A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network

Songyan Zhang; Xinran Zhang; Chao Lu

doi:10.1109/ICPRE59655.2023.10353747

A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network

Songyan Zhang
, Xinran Zhang
, Chao Lu^*

^*Corresponding author for this work

Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Recently, the ambient signal (AS) based load identification method has been favored by researchers due to its ability to capture the time-varying nature of load characteristics. However, load characteristics are not sufficiently perturbed by small disturbances, leading to the easy distortion of effective signals in AS, and inaccurate identification results that cannot reflect the actual load composition and model parameters. To address this issue, this paper proposes a real-time load composition estimator based on a neural differential-algebraic equations network (NDAE) to guide the parameter optimization process. Moreover, considering the redundancy of AS, a hierarchical strategy based on the verification and synthesis of multiple sets of identification results is designed to improve the reliability of the final conclusion. The effectiveness of the proposed strategy is verified using the WSCC 9-node simulation system.

Original language	English
Title of host publication	2023 8th International Conference on Power and Renewable Energy, ICPRE 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1493-1498
Number of pages	6
ISBN (Electronic)	9798350328813
DOIs	https://doi.org/10.1109/ICPRE59655.2023.10353747
State	Published - 2023
Externally published	Yes
Event	8th International Conference on Power and Renewable Energy, ICPRE 2023 - Shanghai, China Duration: 22 Sep 2023 → 25 Sep 2023

Publication series

Name	2023 8th International Conference on Power and Renewable Energy, ICPRE 2023

Conference

Conference	8th International Conference on Power and Renewable Energy, ICPRE 2023
Country/Territory	China
City	Shanghai
Period	22/09/23 → 25/09/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Composite load model
differential-algebraic equations
neural network
parameter identification

Access to Document

10.1109/ICPRE59655.2023.10353747

Cite this

Zhang, S., Zhang, X., & Lu, C. (2023). A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network. In 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023 (pp. 1493-1498). (2023 8th International Conference on Power and Renewable Energy, ICPRE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPRE59655.2023.10353747

Zhang, Songyan ; Zhang, Xinran ; Lu, Chao. / A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network. 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1493-1498 (2023 8th International Conference on Power and Renewable Energy, ICPRE 2023).

@inproceedings{b5b943f2e6d04246a63a1cdc2a590a78,

title = "A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network",

abstract = "Recently, the ambient signal (AS) based load identification method has been favored by researchers due to its ability to capture the time-varying nature of load characteristics. However, load characteristics are not sufficiently perturbed by small disturbances, leading to the easy distortion of effective signals in AS, and inaccurate identification results that cannot reflect the actual load composition and model parameters. To address this issue, this paper proposes a real-time load composition estimator based on a neural differential-algebraic equations network (NDAE) to guide the parameter optimization process. Moreover, considering the redundancy of AS, a hierarchical strategy based on the verification and synthesis of multiple sets of identification results is designed to improve the reliability of the final conclusion. The effectiveness of the proposed strategy is verified using the WSCC 9-node simulation system.",

keywords = "Composite load model, differential-algebraic equations, neural network, parameter identification",

author = "Songyan Zhang and Xinran Zhang and Chao Lu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 8th International Conference on Power and Renewable Energy, ICPRE 2023 ; Conference date: 22-09-2023 Through 25-09-2023",

year = "2023",

doi = "10.1109/ICPRE59655.2023.10353747",

language = "英语",

series = "2023 8th International Conference on Power and Renewable Energy, ICPRE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1493--1498",

booktitle = "2023 8th International Conference on Power and Renewable Energy, ICPRE 2023",

address = "美国",

}

Zhang, S, Zhang, X & Lu, C 2023, A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network. in 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023. 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1493-1498, 8th International Conference on Power and Renewable Energy, ICPRE 2023, Shanghai, China, 22/09/23. https://doi.org/10.1109/ICPRE59655.2023.10353747

A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network. / Zhang, Songyan; Zhang, Xinran; Lu, Chao.
2023 8th International Conference on Power and Renewable Energy, ICPRE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1493-1498 (2023 8th International Conference on Power and Renewable Energy, ICPRE 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network

AU - Zhang, Songyan

AU - Zhang, Xinran

AU - Lu, Chao

PY - 2023

Y1 - 2023

N2 - Recently, the ambient signal (AS) based load identification method has been favored by researchers due to its ability to capture the time-varying nature of load characteristics. However, load characteristics are not sufficiently perturbed by small disturbances, leading to the easy distortion of effective signals in AS, and inaccurate identification results that cannot reflect the actual load composition and model parameters. To address this issue, this paper proposes a real-time load composition estimator based on a neural differential-algebraic equations network (NDAE) to guide the parameter optimization process. Moreover, considering the redundancy of AS, a hierarchical strategy based on the verification and synthesis of multiple sets of identification results is designed to improve the reliability of the final conclusion. The effectiveness of the proposed strategy is verified using the WSCC 9-node simulation system.

AB - Recently, the ambient signal (AS) based load identification method has been favored by researchers due to its ability to capture the time-varying nature of load characteristics. However, load characteristics are not sufficiently perturbed by small disturbances, leading to the easy distortion of effective signals in AS, and inaccurate identification results that cannot reflect the actual load composition and model parameters. To address this issue, this paper proposes a real-time load composition estimator based on a neural differential-algebraic equations network (NDAE) to guide the parameter optimization process. Moreover, considering the redundancy of AS, a hierarchical strategy based on the verification and synthesis of multiple sets of identification results is designed to improve the reliability of the final conclusion. The effectiveness of the proposed strategy is verified using the WSCC 9-node simulation system.

KW - Composite load model

KW - differential-algebraic equations

KW - neural network

KW - parameter identification

UR - https://www.scopus.com/pages/publications/85182761725

U2 - 10.1109/ICPRE59655.2023.10353747

DO - 10.1109/ICPRE59655.2023.10353747

M3 - 会议稿件

AN - SCOPUS:85182761725

T3 - 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023

SP - 1493

EP - 1498

BT - 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th International Conference on Power and Renewable Energy, ICPRE 2023

Y2 - 22 September 2023 through 25 September 2023

ER -

Zhang S, Zhang X, Lu C. A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network. In 2023 8th International Conference on Power and Renewable Energy, ICPRE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1493-1498. (2023 8th International Conference on Power and Renewable Energy, ICPRE 2023). doi: 10.1109/ICPRE59655.2023.10353747

A Robust Parameter Identification Strategy of Composite Load Model with a Neural Differential Algebraic Network

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this