Phase-space based short-term load forecasting for deregulated electric power industry

Abstract

This paper describes the application of a phase-space embedding concept to artificial neural network ( A m ) based short-term electric load forecasting. Embedding parmeters for electric load time-series were determined using the method of Integral Local Deformation. In the reconstructed phase-space modular A " predictor was trained to predict loads up to jive days ahead in one-hour steps. It was found that addition of temperature and cycle variables to the phase-space based input variable set improved forecasting accuracy. The overall number of input variables was much smaller than in the similar cases reported in the literature. In this manner the sue of historical data set needed for training was SignificantIy reduced. Forecasting errors were comparable to or better than the ones reported for the similar cases. Such characteristics make the approach attractive for shortterm load forecasting in the deregulated electric power industy.

Artificial Neural Network for Short-Term Load Forecasting in Distribution Systems

“…It has been demonstrated that this transformation improves the performance of the ANN (Drezga et al [21]). In the case of the day of the week and the month, each variable entered in the form of sines and cosines improves prediction (Hernández et al [15], Ramezani et al [22], Razavi and Tolson [23]).…”

Optimization models based on GM (1,1) and seasonal fluctuation for electricity demand forecasting

“…Researchers believe that electricity demand seems chaotic, many complicated facts such as temperature, price of electricity and many other factors [3][4][5][6][7][8][9] can influence electricity demand. With the power systems growth and the increase in their complexity, many factors have become influential in electric power generation and consumption.…”

Short-Term Load Forecasting for Microgrids Based on Artificial Neural Networks

“… Therefore, load forecasting is performed on the basis of previous-day hourly load curve, aggregated daily load forecast, and calendar variables (day of the week, month, etc.)  Periodic variables are supplied to the network in the form of values of sines and cosines, as it has been demonstrated that this transformation significantly improves the performance of the ANN, as shown Drezga et al [64]. Day of the week and month, which are essential for the ANN to detect weekly, monthly and seasonal patterns, are entered as sine and cosine, because the cyclical variables are best understood by ANN, as shown in [65,66].…”