A Hybrid BA-ELM Model Based on Factor Analysis and Similar-Day Approach for Short-Term Load Forecasting

Abstract

Accurate power-load forecasting for the safe and stable operation of a power system is of great significance. However, the random non-stationary electric-load time series which is affected by many factors hinders the improvement of prediction accuracy. In light of this, this paper innovatively combines factor analysis and similar-day thinking into a prediction model for short-term load forecasting. After factor analysis, the latent factors that affect load essentially are extracted from an original 22 influence factors. Then, considering the contribution rate of history load data, partial auto correlation function (PACF) is employed to further analyse the impact effect. In addition, ant colony clustering (ACC) is adopted to excavate the similar days that have common factors with the forecast day. Finally, an extreme learning machine (ELM), whose input weights and bias threshold are optimized by a bat algorithm (BA), hereafter referred as BA-ELM, is established to predict the electric load. A simulation experience using data deriving from Yangquan City shows its effectiveness and applicability, and the result demonstrates that the hybrid model can meet the needs of short-term electric load prediction.

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

“…Long short-term memory (LSTM) is also a variation of ANN which performs well on load forecasting. A past paper [16] proposed a LSTM-based neural network model for aggregating demand side load forecast over shortand medium-term monthly horizons. Probabilistic load forecasting (PLF) proved to be an effective forecasting method [17].…”

Deep Learning Based on Multi-Decomposition for Short-Term Load Forecasting

“…Learning long-range dependencies with RNNs is challenging because of the vanishing gradient problem. The increase in the number of layers and the longer paths to the past cause the vanishing gradient problem because of the back-propagation algorithm, which has the very desirable characteristic of being very flexible, although causes the vanishing gradient problem [30,[32][33][34].…”

“…The input dimension of the proposed method is 11, which is the sum of the reference profile and 10 IMF signals. We selected the hyperparameters and used ADAM optimization, one of the optimization techniques used in deep learning [30][31][32][33][34][35][36][37][38][39][40].…”

“…However, an RNN has vanishing gradient problems caused by an increase in the number of layers. Nonlinear autoregressive exogenous (NARX) RNNs offer an orthogonal mechanism for dealing with the vanishing gradient problem by allowing direct connections or delays from the distant past data [34,35]. However, NARX RNNs have a limited impact on vanishing gradients, and the delay structure increases the computation time.…”

An Ultrashort-Term Net Load Forecasting Model Based on Phase Space Reconstruction and Deep Neural Network

“…Recently, many systematic and fruitful studies on traditional load forecasting have been conducted. The load forecasting methods mainly include the similar day prediction method [2,3], time series prediction method [4,5], expert system [6,7], and regression analysis method [8,9]. Artificial intelligence and machine learning algorithm are types of prediction methods that have rapidly developed in recent years.…”