Abstract
Forecasting the electricity consumption has always played an important role in the management of power system management, which requires higher forecasting technology. Therefore, based on the principle of "new information priority", combined with rolling mechanism and Markov theory, a novel grey power-Markov prediction model with time-varying parameters (RGPMM(λ,1,1)) is designed, which overcomes the inherent defects of fixed structure and poor adaptability to the changes of original data. In addition, in order to prove the validity and applicability of the prediction model, we have used the model to predict China's total electricity consumption, and have compared it with the prediction results by a series of benchmark models. The result shows that the can better adapt to the characteristics of electricity consumption data, and it also shows the advantages of the proposed forecasting model. In this paper, the proposed forecasting model is used to predict China's total electricity consumption in the next six years from 2018 to 2023, so as to provide certain reference value for power system management and distribution.
Highlights
China is a developing country and is in a period of rapid development
Electricity consumption forecast is an important part of Power Economic Planning, energy investment, and environmental protection (Lin and Liu, 2016)
Accurate electricity consumption forecast is affected by a series of factors, such as population (Hussain et al, 2016), economic growth (Lin and Liu, 2016), power facilities (Khosravi et al, 2012), and climate factors (Hernández et al, 2013), making the prediction problem a challenging and complex task
Summary
Electricity consumption forecast is an important part of Power Economic Planning, energy investment, and environmental protection (Lin and Liu, 2016). Electricity consumption forecast has become an important research area in the operation and management of modern power systems (Kavousi-Fard et al, 2014). The high and low accuracy of electricity consumption forecasting (Amber et al, 2018) is of great significance to economic development and power planning. Accurate electricity consumption forecast is affected by a series of factors, such as population (Hussain et al, 2016), economic growth (Lin and Liu, 2016), power facilities (Khosravi et al, 2012), and climate factors (Hernández et al, 2013), making the prediction problem a challenging and complex task. In order to solve these problems, in recent years, many domestic and foreign experts, scholars and related research institutions have done a lot of in-depth research on electricity consumption forecast models. The main methods are: Nonlinear intelligent models (Bekiroglu et al, 2018, Hernández et al, 2014), traditional statistical analysis models (Chui et al, 2009, Mohamed and Bodger, 2005), and grey prediction models (Xiao et al, 2017)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
