Smart Energy Cyber-Physical Systems: Big Data Analytics and Cyber Security

Speaker:  Shiyan Hu – Houghton, MI, United States
Topic(s):  Graphics and Computer-Aided Design

Abstract

A smart energy cyber-physical system is characterized by the interactions among the sensing devices and the physical energy system. Such a system leverages big data analytics techniques in developing the situational awareness to improve the control performance. Major challenges include how to decide the data are accurate and trustworthy and how to assess the system state even if the data contain uncertainties. To decide whether a sensor (e.g., a smart meter or any intelligent electronic device) returns the reliable measurement, I will describe a systematic framework, which is based on partially observable Markov decision process, orthogonal matching pursuit, and empirical mode decomposition, to assess the accuracy level of a smart meter through comparing with historical meter readings, neighboring meter readings and master meter readings. This framework can also be used to analyze energy usage behaviors for detecting various smart grid cyber attacks such as energy theft. I will then discuss a sparse statistical regression based prognostic health analysis framework to assess the health state of an underlying energy system using the collected sensor data potentially with uncertainties. I will conclude the talk with some of the ongoing research in this topic.

About this Lecture

Number of Slides:  75
Duration:  60 minutes
Languages Available:  Chinese (Simplified), English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.