A Novel Hybrid BND-FOA-LSSVM Model for Electricity Price Forecasting

Abstract

Accurate electricity price forecasting plays an important role in the profits of electricity market participants and the healthy development of electricity market. However, the electricity price time series hold the characteristics of volatility and randomness, which make it quite hard to forecast electricity price accurately. In this paper, a novel hybrid model for electricity price forecasting was proposed combining Beveridge-Nelson decomposition (BND) method, fruit fly optimization algorithm (FOA), and least square support vector machine (LSSVM) model, namely BND-FOA-LSSVM model. Firstly, the original electricity price time series were decomposed into deterministic term, periodic term, and stochastic term by using BND model. Then, these three decomposed terms were forecasted by employing LSSVM model, respectively. Meanwhile, to improve the forecasting performance, a new swarm intelligence optimization algorithm FOA was used to automatically determine the optimal parameters of LSSVM model for deterministic term forecasting, periodic term forecasting, and stochastic term forecasting. Finally, the forecasting result of electricity price can be obtained by multiplying the forecasting values of these three terms. The results show the mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) of the proposed BND-FOA-LSSVM model are respectively 3.48%, 11.18 Yuan/MWh and 9.95 Yuan/MWh, which are much smaller than that of LSSVM, BND-LSSVM, FOA-LSSVM, auto-regressive integrated moving average (ARIMA), and empirical mode decomposition (EMD)-FOA-LSSVM models. The proposed BND-FOA-LSSVM model is effective and practical for electricity price forecasting, which can improve the electricity price forecasting accuracy.

Electricity Price Forecasting Using Recurrent Neural Networks

“…Chaabanae [81] developed the Zhang [80] method and combined auto-regressive fractionally integrated moving average (ARFIMA) with neural networks model. Guo and Zhao [82] also utilized decomposition, optimization and support vector machine techniques in a hybrid work. In another example, Shrivastava and Panigrahi [83] applied a hybrid wavelet extreme learning machine.…”

An Enhanced Hybrid Deep Learning Model to Enhance Network Intrusion Detection Capabilities for Cybersecurity

“…CNN's ability to automatically identify crucial elements, even without human intervention, is one of its main selling points. The use of CNN to identify DDoS attacks has been documented in papers such as [18] and [19]. The sparsity of connections describes how CNN's output values depend on a relatively small input value.…”

“…In particular, it can detect the smell of the food source from great distances. As a result, the FOA has lately been used to fine-tune the settings of a wide range of real-time programs [18] [19]. As part of this effort, we use Fruit fly to fine-tune the neurons in CNN-hidden LSTM layers.…”