Milde M. S. Lira

Application of wavelet and neural network models for wind speed and power generation forecasting in a Brazilian experimental wind park

The wind speed and wind generation forecasting are of extreme importance to aid in the planning studies and scheduled operation of hydrothermal and wind systems. This kind of generation is in the incipient phase in Brazil; however, the perspectives are mainly exciting aiming for increasing the potential of electricity generation. The use of wind power for producing electricity can create uncertainties in the generation. Therefore, the development of wind forecasting models is essential to integrate this kind of energy source with the generation system in an effective way. This work proposes the application of Artificial Neural Networks - ANN to produce a tool capable of accomplishing the wind speed forecasting. The ANN model is created using input data preprocessing by the Wavelet Transform - WT to extract important characteristics of the wind speed. Outputs of several ANNs show clearly the potential of the model based on WT compared with the others.

Recurrent neural networks solving a real large scale mid-term scheduling for power plants

This paper deals with an application of artificial neural network (ANN) to solve the operation planning problem of generation systems in the mid-term operation horizon. This problem is related to economic power dispatch that minimizes the overall production cost while satisfies the load demand. These kinds of problem are large scale optimization problems in which the complexity increases with the planning horizon and the accuracy of the system to be modeled. This paper considers the two-phase optimization neural network which solves linear and quadratic programming problems. These networks are based on the solution of a set of differential equations that are obtained from a transformation of an augmented Lagrange energy function. This network also provides the corresponding Lagrange multiplier associated with each constraint which is the marginal price. The results indicate that the developed ANN model provides optimal scheduling of hydro, thermal and wind power plant towards the minimal operation cost.

Investigating the use of Reservoir Computing for forecasting the hourly wind speed in short -term

This paper presents the results of the models created for forecasting the hourly wind speed in 24-step-forward using Reservoir Computing (RC). RC is a new paradigm that offers an intuitive methodology for using the temporal processing power of recurrent neural networks (RNN) without the inconvenience of training them. Originally, introduced independently as Liquid State Machine [5] or Echo State Network [6], whose basic concept is randomly construct a RNN and leave the weights unchanged. In this work we used Echo State Network (ESN) to create the models and Multi-Layer Networks (MLP) to compare the results. The results showed that the ESN performed significantly better than MLP networks, even though it presents a significantly simpler, and faster, training algorithm.

A fuzzy system for detection of incipient fault in power transformers based on gas-in-oil analysis

Dissolved gas analysis (DGA) is one of the most useful techniques do detect the incipient faults of power transformer. However, the identification of the faulted location by the traditional method is not always an easy task due to the variability of gas data and operational natures. This work aims to develop an intelligent system of preventive maintenance for automatically detecting incipient fault in power transformers through analysis of dissolved gases in transformer insulating oil by introducing the IEC 599 standard (International Electrotechnical Commission). The data used to model the system are taken from chromatographic analysis of CELPE (Electrical Company from Pernambuco). The results show a system with high accuracy when compared with other papers approaching the same problem. Moreover, the results also proved the ability of multiple incipient faults detection.

Combining Multiple Artificial Neural Networks Using Random Committee to Decide upon Electrical Disturbance Classification

An ANN-based automatic classifier for power system disturbance waveforms was developed. Actual voltage waveforms were applied in the training process. Signals were processed in two steps: i) decomposition through wavelet transformation up to the 5th decomposition level; ii) the resultant wavelet coefficients are processed via PCA, reducing the input space of the classifier to a much lower dimension. The classification was carried out using a combination of six MLPs with different architectures: five representing the first to fifth-level details, and one representing the fifth-level approximation. The RPROP algorithm was applied for training the networks. Network combination was formed using random committee which builds an ensemble of randomized base classifiers. Experimental results with real data indicate that the random committee is clearly an effective way to improve disturbance classification accuracy when compared with the simple average and the individual models.

