반복영역 바로가기
주메뉴로 바로가기
좌측메뉴로 바로가기
본문으로 바로가기

Home PeopleFacultyAdjunct/Invited Faculty

Adjunct/Invited Faculty

프린트페이스북

Jinkyoo Park

Ph.D. in Civil and Environmental Engineering,
Stanford, 2016

Education

  • 2009.02 Seoul National University. Architectural Engineering B.S.
  • 2011.08 UT-Austin. Civil and Environmental Engineering M.S.
  • 2015.12 Stanford University. Electrical Engineering M.S.
  • 2016.03 Stanford University. Civil and Environmental Engineering Ph.D.

Research experience

  • 2016.04 ~ Current: Assistant Professor, Department of Industrial & Systems Engineering, KAIST

Research goal

  • Development of data-driven, probabilistic optimization algorithms
  • Big data analytics using sparse and local Gaussian Process regression
  • Cooperative control for multi-agent systems
  • Design, monitoring and control of renewable energy systems (e.g., wind farms)
  • Optimum operation of energy storage systems
  • Monitoring and control of smart manufacturing systems
  • Health monitoring and condition based maintenance for large-scale infrastructures

Research area


Sequential decision-making strategies under uncertainty


Most engineering systems continuously interact with a stochastic environment. The behavior of such systems in uncertain environments can be learned from the data, and the enhanced understanding can be exploited to make optimum decisions regarding the maintenance and operation of the systems. Our lab explores various sequential decision-making procedures (such as bandit problems, Bayesian Optimization, Markov decision process, Reinforcement Learning) in which learning about the target systems and optimizing the system response occur simultaneously. We focus on the conceptualization and the implementation of these algorithms to control target systems that interact with stochastic environments.

Data-driven cooperative control for wind farm


Conventionally, every wind turbine in a wind farm is operated to maximize its own power production without taking into account the interactions among the wind turbines in a wind farm. Because of wake interference, such greedy control strategy can significantly lower the power productions of the downstream wind turbines and, thus, reduce the overall wind farm energy production. As an alternative to the greedy control strategy, we study a cooperative wind farm control strategy that determines and executes the optimum coordinated control actions for maximizing the total wind farm power production. To determine the optimum coordinated control inputs of the wind turbines, we employ a data driven optimization method that seeks to find the optimum control actions using only the power measurement data collected from the wind turbines in a wind farm.

Optimum operation of energy storage systems


Renewable energy sources are intermittent and uncertain, posing challenges in the reliable operation of grid with variable demand. Energy storage systems can effectively resolve the imbalance between the energy generation and demand by decoupling the time of energy generation and usage. Our lab explores various ways to derive the optimum operation of the energy storage system, mainly focusing on data-driven approaches, such as approximated dynamic programming and reinforcement learning. In addition, our lab research into the impacts of distributed energy storage systems to an energy grid in the framework of game theory.

Real-time data collection/processing and learning framework


To efficiently deal with a large volume of streaming data, raw sensor data should be collected and processed effectively in real time. We are investigating ways to organize data in a structured format, to design and extract features that are relevant to characterizing a target system, and to efficiently manage the data and the analytics model constructed using the collected data. As an example, Figure bellow shows the procedure of collecting sensor monitoring data from a manufacturing milling machine and constructing analytics model from the data.
 

Selected publications

  • J. Park and K. H. Law. (2016). “Bayesian Ascent (BA): An efficient data-driven optimization scheme for real-time control and its application to wind farm power maximization,” IEEE Transactions on Control Systems Technology, DOI: 10.1109/TCST.2015.2508007.
  • R. Bhinge, J. Park, N. Biswas, M. Moneer, S. Rachuri, D. Dornfeld and K. H. Law. (2015). “An intelligent machine monitoring system for energy prediction using a Gaussian Process regression,” ASME Journal of Manufacturing Science and Engineering (Accepted).
  • J. Park and K. H. Law. (2015). “A data-driven, cooperative wind farm control to maximize the total power production,” Applied Energy, 165, pp.151-165.
  • J. Park and K. H. Law. (2015). “Cooperative wind turbine control for maximizing wind farm power using sequential convex programming,” Energy Conversion and Management, 101, pp. 295-316.
  • J. Park and K. H. Law. (2015). “Layout optimization for maximizing wind farm power production using sequential convex programming,” Applied Energy, 151, pp. 320-334.
  • J. Park, S. Basu and L. Manuel. (2015). “Toward isolation of salient features in stable boundary layer wind fields that influence loads on wind turbines,” Energies, 8(4), pp. 2977-3012.
  • J. Park, K. Smarsly, K. H. Law and D. Hartmann. (2015). “Analyzing the temporal variation of wind turbine responses using Gaussian Mixture Model and Gaussian Discriminant Analysis,” Journal of Computing in Civil Engineering, 29(4), pp. B4014011-1-11.
  • C. Shi, J. Park, L. Manuel and M. Tognarelli. (2014). “A data-driven model identification algorithm for riser fatigue damage assessment,” Journal of Offshore Mechanics and Arctic Engineering, 136(3), 031702.
  • J. Park, G. Morgenthal, K. Kim, S. Kwon and K. H. Law. (2013). “Power evaluation of flutter-based electromagnetic energy harvesters using computational fluid dynamics simulations,” Journal of Intelligent Material Systems and Structures, 25(14), 1800-1812.
  • J. Park, S. Basu and L. Manuel. (2013). “Large-eddy simulation of stable boundary layer turbulence and estimate of associated wind turbine loads,” Wind Energy, 17(3), pp. 359-384.

Professional activities

  • Best Paper Award for Manufacturing Engineering Division (MED), 2015 ASME International Manufacturing Science and Engineering Conference (MSEC 2015)
  • Best Research Paper Award in the Area of Resilience and Smart Structures, 2013 ASCE International Workshop on Computing in Civil Engineering
  • ILJU Foundation Fellowship, 2011-2015
  • University of Texas at Austin Graduate School Fellowship, 2009-2010
  • Distinguished Graduate for Engineering School of Seoul National University, 2009
  • Pony Chung Foundation Fellowship, 2008-2009

LIST