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

职业：电力系统中的开环离散事件控制

• 批准号: 9983653
• 负责人: Steven Rovnyak
• 金额: $ 20万
• 依托单位: Louisiana Tech University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2000
• 资助国家: 美国
• 起止时间: 2000-06-01 至 2005-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9983653&HistoricalAwards=false
• 关键词: CAREER; Open; Loop; Discrete; Event

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.***

9983653Rovnyak本研究的目标是开发和验证模式识别方法，如决策树（DT）和神经网络（NN）的电力系统广域开环离散事件控制。 拟议的控制将提供独立服务运营商（ISO）和当今的公用事业与必要的工具，以实现降低成本的目标放松管制，而不牺牲可靠性。 拟议的研究将调查选择的突发事件来模拟的训练数据，算法将模拟数据转换成输入输出对，使训练集，和措施的performanceused来评估分类器的操作。 PI和研究生将与康奈尔大学和邦纳维尔电力管理局的研究人员合作，并将针对文献中报道的失步中继、发电机跳闸、有源负载调制、高压直流快速功率变化和无功功率切换的其他方案测试提出的方法。 EE 588，电力系统高级主题的学生将在研究数据上训练和测试NN。 EE 479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参与主动学习，引导学生通过发现问题解决的过程，而不仅仅是奖励记忆技术。 PI将在截止日期分发详细的、带注释的所有家庭作业问题的解答。 PI发现，这些教学方法对包括妇女、少数民族和残疾人在内的各种学生都很成功。