Selecting decision trees for power system security assessment
Selecting decision trees for power system security assessment
复制标题
DOI：
10.1016/j.egyai.2021.100110
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Al-Amin B. Bugaje;J. Cremer;Mingyang Sun;G. Strbac
中科院分区：
文献类型：
--
作者：
Al-Amin B. Bugaje;J. Cremer;Mingyang Sun;G. Strbac
电力系统输送的电力越来越多，未来将涉及更多的分布式可再生能源和设备的动态交互。系统对干扰的响应必须是安全和可预测的，以避免停电。可以在时域中模拟系统响应。然而，这种动态安全评估（DSA）在实时计算上是不可处理的。特别有希望的是从机器学习中训练决策树（DT）作为可解释的分类器，以预测系统对干扰的响应是否安全。在大多数研究中，选择最佳DT模型的重点是预测准确性。然而，仅仅关注预测准确性是不够的。漏报警和假报警的成本有很大的不同，由于安全评估是一项关键任务，因此可解释性对操作员至关重要。在这项工作中，多个目标的可解释性，不同的成本，和精度被认为是DT模型的选择。我们提出了一个严格的工作流程来选择最佳分类器。此外，我们提出了两个图形化的视觉检查的方法来说明选择的概率和干扰的影响的敏感性。我们首次提出了成本曲线来检验结合所有三个目标的选择。IEEE 68总线系统和法国系统的案例研究表明，所提出的方法允许更好的DT选择，增加了80%的可解释性，预期的运营成本降低5%，同时几乎为零的精度妥协。所提出的方法可以很好地扩展到更大的系统，并可用于超越DT的模型。因此，这项工作为人工智能（AI）方法的有前途的应用中的模型选择标准提供了见解。
Power systems transport an increasing amount of electricity, and in the future, involve more distributed renewables and dynamic interactions of the equipment. The system response to disturbances must be secure and predictable to avoid power blackouts. The system response can be simulated in the time domain. However, this dynamic security assessment (DSA) is not computationally tractable in real-time. Particularly promising is to train decision trees (DTs) from machine learning as interpretable classifiers to predict whether the system-wide responses to disturbances are secure. In most research, selecting the best DT model focuses on predictive accuracy. However, it is insufficient to focus solely on predictive accuracy. Missed alarms and false alarms have drastically different costs, and as security assessment is a critical task, interpretability is crucial for operators. In this work, the multiple objectives of interpretability, varying costs, and accuracies are considered for DT model selection. We propose a rigorous workflow to select the best classifier. In addition, we present two graphical approaches for visual inspection to illustrate the selection sensitivity to probability and impacts of disturbances. We propose cost curves to inspect selection combining all three objectives for the first time. Case studies on the IEEE 68 bus system and the French system show that the proposed approach allows for better DT-selections, with an 80% increase in interpretability, 5% reduction in expected operating cost, while making almost zero accuracy compromises. The proposed approach scales well with larger systems and can be used for models beyond DTs. Hence, this work provides insights into criteria for model selection in a promising application for methods from artificial intelligence (AI).