Forecasting models of wind power in Northeastern of Brazil

Wind Power forecasting is extremely important to assist in planning and programming studies for the operation of wind power generation. Several studies have shown that the Brazilian wind potential can contribute significantly to the electricity supply, especially in the Northeast Brazil, where winds present an important feature of being complementary in relation to the flows of the San Francisco River. However, using wind power to generate electricity has some drawbacks, such as uncertainties in generation and some difficulty in planning and operation of the power system. This paper presents actual results of wind power forecasting for two parks in the region of northeastern Brazil with four different models. Models that perform power generation forecasting using the forecasted wind speeds and the wind power curve of the park are called Wind to Power (W2P) and models that perform power generation forecasting using the historical power generation of the park are called Power to Power (P2P). The models perform forecasting of wind power generation with 6 hours ahead, discretized by 10 minutes and with 5 days ahead, discretized by 30 minutes. Models that directly predict the wind power (P2P) got the best results. These models were more suitable for use in the power systems operation planning considering the wind parks analyzed in northeastern Brazil.

Wind forecasting and wind power generation: Looking for the best model based on artificial intelligence

Wind forecasting is extremely important to assist in planning and programming studies for the operation of wind power generation. Several studies have shown that the Brazilian wind potential can contribute significantly to the electricity supply, especially in the Northeast, where winds present an important feature of being complementary in relation to the flows of the San Francisco River. However, using wind power to generate electricity has some drawbacks, such as uncertainties in generation and some difficulty in planning and operation of the power system. This work proposes and develops models to forecast hourly average wind speeds and wind power generation based on Artificial Neural Networks, Fuzzy Logic and Wavelets. The models were adjusted for forecasting with variable steps up to twenty-four hours ahead. The gain of some of the developed models in relation to the reference models was of approximately 80% for forecasts in a period of one hour ahead. The results showed that a wavelet analysis combined with artificial intelligence tools provides more reliable forecasts than those obtained with the reference models, especially for forecasts in a period of 1 to 6 hours ahead.

Using genetic algorithm to develop a neural-network-based load forecasting

This work uses artificial neural networks, whose architecture were developed using genetic algorithm to realize the hourly load forecasting based on the monthly total load consumption registered by the Energy Company of Pernambuco (CELPE). The proposed Hybrid Intelligent System - HIS was able to find the trade-off between forecast errors and network complexity. The load forecasting produces the essence to increase and strengthen in the basic grid, moreover study into program and planning of the system operation. The load forecasting quality contributes substantially to indicating more accurate consuming market, and making electrical system planning and operating more efficient. The forecast models developed comprise the period of 45 and 49 days ahead. Comparisons between the four models were achieved by using historical data from 2005.

A Hybrid Intelligent System for Short and Mid-term Forecasting for the CELPE Distribution Utility

This paper presents the development of a hybrid intelligent system, joining an artificial neural network (ANN) based technique and heuristic rules to adjust the short and mid-term electric load forecasting in the 3, 7, 15, 30, and 45 days ahead. The study was based on load demand data of Energy Company of Pernambuco (CELPE), whose data contain the hourly load consumption in the period from January-2000 until December-2004. The proposed system forecasts a holiday as one Saturday or Sunday based on the specialists information that analyzes the load behaviors of each holiday. The hybrid intelligent system presented an improvement in the load forecasts in relation to the results achieved by the ANN alone. The program was implemented in MATLAB 7.0 R14.

Improving Disturbance Classification by Combining Multiple Artificial Neural Networks

An ANN-based automatic classifier for power system disturbance waveforms was developed. Actual voltage waveforms were applied in the training process. Signals are processed in two steps: i) decomposition through wavelet transformation up to the 5th decomposition level; ii) the resultant wavelet coefficients are processed via PCA, reducing the input space of the classifier to a much lower dimension. The classification is carried out using a combination of 3 MLPs with different architectures. The RPROP algorithm is applied for training the networks. Network combination was formed and the final decision of the classifier corresponds to the combination output with the highest value. The results showed to be quite promising for five disturbance types tested so far: sags, swells, harmonics, oscillatory transients and interruptions, as well as in the particular case of no disturbance.