Interpretation of Stability Assessment Machine Learning Models Based on Shapley Value
Machine learning is a promising method to solve the stability assessment problems of modern complex power systems. The interpretability of machine learning models is fundamental for trusting the prediction and deploying the models on engineering application. In this paper, a model-agnostic interpret...
Saved in:
Published in | 2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2) pp. 243 - 247 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.11.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Machine learning is a promising method to solve the stability assessment problems of modern complex power systems. The interpretability of machine learning models is fundamental for trusting the prediction and deploying the models on engineering application. In this paper, a model-agnostic interpretation method for machine learning power system stability assessment models is proposed based on Shapley value. Shapley values represent the contribution of each state variable to the stability evaluation result. By constructing kernel function and simplifying the form of training data, Shapley values are efficiently calculated based on the weighted linear regression. The resulting additive feature contribution model can be used to explain the internal logic of the prediction and verify the credibility of the model. The experiment results on voltage margin estimation model in the New England 39-bus system demonstrate the correctness and comprehensibility of the interpretations generated by the proposed method. |
---|---|
AbstractList | Machine learning is a promising method to solve the stability assessment problems of modern complex power systems. The interpretability of machine learning models is fundamental for trusting the prediction and deploying the models on engineering application. In this paper, a model-agnostic interpretation method for machine learning power system stability assessment models is proposed based on Shapley value. Shapley values represent the contribution of each state variable to the stability evaluation result. By constructing kernel function and simplifying the form of training data, Shapley values are efficiently calculated based on the weighted linear regression. The resulting additive feature contribution model can be used to explain the internal logic of the prediction and verify the credibility of the model. The experiment results on voltage margin estimation model in the New England 39-bus system demonstrate the correctness and comprehensibility of the interpretations generated by the proposed method. |
Author | Han, Tiansen Wang, Cong Wang, Li Cai, Yanchun Chen, Jinfu |
Author_xml | – sequence: 1 givenname: Tiansen surname: Han fullname: Han, Tiansen organization: Huazhong University of Science & Technology,State Key Laboratory of Advanced Electromagnetic Engineering and Technology,Wuhan,China – sequence: 2 givenname: Jinfu surname: Chen fullname: Chen, Jinfu organization: Huazhong University of Science & Technology,State Key Laboratory of Advanced Electromagnetic Engineering and Technology,Wuhan,China – sequence: 3 givenname: Li surname: Wang fullname: Wang, Li organization: Guangzhou Power Supply Bureau,Guangzhou,China – sequence: 4 givenname: Yanchun surname: Cai fullname: Cai, Yanchun organization: Guangzhou Power Supply Bureau,Guangzhou,China – sequence: 5 givenname: Cong surname: Wang fullname: Wang, Cong organization: Guangzhou Power Supply Bureau,Guangzhou,China |
