Short-time Load Forecasting Research Articles

Short-term load forecasting based on EEMD-Adaboost-BP

ABSTRACT In order to realize short-time load forecasting, an Adaboost-BP method with a weight update mechanism is proposed based on ensemble learning theory. Firstly, the original historical load power is decomposed into a set of sub-series with diverse characteristics via using ensemble empirical mode decomposition. Then, BP neural network is performed as a weak learner to predict the load power of test samples. At the same time, the prediction results are used to update the weight of the weak learner and test sample and then construct a strong learner to obtain the final prediction results. According to the analysis results of the characteristics of each sub-series, the load forecasting model is established. The result of analysing the calculation example shows that the proposed prediction model outperforms all other algorithms in accuracy, which has high engineering application value.

Research on Power Load Forecasting Model Based on Hybrid Algorithm Optimizing BP Neural Network

Short time load forecasting is essential for daily planning and operation of electric power system. It is the important basis for economic dispatching, scheduling and safe operation. Neural network, which has strong nonlinear fitting capability, is widely used in the load forecasting and obtains good prediction effect in nonlinear chaotic time series forecasting. However, the neural network is easy to fall in local optimum, unable to find the global optimal solution. This paper will integrate the traditional optimization algorithm and propose the hybrid intelligent optimization algorithm based on particle swarm optimization algorithm and ant colony optimization algorithm (ACO-PSO) to improve the generalization of the neural network. In the empirical analysis, we select electricity consumption in a certain area for validation. Compared with the traditional BP neutral network and statistical methods, the experimental results demonstrate that the performance of the improved model with more precise results and stronger generalization ability is much better than the traditional methods.

Multi-variable Echo State Network Optimized by Bayesian Regulation for Daily Peak Load Forecasting

In this paper, a multi-variable echo state network trained with Bayesian regulation has been developed for the short-time load forecasting. In this study, we focus on the generalization of a new recurrent network. Therefore, Bayesian regulation and Levenberg-Marquardt algorithm is adopted to modify the output weight. The model is verified by data from a local power company in south China and its performance is rather satisfactory. Besides, traditional methods are also used for the same task as comparison. The simulation results lead to the conclusion that the proposed scheme is feasible and has great robustness and satisfactory capacity of generalization.

Short-term load forecasting method based on neural network hybrid algorithm of adaptive variable coefficients particle swarm optimization and radial basis function

To improve short-term load forecasting accuracy,a neural networks hybrid optimization algorithm of Adaptive Variable Coefficients Particle Swarm Optimization and Radial Basis Function(AVCTPO-RBF)was proposed.The RBF neural network parameters could be optimized.The short-term load forecast model was established based on the AVCTPO-RBF algorithm.Using the method and history load data of Guizhou power system,the short-term load forecasting was carried out.The experimental results show that convergence of the method is faster and forecast accuracy is more accurate than that of the traditional RBF neural network algorithm,the TPO and RBF neural networks algorithm and the neural networks model based on chaos theory.The hybrid algorithm improves the RBF neural network generalization capacity,and overcomes the shortcomings of the traditional TPO algorithm and the RBF neural networks.The short-term load-forecasting accuracy is improved in Guizhou power system,of which the average percentage error is no more than 1.7%.The hybrid algorithm can be effectively used in short time load forecasting of the power system.

Kohonen neural network and wavelet transform based approach to short-term load forecasting

This paper presents Kohonen neural network and wavelet transform (WT) based technique for short-time load forecasting of power systems. Firstly, the historical seasonal load data are classified into four patterns using Kohonen neural network and then Daubechies D2, D4 and D10 WTs are adopted in order to forecast the hourly load. The wavelet coefficients associated with certain frequency and time localisation are adjusted using the conventional multiple regression (MR) method and the components are reconstructed to predict the final loads through the five-scale synthesis technique. The outcome of the study clearly indicates that the proposed composite model of Kohonen neural network and WT approach can be used as an attractive and effective means for short-term load forecasting.

A Novel Short-Term Load Forecasting Technique Using Wavelet Transform Analysis

This paper proposes a novel wavelet transform-based technique for short-time load forecasting of weather-sensitive loads. In this paper, Daubechies D2, D4, and D10 wavelet transforms are adopted to predict short-term loads, and the numerical results reveal that certain wavelet components can effectively be used to identify the load characteristics in electric power systems. The wavelet coefficients associated with certain frequency and time localization are adjusted using the conventional multiple regression method and then reconstructed in order to forecast the final loads through a three-scale synthesis technique. The outcome of the study clearly indicates that the proposed wavelet transform approach can be used as an attractive and effective means for short-term load forecasting.

Very short-term load forecasting using artificial neural networks

In a deregulated, competitive power market, utilities tend to maintain their generation reserve close to the minimum required by an independent system operator. This creates a need for an accurate instantaneous-load forecast for the next several dozen minutes. This paper presents a novel approach to very short-time load forecasting by the application of artificial neural networks to model load dynamics. The proposed algorithm is more robust as compared to the traditional approach when actual loads are forecasted and used as input variables. It provides more reliable forecasts, especially when the weather conditions are different from those represented in the training data. The proposed method has been successfully implemented and used for online load forecasting in a power utility in the United States. To assure robust performance and training times acceptable for online use, the forecasting system was implemented as a set of parsimoniously designed neural networks. Each network was assigned a task of forecasting load for a particular time lead and for a certain period of day with a unique pattern in load dynamics. Some details of this are presented in the paper.

Confidence interval construction for load forecast

Short-time load forecasting is necessary for making optimal decisions regarding the current and future operational states of a power system. The correctness of those decisions depends on the forecast accuracy. The uncertainty in load forecast can be quantified using the concept of a confidence interval. The most commonly used approximation of a confidence interval is known as the standard interval, which is determined from the past forecast errors. This paper presents an alternative method of confidence interval construction for load forecast. It is based on the modeling load as a multivariable probability density function and finding the load forecast as a conditional distribution of load given the information on the explanatory variables, including any uncertainty in their values. The confidence interval is established using the information on the local load variability for the expected conditions, extracted from historical data by means of nonparametric density estimation. This approach allows to construct a confidence interval based on the expected conditions, known with some degree of uncertainty, rather than on the errors observed in the past. It provides a way of translating any uncertainty in the anticipated weather conditions into the confidence interval for the predicted load.

Nonparametric regression based short-term load forecasting

This paper presents a novel approach to short-time load forecasting by the application of nonparametric regression. The method is derived from a load model in the form of a probability density function of load and load affecting factors. A load forecast is a conditional expectation of load given the time, weather conditions and other explanatory variables. This forecast can be calculated directly from historical data as a local average of observed past loads with the size of the local neighborhood and the specific weights on the loads defined by a multivariate product kernel. The method accuracy relies on the adequate representation of possible future conditions by historical data, but a measure to detect any unreliable forecast can be easily constructed. The proposed procedure requires few parameters that can be easily calculated from historical data by applying the cross-validation technique.