Sample Efficient Home Power Anomaly Detection in Real Time Using Semi-Supervised Learning

Xinlin Wang,Sung-Hoon Ahn,Insoon Yang

doi:10.1109/access.2019.2943667

Xinlin Wang, Sung-Hoon Ahn + Show 1 more

Open Access

https://doi.org/10.1109/access.2019.2943667

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2019
Citations: 59	License type: CC BY 4.0

Affiliation: Seoul National University

Abstract

Anomaly detection in home power monitoring can be categorized into two main types: detection of electrical theft, leakage, or nontechnical loss and monitoring anomalies in the daily activities of residents. Focusing on the application and practicality of anomaly detection, we propose sample efficient home power anomaly detection (SEPAD) with improved monitoring performance in terms of electricity usage as well as changes in the daily living activities of residents via provision of detailed feedback. SEPAD consists of two classifiers: an appliance pattern matching classifier (APMC) and an energy consumption habit classifier (ECHC). The APMC uses a single-source separation framework based on a semi-supervised support vector machine (semi-SVM) model. This semi-supervised learning method requires only a small amount of labeled data to achieve high accuracy in near real time and is a sample efficient detection method. The hidden Markov model (HMM)-based ECHC improves the rationality of SEPAD by providing anomaly detection functionality with respect to the daily activities of householders, especially the elderly and residents in developing areas. When SEPAD detects the appearance of an unknown pattern or known patterns contrary to the household’s electricity usage habits, it triggers an alarm. SEPAD was applied to monitor power consumption data from Mkalama, a rural area in Tanzania with 52 households containing nearly 150 occupants connected to a solar powered off-grid network. The results of the practical test demonstrate the high accuracy and practicality of the proposed method.

Highlights

An emphasis on environmentally friendly practices has prompted society to seek more sustainable energy practices, with ambitious targets being set by many countries in an effort to achieve significant energy savings [1]–[4]
According to a 2018 study by the Energy Information Administration, home electricity consumption accounted for 38.5% (1.46 trillion kWh) of the total annual electricity consumption in the United States [5]
A good home power anomaly detector can improve the quality of life of residents by checking for anomalies related to health and well-being

Summary

INTRODUCTION

An emphasis on environmentally friendly practices has prompted society to seek more sustainable energy practices, with ambitious targets being set by many countries in an effort to achieve significant energy savings [1]–[4]. We propose sample efficient home power anomaly detection (SEPAD) that has two main applications: detecting anomalies in electricity usage attributable to theft, leakage, or nontechnical loss and monitoring resident daily activities. 2) The proposed SEPAD is based on a semi-SVM model, which is a sample efficient classification method, that provides a simple but efficient way to reduce training costs and uses a small quantity of labeled data to perform classification with high accuracy. 3) SEPAD employs a two-dimensional monitoring method, that checks for anomalies in the daily living activities of residents according to the electricity usage habits of a household. Our work provides useful guidelines for the application of machine learning technology to home power anomaly detection, when a computing infrastructure with high specifications is unavailable.

RELATED WORK

SUSPICIOUS DATA SELECTION

Suspicious Data Selection

SEMI-SVM-BASED PATTERN MATCHING

ENERGY CONSUMPTION HABIT CLASSIFIER

Variables and Functions

VIII. CONCLUSION