skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids

Abstract

The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasetsmore » as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.« less

Authors:
 [1];  [2];  [3];  [2]
  1. Department of Computer Science, University of Southern California, Los Angeles, CA
  2. Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA
  3. US Army Research Lab, Playa Vista, CA
Publication Date:
Research Org.:
Univ. of Southern California, Los Angeles, CA (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
OSTI Identifier:
1607585
Report Number(s):
EE0008003-6
DOE Contract Number:  
EE0008003
Resource Type:
Conference
Resource Relation:
Conference: 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
Country of Publication:
United States
Language:
English
Subject:
14 SOLAR ENERGY; Smart grids, Generative adversarial networks, Time series analysis, Gallium nitride, Data models, Probability distribution, Data privacy

Citation Formats

Zhang, Chi, Kuppannagari, Sanmukh, Kannan, Rajgopal, and Prasanna, Viktor K. Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids. United States: N. p., 2019. Web. doi:10.1109/SmartGridComm.2018.8587464.
Zhang, Chi, Kuppannagari, Sanmukh, Kannan, Rajgopal, & Prasanna, Viktor K. Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids. United States. https://doi.org/10.1109/SmartGridComm.2018.8587464
Zhang, Chi, Kuppannagari, Sanmukh, Kannan, Rajgopal, and Prasanna, Viktor K. 2019. "Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids". United States. https://doi.org/10.1109/SmartGridComm.2018.8587464. https://www.osti.gov/servlets/purl/1607585.
@article{osti_1607585,
title = {Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids},
author = {Zhang, Chi and Kuppannagari, Sanmukh and Kannan, Rajgopal and Prasanna, Viktor K.},
abstractNote = {The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasets as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.},
doi = {10.1109/SmartGridComm.2018.8587464},
url = {https://www.osti.gov/biblio/1607585}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {10}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: