Research Article
Intelligent Forecasting Method for Substation Operating Cost of Power Network with Nonstationary Characteristics
@INPROCEEDINGS{10.1007/978-3-031-18123-8_37, author={Shaohong Lin and Ying Wang and Xuemei Zhu and Ye Ke and Meihua Zou}, title={Intelligent Forecasting Method for Substation Operating Cost of Power Network with Nonstationary Characteristics}, proceedings={Multimedia Technology and Enhanced Learning. 4th EAI International Conference, ICMTEL 2022, Virtual Event, April 15-16, 2022, Proceedings}, proceedings_a={ICMTEL}, year={2022}, month={10}, keywords={Non-stationary characteristics Power grid Substation Operating cost Intelligence Prediction}, doi={10.1007/978-3-031-18123-8_37} }- Shaohong Lin
Ying Wang
Xuemei Zhu
Ye Ke
Meihua Zou
Year: 2022
Intelligent Forecasting Method for Substation Operating Cost of Power Network with Nonstationary Characteristics
ICMTEL
Springer
DOI: 10.1007/978-3-031-18123-8_37
Abstract
With the rapid development of the national economy, the power system has been greatly expanded. The operation cost of power grid substation also presents a trend of sharp increase, which brings great challenges to power system. In order to manage and control the operation cost of substation effectively, the intelligent prediction method of power system operation cost with non-stationary characteristics is proposed. Based on the MCSSD method, this paper extracts the non-stationary features of substation operation information, analyzes the economic load rate of substation, determines the substation capacity, constructs the intelligent forecast model of substation operation cost according to the operation law of substation equipment life cycle, and obtains the forecast result of operation cost, and based on this, formulates the intelligent forecast and control measures of substation operation cost. The experimental data shows that after the method should be proposed, the average time for forecasting the operation cost of substation is 11.6, which is lower than the maximum limit, and the highest prediction accuracy is 83%. The results of the two indicators are in line with the standard, which fully confirms that the proposed method has a better forecasting effect of substation operation cost.
