Abstract
At present, the change of equipment state is not considered in the prediction of power grid maintenance cost, which leads to inaccurate prediction results. Based on multi-dimensional mixed information, a prediction method of power grid intelligent maintenance cost is proposed. According to the expenses of routine maintenance of various equipment, the intelligent maintenance cost of power grid is divided into routine maintenance and power supply loss cost. The CS algorithm is used to determine the maintenance strategy of power grid equipment, so as to obtain the maximum power grid income under the minimum maintenance cost. The multidimensional mixed information extracted from the daily operation of smart grid determines the maintenance status of equipment in the maintenance strategy. Through the methods of grey prediction and multiple linear regression prediction, the diversified prediction results are output, and then the weighted value of the prediction output results is assigned with the help of the combined prediction model to realize the cost prediction of multi-dimensional indicators. The experimental results show that the intelligent maintenance cost prediction of power grid based on multi-dimensional mixed information can improve the prediction accuracy and contribute to the lean management of power enterprises. Further improve the efficiency and benefit of the multi-dimensional index linkage budget method, promote the digital transformation of power grid enterprises, and provide reference for power supply enterprises.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wei, Q., Yang, T., Gao, Y.: Simulation research on multi-energy complementary dispatch based on hybrid power flow algorithm. Comput. Simulat. 38(11), 77–81 (2021)
Meng, F.: Research on overhaul method of relay protection in intelligent substation. Telecom. Power Technol. 37(12), 109–111 (2020)
Wu, S.: Intelligent budget management and forecast optimization analysis of power grid enterprises under the background of big data. Value Eng. 40(36), 163–165 (2021)
Li, H., Yang, Y., Ran, Q.: Progress-cost forecasting of power grid projects based on GA-SVM quality earned value. Mech. Electric. Eng. Technol. 49(10), 93–95 (2020)
Wang, M., Liu, Y., Gao, H., et al.: A two-stage stochastic model predictive control strategy for active distribution network considering operation cost risk. Adv. Power Syst. Hydroelectr. Eng. 36(11), 8–18 (2020)
Pan, J., Chen, Q., Jin, S.: A mathematical method for operation and maintenance cost prediction based on transfer learning under non-stationary power data. Adv. Appl. Math. 10(1), 98–108 (2021)
Xiong, Y., Zhan, Z., Ke, F., et al.: Overhaul operation and maintenance cost prediction of substation based on improved BP neural network. J. Electric Power Sci. Technol. 36(4), 44–52 (2021)
Cao, M., Xu, A., Jiang, Y., et al.: The application of Elman neural network in uninterrupted maintenance of power grid. J. Phys: Conf. Ser. 1673, 012057 (2020)
Xiao, H., Cao, M.: Balancing the demand and supply of a power grid system via reliability modeling and maintenance optimization. Energy 210 (2020)
Xu, X., Peng, L., Ji, Z., et al.: Research on substation project cost prediction based on sparrow search algorithm optimized BP neural network. Sustainability 13 (2021)
Wu, J., Liu, H., Yang, J., et al.: Tree barrier prediction of power lines based on tree height growth model. IOP Conf. Ser. Earth Environ. Sci. 645(1), 012008 (2021)
Chen, T., Jiang, Y., Jian, W., et al.: Maintenance personnel detection and analysis using mask-RCNN optimization on power grid monitoring video. Neural Process. Lett. 51(3), 1599–1610 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Wang, Y., Zhu, X., Ke, Y., Zheng, C., Zhang, S. (2023). Research on Hybrid Maintenance Cost Prediction of Smart Grid Based on Multi-dimensional Information. In: Fu, W., Yun, L. (eds) Advanced Hybrid Information Processing. ADHIP 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 468. Springer, Cham. https://doi.org/10.1007/978-3-031-28787-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-28787-9_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28786-2
Online ISBN: 978-3-031-28787-9
eBook Packages: Computer ScienceComputer Science (R0)