Load Forecasting Using Hybrid Models

Abstract

Abstract-This paper presents two hybrid neural networks derived from fuzzy neural networks (FNN): wavelet fuzzy neural network (WFNN) using the fuzzified wavelet features as the inputs to FNN and fuzzy neural network (FNCI) employing the Choquet integral as the outputs of FNN. The learning through FNCI is simplified by the use of q-measure and the speed of convergence of the parameters is increased by reinforced learning. The underlying fuzzy models of these hybrid networks are a modified form of fuzzy rules of Takagi-Sugeno model. The number of fuzzy rules is found from a fuzzy curve corresponding to each input-output by counting the total number of peaks and troughs in the curve. The models can forecast hourly load with a lead time of 1 h as they deal with short-term load forecasting. The results of the two hybrid networks using Indian utility data are compared with ANFIS and other conventional methods. The performance of the proposed WFNN is found superior to all the other compared methods.Index Terms-Fuzzy systems, neural networks, short-term load forecasting, wavelet transforms and Choquet integral.

Hybridization of Chaotic Quantum Particle Swarm Optimization with SVR in Electric Demand Forecasting

“…If a stopping threshold (forecasting accuracy) is reached, then`P Cg , P εg , P σg˘a nd its f globalbest i would be determined; otherwise go back to Step 3. In this paper, the mean absolute percentage error (MAPE) as the forecasting accuracy index, shown in Equation (16), is employed for calculating the objective value to determine suitable parameters in Steps 4 and 5 of QPSO algorithm:…”

“…To be based on the same comparison basis, these load data are divided into three subsets, the training data set (from 1981 to 1992, i.e., 12 load data), the validation data set (from 1993 to 1996, that is four load data), and the testing data set (from 1997 to 2000, i.e., four load data). The forecasting accuracy is measured by Equation (16).…”

Pattern similarity-based methods for short-term load forecasting – Part 2: Models

“…The main advantages of the latter hybrid approach are: the ability to respond accurately to unexpected changes in the input variables, the ability to learn from experience, and the ability to synthesize new relationships between the load demand and the input variables. Examples of such STLF models are: [30], where the neuro-fuzzy system is used to adjust the results of load forecasting obtained by RBF network, [31], where two neuro-fuzzy networks are proposed: a wavelet fuzzy neural network using the fuzzified wavelet features as the inputs and fuzzy neural network employing the Choquet integral as the outputs, [32], where an efficient adaptive fuzzy neural network is proposed which can reduce its complexity removing the unneeded hidden units, [33], where an integrated approach which combines a selforganizing fuzzy neural network learning method with a bilevel optimization method, [34] where a neuro-fuzzy system working on the seasonal cycle patterns is proposed, and [35], where fuzzy logic is combined with wavelet transform and neural network.…”

A Simple Regression Model for Electrical Energy Forecasting

“…Many techniques such as auto regressive integrated moving average [3] and regression analysis (RA) [4][5][6][7] have been investigated to solve the problem of LF in the last few decades. Recently, considerable interest appears to be focused on the application of artificial neural networks for LF due to their ability to extract the relationship among input variables and output through learning from the available database [8][9][10][11][12]. ANNs combined with RA [13][14][15][16] as well with fuzzy logic [17,18] for LF have been outlined.…”