Search

Discusses a study which presented an adaptive distance protection scheme using artificial neural networks. Highlights of the study. INSET: Closure to Discussion of 'Stand Alone Intelligent Digital....

Comments on an article appearing in the October 1999 issue of 'IEEE Transactions on Power Delivery,' which dealt with two methods for fault type detection. Simulation for performance verification of a proposed method; Success of pre-processing in simplifying the task of neural networks.

Abstract: In daily power markets, forecasting electricity prices and loads are the most essential task and the basis for any decision making. An approach to predict the market behaviors is to use the historical prices, loads and other required information to forecast the future prices and loads. This paper introduces an approach for several hour ahead (1–6h) electricity price and load forecasting using an artificial intelligence method, such as a neural network model, which uses publicly available data from the NEMMCO web site to forecast electricity prices and loads for the Victorian electricity market. An approach of selection of similar days is proposed according to which the load and price curves are forecasted by using the information of the days being similar to that of the forecast day. A Euclidean norm with weighted factors is used for the selection of the similar days. Two different ANN models, one for one to six hour ahead load forecasting and another for one to six hour ahead price forecasting have been proposed. The MAPE (mean absolute percentage error) results show a clear increasing trend with the increase in hour ahead load and price forecasting. The sample average of MAPEs for one hour ahead price forecasts is 9.75%. This figure increases to only 20.03% for six hour ahead predictions. Similarly, the one to six hour ahead load forecast errors (MAPE) range from 0.56% to 1.30% only. MAPE results show that several hour ahead electricity prices and loads in the deregulated Victorian market can be forecasted with reasonable accuracy. [Copyright &y& Elsevier]

Price forecasting in competitive electricity markets is critical for consumers and producers in planning their operations and managing their price risk, and it also plays a key role in the economic optimization of the electric energy industry. This paper explores a technique of artificial neural network (ANN) model based on similar days (SD) method in order to forecast day-ahead electricity price in the PJM market. To demonstrate the superiority of the proposed model, publicly available data acquired from the PJM Interconnection were used for training and testing the ANN. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors, are discussed. Comparison of forecasting performance of the proposed ANN model with that of forecasts obtained from similar days method is presented. Daily and weekly mean absolute percentage error (MAPE) of reasonably small value and forecast mean square error (FMSE) of less than 7$/MWh were obtained for the PJM data, which has correlation coefficient of determination (R²) of 0.6744 between load and electricity price. Simulation results show that the proposed ANN model based on similar days method is capable of forecasting locational marginal price (LMP) in the PJM market efficiently and accurately. [ABSTRACT FROM AUTHOR]

This paper presents an approach for short-term electricity price and load forecasting using the artificial neural network (ANN) computing technique. The described approach uses the three-layered ANN paradigm with back-propagation. The publicly available data, acquired from the deregulated Victorian power system, was used for training and testing the ANN. The ANN approach based on similarity technique has been proposed according to which the load and price curves are forecasted by using the information of the days being similar to that of the forecast day. A Euclidean norm with weighted factors is used for the selection of similar days. Two different ANN models, one for load forecasting and another for price forecasting, have been proposed. Test results show that average price and load MAPEs for the year 2003 by using the ANN approach are obtained as 14.29% and 0.95%, respectively. MAPE values obtained from the price and load forecasting results confirm considerable value of the ANN based approach in forecasting short-term electricity prices and loads. [ABSTRACT FROM AUTHOR]

The ultrasonic motor has nonlinear characteristics, which vary with driving conditions and possess variable dead-zone in the control input that is associated with the applied load torque. The dead-zone has a problem in accurate positioning actuator. To improve the control performance of the ultrasonic motor, the dead-zone nonlinearity should be eliminated. This article proposes a new position control scheme for the ultrasonic motors that eliminates the problem due to dead-zone by employing fuzzy neural network (FNN). To achieve the accurate position control when drive conditions vary, FNN can adjust the membership function for the antecedent part. The training of FNN is achieved using online backpropagation algorithm. The dead-zone is compensated by FNN, and PI controller performs the accurate positioning of the drive system. The validity of the proposed method is confirmed by experimental results. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a practical method for short-term load forecast problem using artificial neural network (ANN) combined similar days approach. Neural networks applied in traditional prediction methods all use similar days data to learn the trend of similarity. However, learning all similar days data is a complex task, and does not suit the training of neural network. A Euclidean norm with weighted factors is used to evaluate the similarity between the forecast day and searched previous days. According to similar days approach, load curve is forecasted by using information of the days that are similar to weather condition of the forecast day. An accuracy of the proposed method is enhanced by the addition of temperature as a major climate factor, and special attention was paid to model accurately in different seasons, i.e. Summer, Winter, Spring, and Autumn. The one-to-six hour-ahead forecast errors (MAPE) range from 0.98 to 2.43%. Maximum and minimum percentage errors, and MAPE values obtained from the load forecasting results confirm that ANN-based proposed method provides reliable forecasts for several-hour-ahead load forecasting. [Copyright &y& Elsevier]

This paper presents an approach for short-term load forecast problem, based on hybrid correction method. Conventional artificial neural network based short-term load forecasting techniques have limitations especially when weather changes are seasonal. Hence, we propose a load correction method by using fuzzy logic approach in which a fuzzy logic, based on similar days, corrects the neural network output to obtain the next day forecasted load. An Euclidean norm with weighted factors is used for the selection of similar days. The load correction method for the generation of new similar days is also proposed. The neural network has an advantage of dealing with the nonlinear parts of the forecasted load curves, whereas, the fuzzy rules are constructed based on the expert knowledge. Therefore, by combining these two methods, the test results show that the proposed forecasting method could provide a considerable improvement of the forecasting accuracy especially as it shows how to reduce neural network forecast error over the test period by 23 % through the application of a fuzzy logic correction. The suitability of the proposed approach is illustrated through an application to actual load data of the Okinawa Electric Power Company in Japan. [ABSTRACT FROM AUTHOR]

In this article, an approach based on neural network combined with a fuzzy system is proposed for three-hours-ahead load forecasting. In this proposed prediction method, the forecasted load is obtained by adding a correction that is obtained from the neural network and a fuzzy logic to the selected similar days data. The neural network has the advantage of dealing with the nonlinear part of forecasted load curves and the fuzzy rules are constructed based on the expert knowledge. Therefore, by combining these methods, the proposed method is useful in situations where accurate forecasting models are difficult to obtain. The suitability of the proposed approach is illustrated through an application to actual load data of the Okinawa Electric Power Company in Japan. [ABSTRACT FROM AUTHOR]

Proposes a one-hour-ahead load forecasting method using neural network. Significance of load forecasting to electric power system planning and operation; Evaluation of the similarity between a forecast day and a searched previous day; Structure of neural network; Learning and forecasting procedures for the proposed neural network.