Forecasting Monthly Electric Energy Consumption Using Feature Extraction

Abstract

Monthly forecasting of electric energy consumption is important for planning the generation and distribution of power utilities. However, the features of this time series are so complex that directly modeling is difficult. Three kinds of relatively simple series can be derived when a discrete wavelet transform is used to extract the raw features, namely, the rising trend, periodic waves, and stochastic series. After the elimination of the stochastic series, the rising trend and periodic waves were modeled separately by a grey model and radio basis function neural networks. Adding the forecasting values of each model can yield the forecasting results for monthly electricity consumption. The grey model has a good capability for simulating any smoothing convex trend. In addition, this model can mitigate minor stochastic effects on the rising trend. The extracted periodic wave series, which contain relatively less information and comprise simple regular waves, can improve the generalization capability of neural networks. The case study on electric energy consumption in China shows that the proposed method is better than those traditionally used in terms of both forecasting precision and expected risk.

Yearly Electricity Consumption Forecasting using a Nonhomogeneous Exponential Model Optimized by PSO Algorithm

“…For neural network models, the error backpropagation artificial neural network and radial basis function artificial neural network (RBFANN) are the most representative neural network models. As the latter is usually better than the former in terms of learning efficiency and stability [22], RBFANN was selected to forecast India's electricity consumption from 2001 to 2010. As with the ONEM and GM(1, 1), electricity consumption data for 20 continuous years before the forecasting year were also selected to build the model.…”

“…Neural networks and other artificial intelligent algorithms have been used for trend extrapolation of daily [19,20] and monthly [21,22] electricity consumption. Limited by the algorithms themselves, these models usually need large sample data with relative clear laws for parameter training.…”

Energy Demand Forecasting: Combining Cointegration Analysis and Artificial Intelligence Algorithm

“…Contrary to the ARIMA model, PLSR is a popular statistical tool that can deal with data, especially missing or highly correlated data [26]. However, PLSR was recently discussed in the field of energy demand estimation [26,27]. For instance, Zhang et al [26] employed the PLSR model to estimate the transportation energy demand in China on the basis of GDP, urbanization rate, passenger turnover, and freight turnover.…”

Short Term Load Forecasting of Power System

“…They are used as the daily feature vector. Then, the grey relational analysis method is used to calculate the meteorological similarity factors between the forecast day and the historical day [3] . As the power load is generally positively correlated with temperature and negatively correlated with humidity, a multivariate nonlinear regression model between the weather sensitive load and the real-time temperature and humidity can be established [4] .…”