Application of self-organizing combination forecasting method in power load forecast

Author(s):  
Wei Sun ◽  
Xing Zhang
2012 ◽  
Vol 490-495 ◽  
pp. 1362-1366 ◽  
Author(s):  
Ke Zhao ◽  
Lin Gan ◽  
Zhong Wang ◽  
Yan Xiong

For seasonal and long-term power load forecasting problem, this paper presents an optimal combination forecasting method, which can optimize the combination of multiple predictive models. Optimize the combination of the two model predictions with two models as an example, which are the gray GM(1,1) model and linear regression model, and finally compare the predicted values of combination with the real values. The results show that: the combination forecasting method has a high prediction accuracy, and the error is very small.


2014 ◽  
Vol 962-965 ◽  
pp. 1891-1895
Author(s):  
Chang Liu

This paper studies the problem of load forecast in electric companies. We combine the analysis of load cause and gray prediction model together, and enhance the accuracy of prediction, thus improving the economic benefit of electric companies and saving energy resources. Firstly, considering the cause of load, we separate load into three components: basic load component, weather-sensitive load component, and load component because of special events. Then, we take economic development and actual temperature into account to calculate load in each category. And then, we use gray prediction model to make a further prediction. The results show that gray prediction is only accurate in trend. In order to make a more accurate prediction, it should be combined with other forecasting methods. Finally, we combine cause of load with gray prediction model, and establish a combination forecasting model. The combination forecasting model explains the cause of load and the reason for error in gray model. With accurate forecast, it is easy for electric companies to manage their operation perfectly and get the most profit.


2020 ◽  
Vol 22 (3) ◽  
pp. 956-969 ◽  
Author(s):  
Quanbo Ge ◽  
Haoyu Jiang ◽  
Meiguang He ◽  
Yani Zhu ◽  
Jianmin Zhang

2014 ◽  
Vol 494-495 ◽  
pp. 1647-1650 ◽  
Author(s):  
Ling Juan Li ◽  
Wen Huang

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.


Sign in / Sign up

Export Citation Format

Share Document