A Small‐Sample Adaptive Hybrid Model for Annual Electricity Consumption Forecasting

Abstract

Annual electricity consumption forecasting is one of the important foundations of power system planning. Considering that the long-term electricity consumption curves of developing countries usually present approximately exponential growth trends and linear and accelerated growth rate trends may also appear in certain periods, this paper first proposes a small-sample adaptive hybrid model (AHM) to extrapolate the above curves. The iterative trend extrapolation equation of the proposed model can simulate the linear, exponential, and steep trends adaptively at the same time. To estimate the equation parameters using small samples, the partial least squares (PLS) and iteration starting point optimization algorithms are suggested. To evaluate forecasting performance, the artificial neural network (ANN), grey model (GM), and AHM are used to forecast electricity consumption in China from 1991 to 2014, and then the results of these models are compared. Analysis of the forecasting results shows that the AHM can overcome stochastic changes and respond quickly to changes in the main electricity consumption trend because of its specialized equation structure. Overall error analysis indicators also show that AHM often obtains more precise forecasting results than the other two models.

Electricity consumption probability density forecasting method based on LASSO-Quantile Regression Neural Network

“…Amina et al [15] implemented a novel fuzzy wavelet neural network model for electricity consumption forecasting in the power system of the Greek Island of Crete, which provided significantly better results. In [16], a small-sample adaptive hybrid model (AHM) based on trend extrapolation method was proposed to forecast electricity consumption in China from 1991 to 2014, which showed robustness to stochastic changes and obtained more precise forecasting results. Al-Ghandoor et al [17] presented an empirical model based on multivariate linear regression of time series for the Jordanian industrial sector, which identified the main influential factors of electricity consumption.…”

Forecasting the Electricity Demand and Market Shares in Retail Electricity Market Based on System Dynamics and Markov Chain

“…In the matter of energy demand, various forecasting models have been applied to predict the electricity consumption. Traditional methods such as regression analysis (RA), time series analysis, nonparametric method, and small-sample adaptive hybrid model as well as soft computing techniques such as fuzzy logic, genetic algorithm, and neural networks are being extensively used [12][13][14][15][16][17]. Support vector regression, ant colony, and particle swarm optimization are new techniques being adopted for energy demand forecasting.…”