Fast and explainable warm-start point learning for AC optimal power flow using decision tree
The quality of starting point greatly influences the result and convergence efficiency of the optimization algorithm, especially for the non-convex and constrained Alternating Current Optimal Power Flow problem. Generally, speed and accuracy are the two main evaluation metrics for generating startin...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170948 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-170948 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1709482023-10-13T15:40:56Z Fast and explainable warm-start point learning for AC optimal power flow using decision tree Cao, Yuji Zhao, Huan Liang, Gaoqi Zhao, Junhua Liao, Huanxin Yang, Chao School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Warm-Start Point Decision Tree The quality of starting point greatly influences the result and convergence efficiency of the optimization algorithm, especially for the non-convex and constrained Alternating Current Optimal Power Flow problem. Generally, speed and accuracy are the two main evaluation metrics for generating starting points. The data-driven methods learn the starting point through historical data and show good performance. However, most methods utilize “black-box” models, which lack interpretability. Therefore, this paper proposes a fast and explainable warm-start point learning method based on the multi-target binary decision tree with a post-pruning module. The calculated warm-start points can accelerate the solving process and the model inference time is extremely short. The post-pruning module is applied to fit different power system scenarios fairly and alleviate the overfitting problem by pruning the completely grown tree. Also, a set of detailed decision rules for selecting warm-start points are generated after the learning process. The generated rules assist the power system operators in identifying important loads and thereby provide the model interpretability. The experiment shows that the proposed framework can reduce the solving times for the Alternating Current Optimal Power Flow solvers with an extremely short calculation time for the explainable warm-start point. Submitted/Accepted version This work was supported by the National Natural Science Foundation of China, Grant/Award Numbers: 72171206, 42105145; Guangdong Province Natural Science Foundation (No. 2023A1515011438); the Shenzhen Key Lab of Crowd Intelligence Empowered Low-Carbon Energy Network (No. ZDSYS20220606100601002) and Shenzhen Institute of Artificial Intelligence and Robotics for Society. 2023-10-09T05:43:01Z 2023-10-09T05:43:01Z 2023 Journal Article Cao, Y., Zhao, H., Liang, G., Zhao, J., Liao, H. & Yang, C. (2023). Fast and explainable warm-start point learning for AC optimal power flow using decision tree. International Journal of Electrical Power and Energy Systems, 153, 109369-. https://dx.doi.org/10.1016/j.ijepes.2023.109369 0142-0615 https://hdl.handle.net/10356/170948 10.1016/j.ijepes.2023.109369 2-s2.0-85165533012 153 109369 en International Journal of Electrical Power and Energy Systems © 2023 Elsevier Ltd. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1016/j.ijepes.2023.109369. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Warm-Start Point Decision Tree |
spellingShingle |
Engineering::Electrical and electronic engineering Warm-Start Point Decision Tree Cao, Yuji Zhao, Huan Liang, Gaoqi Zhao, Junhua Liao, Huanxin Yang, Chao Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
description |
The quality of starting point greatly influences the result and convergence efficiency of the optimization algorithm, especially for the non-convex and constrained Alternating Current Optimal Power Flow problem. Generally, speed and accuracy are the two main evaluation metrics for generating starting points. The data-driven methods learn the starting point through historical data and show good performance. However, most methods utilize “black-box” models, which lack interpretability. Therefore, this paper proposes a fast and explainable warm-start point learning method based on the multi-target binary decision tree with a post-pruning module. The calculated warm-start points can accelerate the solving process and the model inference time is extremely short. The post-pruning module is applied to fit different power system scenarios fairly and alleviate the overfitting problem by pruning the completely grown tree. Also, a set of detailed decision rules for selecting warm-start points are generated after the learning process. The generated rules assist the power system operators in identifying important loads and thereby provide the model interpretability. The experiment shows that the proposed framework can reduce the solving times for the Alternating Current Optimal Power Flow solvers with an extremely short calculation time for the explainable warm-start point. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Cao, Yuji Zhao, Huan Liang, Gaoqi Zhao, Junhua Liao, Huanxin Yang, Chao |
format |
Article |
author |
Cao, Yuji Zhao, Huan Liang, Gaoqi Zhao, Junhua Liao, Huanxin Yang, Chao |
author_sort |
Cao, Yuji |
title |
Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
title_short |
Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
title_full |
Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
title_fullStr |
Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
title_full_unstemmed |
Fast and explainable warm-start point learning for AC optimal power flow using decision tree |
title_sort |
fast and explainable warm-start point learning for ac optimal power flow using decision tree |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/170948 |
_version_ |
1781793805934002176 |