John B. Theocharis

A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation

In this paper, a fuzzy model is suggested for the prediction of wind speed and the produced electrical power at a wind park. The model is trained using a genetic algorithm-based learning scheme. The training set includes wind speed and direction data, measured at neighboring sites up to 30 km away from the wind turbine clusters. Extensive simulation results are shown for two application cases, providing wind speed forecasts from 30 min to 2 h ahead. It is demonstrated that the suggested model achieves an adequate understanding of the problem while it exhibits significant improvement compared to the persistent method.

Long-term wind speed and power forecasting using local recurrent neural network models

This paper deals with the problem of long-term wind speed and power forecasting based on meteorological information. Hourly forecasts up to 72-h ahead are produced for a wind park on the Greek island of Crete. As inputs our models use the numerical forecasts of wind speed and direction provided by atmospheric modeling system SKIRON for four nearby positions up to 30 km away from the wind turbine cluster. Three types of local recurrent neural networks are employed as forecasting models, namely, the infinite impulse response multilayer perceptron (IIR-MLP), the local activation feedback multilayer network (LAF-MLN), and the diagonal recurrent neural network (RNN). These networks contain internal feedback paths, with the neuron connections implemented by means of IIR synaptic filters. Two novel and optimal on-line learning schemes are suggested for the update of the recurrent networks weights based on the recursive prediction error algorithm. The methods assure continuous stability of the network during the learning phase and exhibit improved performance compared to the conventional dynamic back propagation. Extensive experimentation is carried out where the three recurrent networks are additionally compared to two static models, a finite-impulse response NN (FIR-NN) and a conventional static-MLP network. Simulation results demonstrate that the recurrent models, trained by the suggested methods, outperform the static ones while they exhibit significant improvement over the persistent method.

A recurrent fuzzy-neural model for dynamic system identification

This paper presents a fuzzy modeling approach for identification of dynamic systems. In particular, a new fuzzy model, the Dynamic Fuzzy Neural Network (DFNN), consisting of recurrent TSK rules, is developed. The premise and defuzzification parts are static while the consequent parts of the fuzzy rules are recurrent neural networks with internal feedback and time delay synapses. The network is trained by means of a novel learning algorithm, named Dynamic-Fuzzy Neural Constrained Optimization Method (D-FUNCOM), based on the concept of constrained optimization. The proposed algorithm is general since it can be applied to locally as well as fully recurrent networks, regardless of their structures. An adaptation mechanism of the maximum parameter change is presented as well. The proposed dynamic model, equipped with the learning algorithm, is applied to several temporal problems, including modeling of a NARMA process and the noise cancellation problem. Performance comparisons are conducted with a series of static and dynamic systems and some existing recurrent fuzzy models. Simulation results show that DFNN compares favorably with its competing rivals and thus it can be considered for efficient system identification.

Short term load forecasting using fuzzy neural networks

This paper presents the development of a fuzzy system for short term load forecasting. The fuzzy system has the network structure and the training procedure of a neural network and is called a fuzzy neural network (FNN). An FNN initially creates a rule base from existing historical load data. The parameters of the rule base are then tuned through a training process, so that the output of the FNN adequately matches the available historical load data. Once trained, the FNN can be used to forecast future loads. Test results show that the FNN can forecast future loads with an accuracy comparable to that of neural networks, while its training is much faster than that of neural networks. >

A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation

In this paper, a locally feedback dynamic fuzzy neural network (LF-DFNN) for modeling of temporal processes is suggested. The model is composed of dynamic TSK-type fuzzy rules where the consequent sub-models are implemented by recurrent neural networks with internal feedback paths and dynamic neuron synapses. The LF-DFNN exhibits some interesting features, such as enhanced representation power, local modeling characteristics, model parsimony, and stable learning. Training of the LF-DFNN models is achieved using an optimal on-line learning scheme, the decoupled recursive prediction error algorithm (DRPE). The method has reduced computational demands and is derived through decomposition of the weight vector to several mutually exclusive weight groups. The partial derivatives required for the implementation of the training algorithm are calculated using the adjoint model approach, adapted to the fuzzy networks architecture exercised here. The paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. The LF-DFNN networks are used as advanced forecast models, providing multi-step ahead wind speed estimates from 15min to 3h ahead. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that DRPE outperforms three gradient descent algorithms, in training of the recurrent forecast models.

A novel approach to short-term load forecasting using fuzzy neural networks

An efficient modeling technique based on the fuzzy curve notion is developed in this paper to generate fuzzy models for short-term load forecasting. The suggested forecasting approach proceeds on the following steps: (a) prediction of the load curve extremals (peak and valley loads) using separate fuzzy models; (b) formulation of the representative day based on historical load data; and (c) mapping of the representative day load curve to the forecasted peak values to obtain the predicted day load curves. Very good prediction performance is attained as shown in the simulation results which verify the effectiveness of the modeling technique.

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15min to 3h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.

A genetic algorithm solution approach to the hydrothermal coordination problem

In this paper, a genetic algorithm solution to the hydrothermal coordination problem is presented. The generation scheduling of the hydro production system is formulated as a mixed-integer, nonlinear optimization problem and solved with an enhanced genetic algorithm featuring a set of problem-specific genetic operators. The thermal subproblem is solved by means of a priority list method, incorporating the majority of thermal unit constraints. The results of the application of the proposed solution approach to the operation scheduling of the Greek Power System, comprising 13 hydroplants and 28 thermal units, demonstrate the effectiveness of the proposed algorithm.

Fuzzy modeling for short term load forecasting using the orthogonal least squares method

A fuzzy modeling method is developed in this paper for short term load forecasting. According to this method, identification of the premise part and consequent part is separately accomplished via the orthogonal least squares (OLS) technique. Particularly, the OLS is first employed to partition the input space and determine the number of fuzzy rules and the premise parameters. In the sequel, a second orthogonal estimator determines the input terms which should be included in the consequent part of each fuzzy rule and calculate its parameters. Input selection is automatically performed, given an input candidate set of arbitrary size, formulated by an expert. A satisfactory prediction performance is attained as shown in the test results, showing the effectiveness of the suggested method.

Locally recurrent neural networks for long-term wind speed and power prediction

The paper deals with a real-world application, the long-term wind speed and power forecasting in a wind farm using locally recurrent multilayer networks as forecast models. To cope with the complexity of the process and to improve the performance of the models, a class of optimal on-line learning algorithms is employed for training the locally recurrent networks based on the recursive prediction error (RPE) algorithm. A global RPE algorithm is devised and three local learning algorithms are suggested by partitioning the GRPE into a set of sub-problems at the neuron level to reduce computational complexity and storage requirements. Experimental results on the wind prediction problem demonstrate that the proposed algorithms exhibit enhanced performance, in terms of convergence speed and the accuracy of the attained solutions, compared to conventional gradient-based methods. Furthermore, it is shown that the suggested recurrent forecast models outperform the atmospheric and time-series models.