BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IEEE Sweden - ECPv5.0.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:IEEE Sweden
X-ORIGINAL-URL:https://site.ieee.org/sweden
X-WR-CALDESC:Events for IEEE Sweden
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20191027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20190610
DTEND;VALUE=DATE:20190612
DTSTAMP:20200228T064644
CREATED:20190523T112703Z
LAST-MODIFIED:20190626T062128Z
UID:2190-1560124800-1560297599@site.ieee.org
SUMMARY:Ph.D. and Industrial Short Course on Machine Learning in Power Systems
DESCRIPTION:Record: \n28 participants \nfrom Chalmers\, Vattenfall\, Svenska Krafnät\, KTH\, ABB\, Sapienza University of Rome \napprox. 50% IEEE member \n \n \nCourseDescription_Chalmers_IEEE \n \nRegistration: Send an email to Annie Grundevik with your name\, affiliation and research interest. If you are a PhD student\, indicate if there is a paper that you would like to choose as part of the project. \n \nPh.D. and Industrial Short Course on Machine Learning in Power Systems \nChalmers University of Technology – in cooperation with IEEE Sweden PE/PEL Joint Chapter \nGeneral information \nInstructor: Lang Tong\, Fulbright Distinguished Chair in Alternative Energy \nCornell University \nEmail: langt@chalmers.se \nURL: https://people.ece.cornell.edu/ltong \nLectures: June 10 & 11 10AM-12PM\, 1-4PM (with breaks). \nJune 14\, 10 AM – preliminary 3PM (project presentation\, only for PhD) \nLocations: Chalmers University of Technology\nHörsalsvägen 11\n412 96\, Göteborg\, Sweden \nCredits: 1 \nRegistration: Send an email to Annie Grundevik with your name\, affiliation and research interest. If you are a PhD student\, indicate if there is a paper that you would like to choose as part of the project. \nCourse description \nThis course introduces three types of machine learning problems and some of their applications in power systems: (i) classification; (ii) regression; (ii) sequential learning and decisions. \nMachine learning in classification deals with problems of learning functions with discrete values. Examples in power systems are fault detection\, classification\, and all types of detection problems. A standard machine learning technique is the support vector machine (SVM). Regression learning deals with learning functions with continuous values. Examples in power systems include state estimation\, load or price forecasting\, and system parameter estimations. A typical method is the empirical risk minimization with neural networks. Sequential learning and decision-making deal with problems of continuous learning as more data are collected and decisions are made sequentially based on the information available at the time of decision. A popular learning model is reinforcement learning. \n \nCourse organization \nThere are eight one-hour lecture sessions in two days. The course covers some of the basic concepts and formulations in machine learning as well as selected power system applications. On the last day of the course\, there will be a 10-minute presentation on a research paper relating to machine learning techniques in power system. The project presentation is required for all PhD students that would like to receive the course credit. The Pass/Fail grade of the course is given based on attendance and the completion of the presentation. \nCourse material. Lecture notes and research papers. \nReferences \n[1] T. Hastie\, R. Tibshirani\, and J. Friedman\, The elements of statistical learning: data mining\, inference\, and prediction\, 2nd edition\, Springer 2009 \n[2] R. Sutton and A. G. Barto\, Reinforcement Learning\, 2nd edition\, MIT Press\, 2018. \n \nTentative topics \n \n\nNeural networks and learning\n\nStructure of neural network and universal approximation.\nSupervised (and unsupervised) learning. Empirical risk minimization\nBag of tricks: stochastic gradient descent\, drop-out\, early stopping.\nPerformance: PAC learning\, VC dimension\, bias-variance tradeoff\nSpecial neural networks: CNN\, RNN\, GANS\, Auto encoder\, and LTSM\n\n\nClassification\n\nHypothesis testing and classification problems.\nStructure of classifiers and learning algorithms: SVM\, Naïve Bayes\, K-mean.\nPower system applications: voltage instability detection and assessment.\n\n\nRegression\n\nThe regression problem and supervised learning\nPower system application: state estimation and bad-data detection\n\n\nSequential (online) learning\n\nThe Markov decision problem (MDP)\, decision tree\, and reinforcement learning\nThe multi-armed bandit problem (MAB)\nPower system application: virtual bidding in the electricity market\n\n\n\n \n \n \n
URL:https://site.ieee.org/sweden/event/ph-d-and-industrial-short-course-on-machine-learning-in-power-systems/
LOCATION:Chalmers University of Technology\, Hörsalsvägen 11 412 96\, Göteborg\, Sweden
ORGANIZER;CN="IEEE%20PE%2FPEL%20Chapter":MAILTO:Ambra.Sannino@dnvgl.com
END:VEVENT
END:VCALENDAR