Unbiased Direct DGM(1,1) Model of Non-Homogeneous Exponential Sequence and its Application in Electric Load Forecasting

2013 ◽  
Vol 732-733 ◽  
pp. 972-975 ◽  
Author(s):  
De Qiang Zhou
Keyword(s):  
Load Forecasting ◽  
Grey Model ◽  
Electric Load ◽  
Traditional Methods ◽  
Recursive Solution ◽  
Forecasting Method ◽  
Application Scope ◽  
Exponential Sequence ◽  
Electric Load Forecasting

The traditional GM (1,1) has been used widely in the load forecasting, however, there are many defects in the GM (1,1). In order to overcome these defects and expand the application scope of the grey model in load forecasting, a new load forecasting method based on DDGM(1,1) is presented. First, the recursive solution of DDGM(1,1) is given. Then, based on the solution, the unbiased property for non-homogeneous exponential incremental sequence of this model is proved. It is applied to some load forecasting and is compared with the traditional GM (1,1) model.The results show that the presented forecasting method is superior obviously to traditional methods, and it can be used for the approximate non-homogeneous exponential incremental load forecasting generally.

UGM (1,1) Model and its Application to Electric Load Forecasting

2012 ◽  
Vol 461 ◽  
pp. 493-496
Author(s):  
Pei Rong Ji ◽  
Qiang Huang ◽  
Wei Zou
Keyword(s):  
Load Forecasting ◽  
Exponential Model ◽  
Electric Load ◽  
Proposed Model ◽  
Application Scope ◽  
Better Than ◽  
Electric Load Forecasting

GM (1, 1) model is a widely used model for forecasting. The characteristics of the model have been analyzed. The fact that the model is a biased exponential model has been testified. Based on the results, UGM (1, 1) model is presented in this paper. The proposed model has more extensive application scope than GM (1, 1) model for the reason that the model can limit the inherent deviation of GM (1,1) model. The proposed model is applied to the field of electric load forecasting, the actual results also show that the model is better than GM (1, 1) model.

Research of Combined Optimum Grey Model to Mid and Long Term Electric Load Forecasting

2014 ◽  
Vol 986-987 ◽  
pp. 1379-1382
Author(s):  
Xiang Shuo He ◽  
Li Yang ◽  
Xiao Na Yu
Keyword(s):  
Load Forecasting ◽  
Practical Method ◽  
Grey Model ◽  
Model Parameters ◽  
Electric Load ◽  
Power Load ◽  
Partial Error ◽  
Random Disturbances ◽  
Electric Load Forecasting

It is well known that mid and long term electric load forecasting has many uncertain factors that influence the forecasting precision greatly, so every forecasting method has its limitation. Considering limitations of basic grey model and conventional improved models, a new practical method called combined optimum grey model for mid and long term load forecasting is introduced. The combined model is composed of partial error optimum grey model (GM) as well as equa-l dimension and new-information grey model. The forecasting algorithm can estimate model parameters, meet the requirements of dynamic power load and overcome random disturbances. Example analysis shows that the forecasting error is below 3 percent. Compared with conventional theoretical methods, the proposed scheme has the characters of simple computation, high forecasting precision and good applicability.

scholarly journals A Novel Short-Term Residential Electric Load Forecasting Method Based on Adaptive Load Aggregation and Deep Learning Algorithms

Energies ◽  
2021 ◽  
Vol 14 (22) ◽  
pp. 7820
Author(s):  
Tingting Hou ◽  
Rengcun Fang ◽  
Jinrui Tang ◽  
Ganheng Ge ◽  
Dongjun Yang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Load Forecasting ◽  
System Level ◽  
Electric Load ◽  
Short Term ◽  
Power Load ◽  
Forecasting Method ◽  
Home Energy Management ◽  
Aggregated Load ◽  
Electric Load Forecasting

Short-term residential load forecasting is the precondition of the day-ahead and intra-day scheduling strategy of the household microgrid. Existing short-term electric load forecasting methods are mainly used to obtain regional power load for system-level power dispatch. Due to the high volatility, strong randomness, and weak regularity of the residential load of a single household, the mean absolute percentage error (MAPE) of the traditional methods forecasting results would be too big to be used for home energy management. With the increase in the total number of households, the aggregated load becomes more and more stable, and the cyclical pattern of the aggregated load becomes more and more distinct. In the meantime, the maximum daily load does not increase linearly with the increase in households in a small area. Therefore, in our proposed short-term residential load forecasting method, an optimal number of households would be selected adaptively, and the total aggregated residential load of the selected households is used for load prediction. In addition, ordering points to identify the clustering structure (OPTICS) algorithm are also selected to cluster households with similar power consumption patterns adaptively. It can be used to enhance the periodic regularity of the aggregated load in alternative. The aggregated residential load and encoded external factors are then used to predict the load in the next half an hour. The long short-term memory (LSTM) deep learning algorithm is used in the prediction because of its inherited ability to maintain historical data regularity in the forecasting process. The experimental data have verified the effectiveness and accuracy of our proposed method.

Sign in / Sign up

Export Citation Format

Share Document