Logo: University of Southern California

Events Calendar


  • PhD Defense - Chung Ming Cheung

    Fri, May 07, 2021 @ 09:00 AM - 11:00 PM

    Computer Science

    University Calendar


    PhD Candidate: Chung Ming Cheung

    Time: May 7th 2021, 9 - 11 am

    Zoom link:
    prasannaseminars.github.io

    Committee: Professor Viktor K Prasanna (Chair)
    Professor C S Raghavendra
    Professor Aiichiro Nakano

    Title: Data-Driven Methods for Increasing Real-Time Observability in Smart Distribution Grids

    Abstract:
    Traditional power distribution grids have evolved into smart grids with the development of advanced metering infrastructures and renewable energy based distributed energy resources (DER). This has introduced the following challenges: (1) The stochasity of renewable energy based DERs has increased the volatility of grid frequency; (2) the decentralization of generation into small scaled DERs has reduced grid inertia. To address these challenges, real-time knowledge and understanding of signal measurements of grid assets, called observability, are crucial to make grid operation decisions swiftly. High observability can be obtained through extensive metering of assets in smart grids for data collection, and time series analytics that extract information from the collected time series data. However, the proliferation of DERs has introduced new challenges in these analytics. DERs located behind-the-meters (BTM) are not recorded individually and hidden from real-time observations. This combined with the volatile nature of DER assets greatly reduces observability. As a result, these data-driven models do not have full observability of data and suffer from accuracy losses.

    In this thesis, we develop data-driven approaches to improve observability. We develop unsupervised disaggregation models for separation of signals of BTM DERs hidden from net meter measurements. We focus on the separation of signals from the activity of BTM solar photovoltaics and battery storages. We also propose capturing spatial features using machine learning models such as spatial-temporal graph convolution networks for improving time series analytics in smart grids, e.g. load forecasting and missing data imputation. Moreover, we show that the increase in observability provided by these data-driven models can enhance other time series analytics in smart grids.

    WebCast Link: prasannaseminars.github.io

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal

Return to Calendar