Electric supply and demand forecasting using seasonal grey model based on PSO-SVR

Abstract

PurposeGiven the effects of natural and social factors, data on both the supply and demand sides of electricity will produce obvious seasonal fluctuations. The purpose of this article is to propose a new dynamic seasonal grey model based on PSO-SVR to forecast the production and consumption of electric energy.Design/methodology/approachIn the model design, firstly, the parameters of the SVR are initially optimized by the PSO algorithm for the estimation of the dynamic seasonal operator. Then, the seasonal fluctuations in the electricity demand data are eliminated using the dynamic seasonal operator. After that, the time series after eliminating of the seasonal fluctuations are used as the training set of the DSGM(1, 1) model, and the corresponding fitted, and predicted values are calculated. Finally, the seasonal reduction is performed to obtain the final prediction results.FindingsThis study found that the electricity supply and demand data have obvious seasonal and nonlinear characteristics. The dynamic seasonal grey model based on PSO-SVR performs significantly better than the comparative model for hourly and monthly data as well as for different time durations, indicating that the model is more accurate and robust in seasonal electricity forecasting.Originality/valueConsidering the seasonal and nonlinear fluctuation characteristics of electricity data. In this paper, a dynamic seasonal grey model based on PSO-SVR is established to predict the consumption and production of electric energy.

A matrixed nonlinear exponential grey Bernoulli model for interval number prediction of crude oil futures prices

“…The grey prediction model performs excellently in predicting uncertain systems with small samples (Deng, 1982). It has been applied in fields such as traffic (Mao et al, 2018;He et al, 2023b), tourism demand (Hu, 2023;Jiang and Hu, 2023), material life (Li and Xie, 2023) and energy consumption (Ofosu-Adarkwa and Yao and Mao, 2023). GM(1,1) can be improved according to the needs of the actual sequence.…”

A novel fractional order Grey prediction modeland its application to Chinese carbon emissions

“…Grey system theory was proposed by Professor Deng Julong in 1982 for a "small sample, poor information" system, and in recent years researchers had more research results in grey correlation analysis (Chu and Xiao 2023;Duan and Pang 2023a), grey prediction model (He et al 2023;Zeng et al 2019), etc. In particular, the grey prediction model part is an important part of the grey theory, which has been widely applied to energy (Yao and Mao 2023;Zeng et al 2020;Duan and Luo 2022), transportation (Wen et al 2023;Duan and Wang 2023b), environment (Tu and Chen 2021;Wang et al2020), and other fields. In recent years, grey prediction models have also been applied to carbon emission forecasting, for example, Şahin (2019) combined linear and nonlinear metabolic grey prediction models and optimized their parameters, and then the models were used to predict greenhouse gas emissions in Turkey, providing effective reference recommendations for governmental plans based on the calculated results.…”

Multi-country CO2 emission forecasting based on background value optimized Nonlinear Grey Bernoulli and BP neural network combined model

“…When the nonlinear parameter is 2, it is called the Grey Verhulst model, this model is suitable for dealing with time series growth such as ' S ' curve [18,[32][33]. Many scholars have improved the model in terms of both background value optimization and structural parameter adjustment [31]. Zhou et al take power index and background value coefficient as the core decision variables, and use particle swarm optimization (PSO) technology to optimize these two variables [34].…”