基于逐步特征增广梯度提升的暂态功角稳定评估及可解释性分析OA北大核心CSTPCD
Transient Angle Stability Assessment and Interpretability Analysis Based on Gradient Boosting Enhanced With Step-wise Feature Augmentation
基于数据驱动的电力系统暂态功角稳定评估虽然可以提供较为准确的结果,但其评估结果缺乏可解释性,导致难以应用于工程实际中.针对该问题,提出一种基于逐步特征增广梯度提升(gradient boosting enhanced with step-wise feature augmentation,AugBoost)的暂态功角稳定评估及可解释性分析方法.首先,通过训练AugBoost评估模型,建立电力系统输入特征与暂态功角稳定指标之间的映射关系;其次,将相量测量单元的实时量测数据传输到训练好的AugBoost评估模型中,提供实时评估结果;并根据沙普利值加性解释(Shapley additive explanations,SHAP)模型对评估结果和输入特征之间的关系进行解释,提高结果的可信度.最后,设计模型更新过程来提升评估模型面对电力系统运行工况变化的鲁棒性.在电力系统仿真软件PSS/E提供的 23节点系统和 1648节点系统上的仿真结果验证了所提方法的有效性.
Although the transient angle stability assessment of power systems based on data-driven can provide more accurate results,it is difficult to apply in engineering practice due to the lack of interpretability of the results.To solve this problem,an analysis method of transient angle stability assessment and in-terpretability based on gradient boosting enhanced with step-wise feature augmentation(AugBoost)was proposed.Firstly,the mapping relationship between the power system input fea-tures and transient angle stability index was established by training the AugBoost assessment model.Secondly,the real-time measurement data of phasor measurement units were transferred to the trained AugBoost assessment model to provide real-time assessment results.And the relationship between assessment results and input features was explained according to Shapley additive explanations(SHAP)interpreta-tion model to improve the credibility of results.Finally,a mod-el update process was designed to improve the robustness of the assessment model to the variation of power system operating conditions.The simulation results on the 23-bus power system and the 1648-bus power system provided by power system sim-ulation software PSS/E verify the effectiveness of the proposed method.
刘旭;刘颂凯;杨超;张磊;段雨舟;晏光辉
三峡大学电气与新能源学院,湖北省宜昌市 443002深圳供电局有限公司罗湖供电局,广东省深圳市 518020国网十堰供电公司,湖北省十堰市 442000
动力与电气工程
暂态功角稳定评估逐步特征增广梯度提升沙普利值加性解释可解释性分析模型更新
transient angle stability assessmentAugBoostShapley additive explanations(SHAP)interpretability analys-ismodel update
《现代电力》 2024 (005)
844-853 / 10
国家自然科学基金项目(52007103,62233006);湖北省自然科学基金项目(2022CFB825);电力系统智能运行与安全防御宜昌市重点实验室(三峡大学)开放基金(2020DLXY06);梯级水电站运行与控制湖北省重点实验室(三峡大学)开放基金(2019KJX11). Project Supported by National Natural Science Foundation of China(52007103,62233006);Natural Science Foundation of Hubei Province(2022CFB825);Open Foundation of Yichang Key Laboratory of Intelligent Operation and Security Defense of Power System(2020DLXY06);Open Foundation of Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station(2019KJX11).
评论