The Application of Improved GM(1,1) in Power Load Forecasting

2010 ◽  
Vol 108-111 ◽  
pp. 151-155
Author(s):  
Cheng Xiang Fan ◽  
Kai Quan Shi ◽  
Ke Jun Li
Keyword(s):  
Load Forecasting ◽  
Original Data ◽  
Data Sequence ◽  
Proposed Model ◽  
Power Load ◽  
Forecasting Method ◽  
Power Load Forecasting ◽  
Novel Method

The forecasting precision of GM(1,1) is very low, when the data sequence is not smooth. The logarithm smoothing is used for the original data sequence. Considering the low precision caused by overlarge and forecasting gray interval for gray modeling, A novel method is proposed for power load forecasting: weighted forecasting method of gray related degree with revised parameter and logarithm smoothing. The method can make various factors weaken or counteracted and prevent the forecasting data from too fast increasing. The proposed model is demonstrated by a test in a certain area. The result shows that the method is effective both in theory and in practice.

A Short-Term Power Load Forecasting Method Based on BP Neural Network

2014 ◽  
Vol 494-495 ◽  
pp. 1647-1650 ◽  
Author(s):  
Ling Juan Li ◽  
Wen Huang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
High Speed ◽  
Load Forecasting ◽  
High Accuracy ◽  
Back Propagation Algorithm ◽  
Short Term ◽  
Power Load ◽  
Forecasting Method ◽  
Power Load Forecasting

Short-term power load forecasting is very important for the electric power market, and the forecasting method should have high accuracy and high speed. A three-layer BP neural network has the ability to approximate any N-dimensional continuous function with arbitrary precision. In this paper, a short-term power load forecasting method based on BP neural network is proposed. This method uses the three-layer neural network with single hidden layer as forecast model. In order to improve the training speed of BP neural network and the forecasting efficiency, this method firstly reduces the factors which affect load forecasting by using rough set theory, then takes the reduced data as input variables of the BP neural network model, and gets the forecast value by using back-propagation algorithm. The forecasting results with real data show that the proposed method has high accuracy and low complexity in short-term power load forecasting.

scholarly journals A Novel Hybrid Method for Short-Term Power Load Forecasting

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Huang Yuansheng ◽  
Huang Shenhai ◽  
Song Jiayin
Keyword(s):  
Empirical Mode Decomposition ◽  
Hybrid Method ◽  
Load Forecasting ◽  
Ensemble Empirical Mode Decomposition ◽  
Support Vector ◽  
Residual Term ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Power Load ◽  
Power Load Forecasting

Influenced by many uncertain and random factors, nonstationary, nonlinearity, and time-variety appear in power load series, which is difficult to forecast accurately. Aiming at locating these issues of power load forecasting, an innovative hybrid method is proposed to forecast power load in this paper. Firstly, ensemble empirical mode decomposition (EEMD) is used to decompose the power load series into a series of independent intrinsic mode functions (IMFs) and a residual term. Secondly, genetic algorithm (GA) is then applied to determine the best weights of each IMF and the residual term named ensemble empirical mode decomposition based on weight (WEEMD). Thirdly, least square support vector machine (LSSVM) and nonparametric generalized autoregressive conditional heteroscedasticity (NPGARCH) are employed to forecast the subseries, respectively, based on the characteristics of power load series. Finally, the forecasted power load of each component is summed as the final forecasted result of power load. Compared with other methods, the forecasting results of this proposed model applied to the electricity market of Pennsylvania-New Jersey-Maryland (PJM) indicate that the proposed model outperforms other models.

Sign in / Sign up

Export Citation Format

Share Document