Abstract | ||
---|---|---|
This paper introduces the multiple linear regression, stepwise linear regression, neural network method, and improves the neural network. Comprehensive analysis of the current prediction methods, the application principle of a detailed analysis and comparison of the various prediction methods advantages and disadvantages. Put forward to improve short-term load forecasting accuracy is not only attach importance to the accumulation of historical data, more should pay attention to choose the right forecasting model, integrated prediction model is the future development direction of power load forecasting method. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CSCWD.2016.7565983 | 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD) |
Keywords | Field | DocType |
power system,Short-term load forecasting,Data mining | Data mining,Stepwise regression,Load modeling,Computer science,Load forecasting,Probabilistic forecasting,Artificial intelligence,Artificial neural network,Machine learning,Linear regression | Conference |
ISBN | Citations | PageRank |
978-1-5090-1916-8 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hu-Ping Yang | 1 | 0 | 0.34 |
Fei-Fei Yan | 2 | 0 | 0.34 |
Hua Wang | 3 | 0 | 0.68 |
li zhang | 4 | 101 | 18.22 |