Dynamic Composite Load Signature Detection and Classification using Supervised Learning over Disturbance Data

被引:0
|
作者
Tray, Kelly [1 ]
Cicilio, Phylicia [1 ]
Brekken, Ted [1 ]
Cotilla-Sanchez, Eduardo [1 ]
机构
[1] Oregon State Univ, Sch Elect & Comp Engn, Corvallis, OR 97331 USA
来源
2017 IEEE ENERGY CONVERSION CONGRESS AND EXPOSITION (ECCE) | 2017年
关键词
Composite load model; dynamic composite load signatures; Load Model Data Tool (LMDT); multi-layer perceptron; data preprocessing;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Load modeling that can accurately represent the dynamic behavior of generators and loads is important in the operation and planning of transmission and distribution systems. Yet, it is a complex subject in power system research communities and electric utilities. The composition of the end-use loads is changing continually based on climate zone, season, and time. The WECC composite load model has been developed recently to better represent Fault Induced Delayed Voltage Recovery (FIDVR) events, which is caused by air-conditioning stalling phenomena. The approach is based on using the information of the load class at the substation level and composition of airconditioning, induction machines, power electronics, and static loads associated with the load class. Therefore, it is important to be able to identify and classify the load class. This can be accomplished by using machine learning based signature detection since each load class has a unique signature response due to a particular disturbance in the system. The objective of this project is to implement a supervised learning, Artificial Neural Network (ANN), algorithm to detect and classify the composite load signatures in terms of residential, commercial, agriculture, and mixed load class. Furthermore, the process of creating WECC composite load model data, using the Load Model Data Tool (LMDT), to be used in time-domain dynamic simulation (PSS/E) is demonstrated. The One-Area Reliability Test System is used for the purpose of demonstration and validation of our proposed methodology. The key contribution of this research includes: 1) To demonstrate automated disturbance data creation and collection using the latest composite load model developed by WECC. 2) Introduce a new automated solution to determine the load classes by leveraging synchrophasor data and machine learning techniques.
引用
收藏
页码:1560 / 1566
页数:7
相关论文
共 50 条
  • [21] On-line supervised learning for dynamic security classification using probabilistic neural networks
    Gavoyiannis, AE
    Voumvoulakis, EM
    Hatziargyriou, ND
    2005 IEEE POWER ENGINEERING SOCIETY GENERAL MEETING, VOLS, 1-3, 2005, : 2669 - 2675
  • [22] Constrained dynamic programming and supervised penalty learning algorithms for peak detection in genomic data
    Hocking, Toby Dylan
    Rigaill, Guillem
    Fearnhead, Paul
    Bourque, Guillaume
    Journal of Machine Learning Research, 2020, 21
  • [23] Disturbance rejection and high dynamic quadrotor control based on reinforcement learning and supervised learning
    Mingjun Li
    Zhihao Cai
    Jiang Zhao
    Jinyan Wang
    Yingxun Wang
    Neural Computing and Applications, 2022, 34 : 11141 - 11161
  • [24] Disturbance rejection and high dynamic quadrotor control based on reinforcement learning and supervised learning
    Li, Mingjun
    Cai, Zhihao
    Zhao, Jiang
    Wang, Jinyan
    Wang, Yingxun
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (13): : 11141 - 11161
  • [25] Regression on dynamic PLS structures for supervised learning of dynamic data
    Dong, Yining
    Qin, S. Joe
    JOURNAL OF PROCESS CONTROL, 2018, 68 : 64 - 72
  • [26] Constrained Dynamic Programming and Supervised Penalty Learning Algorithms for Peak Detection in Genomic Data
    Hocking, Toby Dylan
    Rigaill, Guillem
    Fearnhead, Paul
    Bourque, Guillaume
    JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
  • [27] Email Classification Using Supervised Learning Algorithms
    Bhadra, Akshay
    Hitawala, Saifuddin
    Modi, Ruchit
    Salunkhe, Suraj
    PROGRESS IN ADVANCED COMPUTING AND INTELLIGENT ENGINEERING, VOL 2, 2018, 564 : 81 - 90
  • [28] Adaptive Data Augmentation for Supervised Learning over Missing Data
    Liu, Tongyu
    Fan, Ju
    Luo, Yinqing
    Tang, Nan
    Li, Guoliang
    Du, Xiaoyong
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2021, 14 (07): : 1202 - 1214
  • [29] Genetic Classification of Populations Using Supervised Learning
    Bridges, Michael
    Heron, Elizabeth A.
    O'Dushlaine, Colm
    Segurado, Ricardo
    Morris, Derek
    Corvin, Aiden
    Gill, Michael
    Pinto, Carlos
    PLOS ONE, 2011, 6 (05):
  • [30] Spam Classification using Supervised Learning Techniques
    Lakshm, R. Deepa
    Radha, N.
    PROCEEDINGS OF THE FIRST AMRITA ACM-W CELEBRATION OF WOMEN IN COMPUTING IN INDIA (A2WIC), 2010,