youn, Y.C. Kang, "Short-term Load Forecasting for Special Days in anomalous Load Conditions Using Neural Network and Fuzzy Inference Method," IEEE Transactions on Power Systems, vol.15, pp. 559-569, 2000. [DOI:10.1109/59.867141]
3. [3] W. Charytoniuk, M. S. Chen, "Neural Network design for Short-Term Load Forecasting," Proceedings of International Conference on Electric Utility Deregulation and Restructuring and Power Technologies, London, pp. 4-7, 2000.
4. [4] Z. Tao, Z. Dengfu, Z. Lin, W. Xifan, X. Daozhi, "Short-Term Load Forecasting Using Radial Basis Function Networks and Expert system," Journal of XI'AN JIAOTONG University , vol.35, pp. 331-334, 2001.
5. [5] Z. Xin, C. Tian-Lun, "Nonlinear Time Series Forecast Using Radial Basis Function Neural Network," Commun. Theor. Phys, vol.40, pp.165-168, 2003. [DOI:10.1088/0253-6102/40/2/165]
6. [6] V. S. Kodogiannis, E. M. Anagnostakis, "Soft computing based techniques for short-term load forecasting," Fuzzy Sets and Systems 128(3), pp. 413-426, 2002. [DOI:10.1016/S0165-0114(01)00076-8]
7. [7] R.R.B. de Aquino, et.al, "Combined Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System for Improving a Short-Term Electric Load Forecasting," Lecture Notes in Computer Science, 4669, 779-788, 2007. [DOI:10.1007/978-3-540-74695-9_80]
8. [8] Musa, Abdallah Bashir. "A comparison of ℓ1-regularizion, PCA, KPCA and ICA for dimensionality reduction in logistic regression." International Journal of Machine Learning and Cybernetics 5.6 , pp.861-873, 2014. [DOI:10.1007/s13042-013-0171-7]
9. [9] L. Cayton, Algorithms for manifold learning, University of California, San Diego, Tech. Report, 2005.
10. [10] I. Borg and P. Groenen, Modern Multidimen-sional Scaling: Theory and Applications. New York: Springer-Verlag, 1997. [DOI:10.1007/978-1-4757-2711-1]
11. [11] J. B. Kruskal, "Multidimensal scaling by optimizing goodness of fit to a nonmetric hypothesis," Psychometrika, vol.29, pp. 1-27, 1964. [DOI:10.1007/BF02289565]
12. [12] Ji, Rongrong, et al, "Towards Optimal Manifold Hashing via Discrete Locally Linear Embedding," IEEE Transactions on Image Processing, 2017. [DOI:10.1109/TIP.2017.2735184] [PMID]
13. [13] Liu, Xin, et al, "Locally linear embedding (LLE) for MRI based Alzheimer's disease classification," Neuroimage, vol. 83, pp.148-157.2013. [DOI:10.1016/j.neuroimage.2013.06.033] [PMID] [PMCID]
14. [14] J. Yang, B. Ming Xiang, and Y. Zhang, "Multi-manifold Discriminant Isomap for visualization and classification," Pattern Recognition, vol. 55, pp. 215-230, 2016. [DOI:10.1016/j.patcog.2016.02.001]
15. [15] M. Belkin ,and P. Niyogi, "Laplacian eigenmaps for dimensionality reduction and data representation," Neural Compute, vol. 15(6), pp. 1373-1396, 2003. [DOI:10.1162/089976603321780317]
16. [16] Ye. Qiang, and W. Zhi, "Discrete hessian eigenmaps method for dimensionality reduction," Journal of Computational and Applied Mathematics, vol.278, pp.197-212, 2015. [DOI:10.1016/j.cam.2014.09.011]
17. [17] Su, Zuqiang, et al., "Fault diagnosis method using supervised extended local tangent space alignment for dimension reduction," Meas-urement, vol. 62, pp.1-14, 2015. [DOI:10.1016/j.measurement.2014.11.003]
18. [18] L. Haghverdi, F. Buettner, and J. Fabian, "Diffusion maps for high-dimensional single-cell analysis of differentiation data," Bioin-formatics, vol. 31.18, pp.2989-2998, 2015. [DOI:10.1093/bioinformatics/btv325] [PMID]
19. [19] Lunga, Dalton, et al. "Manifold-learning-based feature extraction for classification of hyperspectral data: A review of advances in manifold learnping," IEEE Signal Processing Magazine, vol. 31.1, pp.55-66, 2014. [DOI:10.1109/MSP.2013.2279894]
20. [20] J. Wang, Z. Zhang, and H. Zha, "Adaptive manifold learning," In Advances in Neural Information Processing Systems, 2004.
21. [21] W. H Press, et al, Numerical Recipes in C: The Art of Scientific Computing, Cambridge University Press, pp. 616, 1992.
22. [22] R. Fariborznia, N. Amjadi, "short term load forecast by using time series decomposition of load and neural networks," Journal of Modeling in Engineering, vol.15 (16), 2007.
23. [23] S.sh. Seyed Jalal, et al, "A Composite Model for Load Forecasting in the Restructured Electricity Market," Journal of Quality and Productivity in Iran Electric Industry, vol.2(3), 2013.
24. [24] A. Moshari, et al., "Purification of Neural Network Train Data and its Effect on Reducing Short-Term Prediction Errors of Power Systems," Esteghlal Magazine. vol.28 (2), 2009.
25. [25] H. Shayeghi, et al, "Multi-Input Multi-output System Modeling for simultaneous prediction of price and load in the smart grid by applying load management," Journal of Computational Intelligence in Electrical Engineering, Vol. 6 (4), 2015.
26. [26] M. Karimi , et al., "Prioritizing the same days to predict the short-term load of Iran's network by considering the temperature and power system segmentation," Journal of Iranian Association of Electrical and Electronics Engineers. Vol. 14 (3), 2016.
27. [27] H. Ghanei yakhdan, "A new method to hide errors in video frames using RBF neural network," Journal of Signal and Data Processing, vol.10 (1), 2013.
28. [28] N. Goharian, et al., "Use of combination of genetic algorithm and artificial neural networks to predict the bite force from an electromyogram signal," Journal of Signal and Data Processing, Vol.14 (1), 2017.

Add your comments about this article : Your username or Email:

Send email to the article author

© 2015 All Rights Reserved | Signal and Data Processing