Application of Time Series Prediction Models in Chinese Electricity Consumption Analysis

Yisheng Gao; Shaoxuan Xie

doi:10.54097/m2cwn583

Authors

Yisheng Gao
Shaoxuan Xie

DOI:

https://doi.org/10.54097/m2cwn583

Keywords:

Time series prediction, ARIMA model, electricity consumption forecast, cyclical factors, seasonal decomposition.

Abstract

Study focuses on the application of time series prediction models in analyzing electricity consumption in China, aiming to promote the intelligentization and sustainable development of the country's power system. The ARIMA model was chosen for this research, incorporating historical electricity data to forecast future consumption. Through a series of steps including data preprocessing, model construction, and prediction analysis, the results indicate a general growth trend in electricity consumption, influenced by seasonal and cyclical factors. By plotting periodic decomposition charts, the study visually reveals the components and patterns of electricity data, providing scientific decision-making support for the planning, scheduling, and management of the electricity industry.

Downloads

Download data is not yet available.

References

Hu X. Stability prediction analysis of strong rainfall on slopes based on time series ARIMA model [J]. Pearl River Water Transport, 2024, (04).

YAN Xun, TIE Chengcheng, YAN Wei et al. Analysis of global temperature prediction based on ARIMA model and CNN-LSTM combined model [J]. Science and Innovation, 2024, (02).

ZHAO Ziyue, LIU Xuemei. Crop sowing area prediction based on ARIMA-GM combination model--Taking Jilin Province as an example [J]. Jilin Water Resources, 2024, (01).

NI Xuan, CHEN Yichen. ARIMA model combined with LSTM neural network to establish a prediction model for drug procurement decision-making [J]. Heilongjiang Science, 2024, 15 (02).

Jia Li. Power analysis and prediction based on neural network [D]. Southwest University of Science and Technology, 2021.

Liu Yibo. Power prediction analysis based on LSTM neural network [J]. Integrated Circuit Application, 2023, 40 (08).

SHEN Xingru. Electricity prediction based on big data mining technology [D]. Southeast University, 2022.

Yan Lidan. Application of particle filtering method based on ARMA model in electricity consumption analysis [D]. Guilin University of Electronic Science and Technology, 2022.

YANG Yang, TIAN Dingsheng, ZHANG Bao'an, et al. Research on urban economy and population forecasting based on ARIMA model [J]. Comprehensive Transport, 2023, 45 (11).

Zhang Xinyu. Forecasting analysis of disk occupancy based on ARIMA and exponential smoothing algorithm [J]. Modern Information Technology, 2023, 7 (24): 67-71.