Power customer complaint prediction model based on time series analysis

被引：1

作者：

Guo S. ^{[1
]}

Tang L. ^{[1
]}

Guo X. ^{[1
]}

Huang Z. ^{[1
]}

机构：

[1] Information and Telecommunications Company, State Grid Shandong Electric Power Company, Jinan

来源：

Revue d'Intelligence Artificielle | 2020年 / 34卷 / 04期

关键词：

Backpropagation neural network (BPNN); Customer service; Prediction model; Time series analysis;

D O I：

10.18280/ria.340412

中图分类号：

学科分类号：

摘要：

To improve customer service of power enterprises, this paper constructs an intelligent prediction model for customer complaints in the near future based on the big data on power service. Firstly, three customer complaint prediction models were established, separately based on autoregressive integrated moving average (ARIMA) time series algorithm, multiple linear regression (MLR) algorithm, and backpropagation neural network (BPNN) algorithm. The predicted values of the three models were compared with the real values. Through the comparison, the BPNN model was found to achieve the best predictive effect. To help the BPNN avoid local minimum, the genetic algorithm (GA) was introduced to optimize the BPNN model. Finally, several experiments were conducted to verify the effect of the optimized model. The results show that the relative error of the optimized model was less than 40% in most cases. The proposed model can greatly improve the customer service of power enterprises. © 2020 Lavoisier. All rights reserved.

引用

页码：471 / 477

页数：6

共 20 条

[1]

Montoya F.G., Banos R., Gil C., Espin A., Alcayde A., Gomez J., Minimization of voltage deviation and power losses in power networks using Pareto optimization methods, Engineering Applications of Artificial Intelligence, 23, 5, pp. 695-703, (2010)

[2]

Dragicevic T., Wheeler P., Blaabjerg F., Artificial intelligence aided automated design for reliability of power electronic systems, IEEE Transactions on Power Electronics, 34, 8, pp. 7161-7171, (2018)

[3]

Wang H.F., Zhang C.Y., Lin D.Y., He B.T., An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression, Frontiers of Information Technology & Electronic Engineering, 20, 6, pp. 816-828, (2019)

[4]

Yu S., Zhu K., Diao F., A dynamic allparameters adaptive BP neural networks model and itsapplication on oil reservoir prediction, AppliedMathematics and Computation, 195, 1, pp. 66-75, (2008)

[5]

Ling M.H., Tsui K.L., Balakrishnan N., Accelerated degradation analysis for the quality of asystem based on the gamma process, IEEE Transactionson Reliability, 64, 1, pp. 463-472, (2014)

[6]

Miao X., Hao Y., Zhang F., Zou S., Ye S., Xie Z., Spatial distribution of heavy metals and theirpotential sources in the soil of Yellow River Delta: Atraditional oil field in China, EnvironmentalGeochemistry and Health, 42, 1, pp. 7-26, (2020)

[7]

Wang Y., Wang C., Shi C., Xiao B., Short-termcloud coverage prediction using the ARIMA time seriesmodel, Remote Sensing Letters, 9, 3, pp. 274-283, (2018)

[8]

Chen C.K., Shie A.J., Yu C.H., A customer-oriented organisational diagnostic model based on datamining of customer-complaint databases, ExpertSystems with Applications, 39, 1, pp. 786-792, (2012)

[9]

Gregoire Y., Laufer D., Tripp T.M., Acomprehensive model of customer direct and indirectrevenge: Understanding the effects of perceived greedand customer power, Journal of the Academy ofMarketing Science, 38, 6, pp. 738-758, (2010)

[10]

Sun G., Bin S., Jiang M., Cao N., Zheng Z., Zhao H., Xu L., Research on Public Opinion PropagationModel in Social Network Based on Blockchain, CMC-Computers Materials & Continua, 60, 3, pp. 1015-1027, (2019)

← 1 2 →