A segmented forecasting method for net power load based on ramp recognition

Read full text Summarise with VIRAT
Authors: Gang Wang, Zhifei Cai, Junfeng Qu, Di Ge, Xiao Fan Yang, Hui Li
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Abstract Accurate forecasting of net power load on the public grid for integrated source-grid-load-storage projects is crucial for ensuring the safe and stable operation of power systems. Sudden fluctuations in net load (ramping events) pose significant challenges to grid dispatch. This paper addresses the identification and prediction of net load ramping events by first proposing a definition method based on ramping segments. It identifies ramping events by analyzing the magnitude of power changes between adjacent sampling moments. Then, a CNN-BiLSTM hybrid network is constructed for point prediction and is combined with an adaptive bandwidth kernel density estimation (KDEAB) method to establish an interval prediction model. Finally, the effectiveness of the proposed method is validated through case studies. Experimental results demonstrate that the proposed method can effectively identify net load ramping events. Its interval predictions achieve coverage and confidence levels close to the target, exhibiting good overall prediction performance.

Fields of Study & Subjects

Energy Load and Power Forecasting Smart Grid Energy Management Electric Power System Optimization

Publication details

Journal / source
Journal of Physics Conference Series
Volume
3192
Issue
1
Pages
012012–012012
Publication date
1 March 2026
Language
EN