Day‐ahead price forecasting of electricity markets by a hybrid intelligent system

Abstract

SUMMARYPrice forecasting is so valuable for both producers and consumers in the new competitive electric power markets. In this paper, a new hybrid intelligent system (HIS) is proposed for day-ahead prediction of market clearing price (MCP) in the pool-based markets. MCP has a volatile and time-dependent behavior owning many outliers. Prediction of such a complex signal is a challenging task requiring a qualified forecast tool, which not only fits well to the training data, but also can predict the stochastic behavior of the unseen part of the signal. The proposed hybrid system is composed of a real-coded genetic algorithm (RCGA), cross-validation, repetitive training, and archiving techniques combined in the framework of a neural network (NN). The proposed RCGA with enhanced stochastic search capability is used for training of the NN while the cross-validation, repetitive training and archiving techniques enhances generalization capability of it. The proposed forecast strategy is examined on the different periods of the Spanish electricity market. It is shown that the method can provide more accurate results than the other price forecasting techniques such as ARIMA time series, wavelet-ARIMA, fuzzy neural network (FNN), and generalized auto-regressive conditional heteroskedastic (GARCH) methods.

Enhanced Forecasting Approach for Electricity Market Prices and Wind Power Data Series in the Short-Term

“…The results obtained with the HWDA approach are provided in Figures 5-8 Tables 2 and 3 shows the comparative MAPE criterion and weekly error variance criterion results, respectively, between the HWDA approach and ten previous published methodologies, namely NN [13], FNN [11], AWNN [14], HIS [12], CNEA [15], CNN [16], WPA [19], mutual information with composite NN (MI+CNN) [22], and hybrid evolutionary algorithm (HEA) [44], indicating the enhancements as the percentage evolution between the HWDA approach and the respective comparative methodology under analysis. As mentioned in [10,21], this market has features that are difficult to forecast due to influences from dominant players, which are reflected in historical data.…”

Short-term electricity prices forecasting in a competitive market by a hybrid PSO–ANFIS approach

“…Also, for the sake of a fair comparison, the same test weeks as in [13][14][15][16][17][18][19][20][21][22] Table 2 presents the values for the criterions to evaluate the accuracy of the HPA approach in forecasting electricity prices. The first column indicates the week, the second column presents the MAPE in percent, the third column presents the square root of the SSE, and the fourth column presents the SDE.…”

“…The soft computing techniques include neural networks (NN) [16], neural networks combined with wavelet transform (NNWT) [17], fuzzy neural networks (FNN) [18], weighted nearest neighbors (WNN) [19], adaptive wavelet neural network (AWNN) [20], hybrid intelligent system (HIS) [21], cascaded neuro-evolutionary algorithm (CNEA) [22], and other hybrid approaches [23,24]. Usually, an inputoutput mapping is learned from historical examples, thus there is no need to model the system.…”

“…The proposed approach is based on the combination of particle swarm optimization (PSO) and adaptive-network based fuzzy inference system (ANFIS). Our HPA (hybrid PSO-ANFIS) approach is examined on the electricity market of mainland Spain, commonly used as the test case in several price forecasting papers [13][14][15][16][17][18][19][20][21][22]. It has been concluded that the Spanish market has a hard nonlinear behaviour and time variant functional relationship [14,18].…”

Pronóstico del Precio de la Energía Eléctrica usando Redes Neuro-Difusas

“…Su aplicación a los mercados de California y de España mostró errores medios inferiores al 10%. Ante el comportamiento no lineal de este tipo de variables económicas, se han propuesto nuevos métodos basados en diferentes estructuras de redes neuronales artificiales (Amjady y Keynia, 2009) y métodos híbridos combinando algoritmos genéticos y redes neuronales (Amjady y Hemmati, 2009). Los resultados con redes neuronales fueron evaluados con datos de los mercados eléctricos de España y PJM (Pennsylvania -New Jersey -Maryland) mostrando siempre un mejor desempeño que los métodos ARIMA y GARCH.…”