GLAD: A Method of Microgrid Anomaly Detection Based on ESD in Smart Power Grid

Qiyu Wei 魏启宇, Rui Ma, Yiqiu Wang, Mingyu Chen, Yanru Sun, Mingjie Liu, Xiaoyong Lin
July, 2020

Abstract

A microgrid is defined as a group of interconnected loads and distributed energy resources, that the electrical loads fluctuate with respect to the grid. When focusing on load anomaly in microgrid, different from the traditional centralized grid (macrogrid), a method of microgrid anomaly detection based on the extreme studentized deviate(ESD) test, is proposed as GLAD (grid load anomaly detection). GLAD under the enhanced ESD is adapted to solve this problem properly, using the detect_ts function of PyCuliarity library to carry out anomaly detection simulation experiment in Python software, according to a series of statistical analysis. In the paper, the existing time series and anomaly detection methods are firstly analyzed and summarized, then GLAD are designed to detect the grid load variations. Some conventional anomaly detection methods are also discussed for higher efficiency of GLAD. Moreover, there are still better methods for anomaly detection of microgrid, Finally, GLAD with machine learning modeling is discussed for the future smartgrids of anomaly detection in distributed energy resources.

Type
Conference paper
Publication
In 2020 IEEE International Conference on Power, Intelligent Computing and Systems
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Create your slides in Markdown - click the Slides button to check out the example.

Supplementary notes can be added here, including code, math, and images.

Qiyu Wei 魏启宇
Qiyu Wei 魏启宇
Ph.D student.

My research interests include AI in Semiconductor, 3D Deep Learning and Bayesian Optimisation.