Predictive-Modeling Technologies in Web Power Engineering

Abstract:

Web marketing can improve the management level of power-grid enterprises. With the increasing of market-oriented process, it is necessary to classify the customer efficiently to provide special electricity services. The predictive-modeling technologies can carry out classification for customer well. Thus, the four typical predictive-modeling technologies--regression analysis, Bayesian networks, decision tree, and neural networks--are introduced. In addition, the instances in web power marketing are used for illustrating these methods. The application of one or more predictive-modeling technologies can classify well to improve the marketing efficient of power-grid enterprises.

• Periodical: Applied Mechanics and Materials (Volume 312)
• Pages: 923-927
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.312.923
• Online since: February 2013
• Authors: Gong Li Rong
• Keywords: Bayesian Network (BN), Customer Classification, Decision Tree, Neural Network (NN), Predictive-Modeling, Regression Analysis, Web Power Marketing

References

[1] LI Xiang. The discussion about electricity service marketing[J]. State Grid, 2007, (3):56–57.

[2] LI Xiang. What is the suitable power marketing in modern times[J]. State Grid, 2007, (8):29–31.

[3] HUANG Xinhong, CHEN Hongxia. The application of customer classification strategy to power marketing[J]. China Electric Power Education, 2011, (36):76–77.

[4] SUN Zhongwen. Based on customer credit electricity marketing project management[Master Thesis][D]. Beijing:North China Electric Power University, 2007.

[5] XU Jianhua. Mathematical Methods in Contemporary Geography[M]. Beijing:Higher education press, 1994.

[6] PAOLO Giudici. Applied Data Mining[M]. Fang Yuan, etc. Beijing:Electronic Industry Press, 2004.

[7] ZHANG Lianwen, GUO Haipeng. Introduction to Bayesian networks[M]. Beijing:Science Press, 2006.

[8] ZHOU Zhongbao, DONG Doudou, Zhou Jinglun. Application of Bayesian Networks in Reliability Analysis[J]. Systems Engineering-Theory and Practice, 2006, (6):95–100.

DOI: 10.1109/ecbs.2006.58

[9] LUAN Lihua, JI Genlin. The study on decision tree classification techniques[J]. Computer Engineering, 2004, 30(9):94–96.

[10] Quinlan, J R. Inductin of Decision Trees[J]. Machine learning, 1986, 1:81–106.

[11] Quinlan, J R. C4.5: Programs for Machine learning[M]. San Mateo, CA:Morgan Kaufmann Publisher, 1993.

[12] HOPFIELD, John. Neural networks and physical systems with emergent collective computational abilities[J]. Proceedings of the National Academy of Sciences of the USA, 1982, 79(8) :2554–2558.

DOI: 10.1073/pnas.79.8.2554

[13] RUMELHART, D. E., MCCLELLAND, J. L. & the PDP research group. Parallel distributed processing: Explorations in the microstructure of cognition. Volume I:foundations[M]. Cambridge, MA:MIT Press, 1986.

DOI: 10.21825/philosophica.82503

[14] MCCLELLAND, J. L., RUMELHART, D. E. & the PDP research group. Parallel distributed processing: Explorations in the microstructure of cognition. Volume II:Psychological and Biological Models[M]. Cambridge, MA:MIT Press, 1986.

DOI: 10.21825/philosophica.82503

[15] KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biological Cy bernetics, 1982, 43(1):59–69.

DOI: 10.1007/bf00337288

[16] CARPENTER G A, GROSSBERG S. ART 2: Self-organization of stable category recognition codes for analog input patterns[J]. Applied Optics, 1987, 26(23):4919–4930.

DOI: 10.1364/ao.26.004919