Informacionnye Tehnologii · 20 Nov 2026
Development of a method for dynamic IR drop analysis based on machine learning
E. D. Demidov, A. A. Vasilev
Citations by database
Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.
- Crossref1
- OpenCitations0
Citations per year
The current year is still counting.
- 2026 so far0
Abstract
This paper presents the development of a machine learning-based method for dynamic IR drop analysis. The proposed approach includes a methodology for training a neural network model using circuit characteristics, as well as a method for generating the input data supplied to the machine learning model. The paper describes the selected neural network architecture, the evaluation metrics used during training, and a customized loss function designed to improve the accuracy of dynamic IR drop prediction. Validation results obtained on an independent test dataset are presented, and the proposed approach is evaluated in terms of prediction accuracy and execution time compared with the conventional dynamic IR drop analysis methodology. The validation results demonstrate that the proposed model achieves a mean absolute error (MAE) of less than 400 mV and a mean relative error below 20 %. Furthermore, the developed approach provides a significant reduction in dynamic IR drop analysis time compared with the conventional method. As the analyzed circuit grows in size, the achieved speedup steadily increases.
What the data shows
- Crossref counts 1 citations, the most of the databases. The others count 0.
Graph
This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.
Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.
Start with
Cited by 0 papers
Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.
References (18)
What it cites, from open citation data, with Crossref's record of each.