Abstract
Considering the importance of the peak load to the dispatching and management of the system, the error of peak load is proposed in this paper as criteria to evaluate the effect of the forecasting model. This paper proposes a systemic framework that attempts to used data mining and knowledge discovery (DMKD) pretreatment of the data. And a new model is proposed which combining artificial neural networks with data mining and knowledge discovery for electric load forecasting. With DMKD technology, the system not only could mine the historical daily loading which had the same meteorological category as the forecasting day to compose data sequence with highly similar meteorological features, meanwhile, but also could eliminate the redundant influential factors. Then an artificial neural network is constructed to predict according to its characteristics. Using this new model, it could eliminate the redundant information accelerated the training of neural network and improve the stability of the convergence. Comparing with single SVM and BP neural network, this new method can achieve greater forecasting accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Niu, D.-x., Cao, S., Lu, J.: Technology and Application of Power Load Forecasting. China Power Press, Beijing (2009)
Niu, D.-x., Wang, Y.-l., Wu, D.-s.: Dash. Power load forecasting using support vector machine and ant colony optimization. Expert Systems with Applications 37, 2531–2539 (2010)
Niu, D.-x., Wang, Y.-l., Duan, C.-m., Xing, M.: A New Short-term Power Load Forecasting Model Based on Chaotic Time Series and SVM. Journal of Universal Computer Science 15(13), 2726–2745 (2009)
Luo, Q.: Advancing knowledge discovery and data mining. In: Workshop on Knowledge Discovery and Data Mining, pp. 1–5 (2008)
Nolan, R.L., Wetherbe, J.C.: Toward a comprehensive framework for MIS research. MIS Quarterly 4(2), 1–19 (1980)
Zhang, W., Zeng, T., Li, H.: Parallel mining association rules based on grouping. Computer Engineering 30(22), 84–85 (2004)
Li, Q., Yang, L., Zhang, X., et al.: An effective apriori algorithm for association rules in data mining. Computer Application and Software 21(12), 84–86 (2004)
Han, J., Pei, J., Yin, Y., Mao, R.: Mining Frequent Patterns without Candidate Generation: A Frequent-Pattern Tree Approach. Data Mining and Knowledge Discovery, 53–87 (2004)
Huang, H.G., Hwang, R.C., Hsieh, J.G.: A new artificial intelligent peak power load forecaster based on non-fixed neural networks. Electrical Power Energy Syst., 245–250 (2002)
Li, K., Gao, C., Liu, Y.: Support vector machine based hierarchical clustering of spatial databases. Journal of Beijing Institute of Technology 22(4), 485–488 (2002)
He, F., Zhang, G., Liu, Y.: Improved load forecasting method based on BP network. East China Electric Power 32(3), 31–33 (2004)
Zi, Z., Zhao, S., Wang, G.: Study of relationship between fuzzy logic system and support vector machine. Computer Engineering 30(21), 117–119 (2004)
Jiang, Y., Lu, Y.: Short-term Load Forecasting Using a Neural Network Based on Similar Historical Day Data. In: Proceedings of the EPSA, pp. 35–40 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Y., Niu, D., Wang, Y. (2010). Power Load Forecasting Using Data Mining and Knowledge Discovery Technology. In: Nguyen, N.T., Le, M.T., Świątek, J. (eds) Intelligent Information and Database Systems. ACIIDS 2010. Lecture Notes in Computer Science(), vol 5990. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12145-6_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-12145-6_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12144-9
Online ISBN: 978-3-642-12145-6
eBook Packages: Computer ScienceComputer Science (R0)