Avoiding Occupancy Detection From Smart Meter Using Adversarial Machine Learning

Ibrahim Yilmaz,Ambareen Siraj

doi:10.1109/access.2021.3057525

Ibrahim Yilmaz, Ambareen Siraj

Open Access

https://doi.org/10.1109/access.2021.3057525

Copy DOI

Abstract

More and more conventional electromechanical meters are being replaced with smart meters because of their substantial benefits such as providing faster bi-directional communication between utility services and end users, enabling direct load control for demand response, energy saving and so on. However, the fine-grained usage data provided by smart meter brings additional vulnerabilities from users to companies. Occupancy detection is one such example which causes privacy violation of smart meter users. Detecting the occupancy of a home is straightforward with time of use information as there is a strong correlation between occupancy and electricity usage. In this work, our major contributions are twofold. First, we validate the viability of an occupancy detection attack based on a machine learning technique called Long Short Term Memory (LSTM) method and demonstrate improved results. In addition, we introduce an Adversarial Machine Learning Occupancy Detection Avoidance (AMLODA) framework as a counter attack in order to prevent abuse of energy consumption. Essentially, the proposed privacy-preserving framework is designed to mask real-time or near real-time electricity usage information using calculated optimum noise without compromising users’ billing systems functionality. The results show that without the use of the proposed AMLODA approach, our occupancy detection attack models using LSTM achieve a high detection rate with Matthews Correlation Coefficient (MCC) value of 0.89 on average for the five different households energy consumption data under investigation captured during the winter and summer seasons. With the proposed AMLODA approach working to protect consumers’ privacy, occupancy detection attacks are demonstrated to be mitigated with the MCC values of the attack models converging to zero with no significant change over the actual consumption data and thus protecting needed functionalities of the utility companies.

Highlights

In modern-day households and businesses, smart meters are being deployed more than traditional meters
To the best of our knowledge, this paper presents the first research that demonstrates an effective and efficient obfuscation-based privacy preserving solution that does not rely on any external devices/entities for maintaining consumers’ privacy
Using Long Short Term Memory (LSTM), we show the viability of an occupancy detection attack over a massive real-world electricity consumption dataset

Summary

Introduction

In modern-day households and businesses, smart meters are being deployed more than traditional meters. Providers as needed without direct human intervention Such detailed and timely energy usage information offers numerous advantages to both grid participants and utility companies. On the users’ sides, benefits of smart meters include monitoring of the users’ electricity usage pattern in a timely manner, which allows users to keep track of their energy consumption in real-time or near real-time. This results in robust demand response systems that allow customers to save money by consuming less energy during peak hours and selling excess energy to the grid provider [3]. As a result of our proposed approach, both grid providers and grid participants can take advantage of smart grid benefits with ease

Objectives

Methods

Results

Conclusion