CAREER: Open-Loop Discrete-Event Control in Electric Power Systems

9983653Rovnyak本研究的目标是开发和验证用于电力系统广域开环离散事件控制的模式识别方法，如决策树(DTD)和神经网络(NNS)。拟议的控制措施将为独立服务运营商(ISO)和目前的公用事业公司提供必要的工具，以在不牺牲可靠性的情况下实现放松管制的成本降低目标。这项拟议的研究将调查训练数据的意外情况的选择，将模拟数据转换为组成训练集的输入-输出对的算法，以及用于评估分类器操作的性能度量。PI和研究生将与康奈尔大学和邦内维尔电力管理局的研究人员合作，并将与文献中报告的其他失步继电器、发电机跳闸、有源负载调制、高压直流快速功率变化和重新启动电源切换方案进行对比测试。EE588，电力系统高级主题的学生，将根据研究数据培训和测试NN。EE479自动控制系统实验室的本科生将为本提案中分析的简单电力系统模型设计反馈控制。PI将通过频繁和广泛的练习让所有学生积极学习，引导学生完成解决问题的发现过程，而不仅仅是奖励技术的记忆。PI将在截止日期分发所有家庭作业问题的详细、带注释的解决方案。国际学生联合会发现，这些教学方法在包括妇女、少数族裔和残疾人在内的广泛学生中取得了成功。

9983653RovnyakThe goal of this research is to develop and validate patternrecognition methods such as Decision Trees (DTs) and Neural Networks (NNs)for electric power system wide-area open-loop discrete-event control. Theproposed controls will provide Independent Service Operators (ISOs) andpresent-day utilities with tools necessary to achieve the cost reductiongoals of deregulation without sacrificing reliability. The proposedresearch will investigate the selection of contingencies to simulate forthe training data, algorithms for converting simulation data into input-output pairs that make up the training sets, and measures of performanceused to evaluate the classifier operation. The PI and graduate studentswill collaborate with researchers at Cornell University and the BonnevillePower Administration and will test the proposed methods against otherschemes reported in the literature for out-of-step relaying, generatortripping, active load modulation, HVDC fast power changes, and reactivepower switching. Students in EE 588, Advanced Topics in Power Systems,will train and test NNs on data from the research. Undergraduate studentsin EE 479, Automatic Control Systems Laboratory, will design feedbackcontrols for the simple power system model that is analyzed in thisproposal. The PI will engage all students in active learning throughfrequent and extensive exercises that lead students through the discoveryprocess of problem solving instead of just rewarding the memorization oftechniques. The PI will distribute detailed, annotated solutions to allhomework problems on the due date. These teaching methods have been foundby the PI to be successful with a broad spectrum of students, includingwomen, minorities and people with disabilities.***