#6443. Saturated load forecasting based on clustering and logistic iterative regression

November 2026publication date
Proposal available till 25-05-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Electrical and Electronic Engineering;
Energy Engineering and Power Technology;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №6443.1 Contract №6443.2 Contract №6443.3 Contract №6443.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Saturated load forecasting is the basis of power grid planning, its accuracy directly affects the utility of consumers. However, saturated load forecasting suffered from insufficient training data. To face this challenge, this paper proposed an improved load forecasting method by combining clustering with logistic iterative regression. Before regression, historical load is clustered based on Fuzzy C-means. According to unsaturated historical data under different clusters, three unknown parameters in logistic regression model are formulated: Neyman-Fisher factorization is used to obtain unbiased sufficient statistics of one parameter. Least square is employed to solve the other two parameters. Afterward, predictive model is acquired by selecting model with least error rate. Subsequently, the optimal cluster number is determined by average absolute percentage error. Finally, the optimal load forecasting model is determined based on the optimal cluster number. Simulation shows that this method improves the accuracy of load forecasting compared with other methods.
Keywords:
Clustering; Load forecasting; Logistic; Parameter estimation

Contacts :
0