BookMark | eNotj71OwzAYAI0EA5Q-AULyC6T4ix3_jKUqNFIqhlLWyna-UEupE8VmyNuDRKeb7qR7ILdxiEjIM7AVADMv27oUihu2KhmYlWESjBY3ZGmUBlVq4MBVdU-Odcw4jRNmm8MQ6dDRQ7Yu9CHPdJ0SpnTBmOne-nOISBu0Uwzxm-6HFvtEX23Clv6Jh7Mde5zpl-1_8JHcdbZPuLxyQY5v28_Nrmg-3uvNuikCgM4F9513vNVMVUooZq3gFXJZKVc6j5WWUmoJ3AsrvVRgvFAO2hKZ6bQTXPEFefrvBkQ8jVO42Gk-XWf5L81YTnE |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/EI247390.2019.9061984 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore Digital Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 9781728131375 1728131375 |
EndPage | 247 |
ExternalDocumentID | 9061984 |
Genre | orig-research |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-i118t-3cfcb3d80757470aa435e3657b2bce586668613c4a6c6719c47b1d2e09f8b4373 |
IEDL.DBID | RIE |
IngestDate | Wed Jun 26 19:27:16 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i118t-3cfcb3d80757470aa435e3657b2bce586668613c4a6c6719c47b1d2e09f8b4373 |
PageCount | 5 |
ParticipantIDs | ieee_primary_9061984 |
PublicationCentury | 2000 |
PublicationDate | 2019-Nov. |
PublicationDateYYYYMMDD | 2019-11-01 |
PublicationDate_xml | – month: 11 year: 2019 text: 2019-Nov. |
PublicationDecade | 2010 |
PublicationTitle | 2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2) |
PublicationTitleAbbrev | EI2 |
PublicationYear | 2019 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.786911 |
Snippet | Machine learning is a promising method to solve the stability assessment problems of modern complex power systems. The interpretability of machine learning... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 243 |
SubjectTerms | Data models Estimation interpretation Machine learning Power system stability Predictive models Shapley value Stability analysis stability assessment Training data |
Title | Interpretation of Stability Assessment Machine Learning Models Based on Shapley Value |
URI | https://ieeexplore.ieee.org/document/9061984 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwGA3bTp5UNvE3OXg0XdukTXJU2ZjCRNDJbiM_vqg4tqHtQf96k7ZOJh68hZCSki_05Uvfex9CZxyslYwakoF2hCUuJTLXmnAAliaOhup7gW1xm48m7GaaTVvofK2FAYCKfAZRaFb_8u3SlOGqrC89-EjB2qgt4rTWajWinCSW_cF1yrhP4QNfS0bN2I2iKRVmDLfR-Hu2miryGpWFjsznLyPG_77ODur9qPPw3Rp3dlELFl002WQP4qXD_hxZMV8_8MXafhOPK_Ik4MZX9QmHYmjzd3zp0cxi_-D9s1r5DwV-VPMSemgyHDxcjUhTMoG8-EyhINQ4o6kNDsM-T4iV8qchoHnGdaoNZMInK8IDuGEqNzlPpGFcJzaFWDqhg8vRHuoslgvYR9hvMapja53TwDJuhGAuVsyaPFyTKHqAumFJZqvaFWPWrMbh391HaCuEpVbxHaNO8VbCiYfzQp9WcfwCaxeiYw |
link.rule.ids | 310,311,786,790,795,796,802,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT8IwGP2CeNCTGjD-tgePbuxHt65HNRBQICaC4UbW9qsaCRDdDvrX224Tg_HgbV3WtGmbvn7de-8DuGCoFKehdCIU2qG-DhweC-EwRBr4OrTZ9yzbYhh3x_R2Ek1qcLnSwiBiQT5D1z4W__LVQub2qqzFDfjwhG7ApsF5j5dqrUqWY8qtdi-gzATxlrHF3errtbQpBWp0dmDw3V5JFnl180y48vOXFeN_O7QLzR99HrlfIc8e1HDegPE6f5AsNDEnyYL7-kGuVgacZFDQJ5FUzqpPxKZDm72Ta4NnipiKD8_p0mwV5DGd5diEcac9uuk6VdIE58XECpkTSi1FqKzHsIkUvDQ15yEM44iJQEiMEhOuJAbCJU1jGTOfS8qErwL0uE6E9Tnah_p8MccDIGaRhcJTSmuBNGIySaj2UqpkbC9K0vAQGnZIpsvSF2NajcbR36_PYas7GvSn_d7w7hi27RSVmr4TqGdvOZ4acM_EWTGnXytjpbk |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+IEEE+3rd+Conference+on+Energy+Internet+and+Energy+System+Integration+%28EI2%29&rft.atitle=Interpretation+of+Stability+Assessment+Machine+Learning+Models+Based+on+Shapley+Value&rft.au=Han%2C+Tiansen&rft.au=Chen%2C+Jinfu&rft.au=Wang%2C+Li&rft.au=Cai%2C+Yanchun&rft.date=2019-11-01&rft.pub=IEEE&rft.spage=243&rft.epage=247&rft_id=info:doi/10.1109%2FEI247390.2019.9061984&rft.externalDocID=9061984 |