More Like this

1. Learning from Non-Experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes

   https://doi.org/10.1145/3491241  

   Codispoti, Jackson ; Khamesi, Atieh R. ; Penn, Nelson ; Silvestri, Simone ; Shin, Eura ( February 2022 , ACM Transactions on Cyber-Physical Systems)

   With the acceleration of ICT technologies and the Internet of Things (IoT) paradigm, smart residential environments , also known as smart homes are becoming increasingly common. These environments have significant potential for the development of intelligent energy management systems, and have therefore attracted significant attention from both academia and industry. An enabling building block for these systems is the ability of obtaining energy consumption at the appliance-level. This information is usually inferred from electric signals data (e.g., current) collected by a smart meter or a smart outlet, a problem known as appliance recognition . Several previous approaches for appliance recognition have proposed load disaggregation techniques for smart meter data. However, these approaches are often very inaccurate for low consumption and multi-state appliances. Recently, Machine Learning (ML) techniques have been proposed for appliance recognition. These approaches are mainly based on passive MLs, thus requiring pre-labeled data to be trained. This makes such approaches unable to rapidly adapt to the constantly changing availability and heterogeneity of appliances on the market. In a home setting scenario, it is natural to consider the involvement of users in the labeling process, as appliances’ electric signatures are collected. This type of learning falls into the category of Stream-based Active Learning (SAL). SAL has been mainly investigated assuming the presence of an expert , always available and willing to label the collected samples. Nevertheless, a home user may lack such availability, and in general present a more erratic and user-dependent behavior. In this paper, we develop a SAL algorithm, called K -Active-Neighbors (KAN), for the problem of household appliance recognition. Differently from previous approaches, KAN jointly learns the user behavior and the appliance signatures. KAN dynamically adjusts the querying strategy to increase accuracy by considering the user availability as well as the quality of the collected signatures. Such quality is defined as a combination of informativeness , representativeness , and confidence score of the signature compared to the current knowledge. To test KAN versus state-of-the-art approaches, we use real appliance data collected by a low-cost Arduino-based smart outlet as well as the ECO smart home dataset. Furthermore, we use a real dataset to model user behavior. Results show that KAN is able to achieve high accuracy with minimal data, i.e., signatures of short length and collected at low frequency. 

   more » « less
2. A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data

   https://doi.org/10.3390/electronics10040407  

   Mokhtari, Sohrab ; Abbaspour, Alireza ; Yen, Kang ; Sargolzaei, Arman ( February 2021 , Electronics)

   Attack detection problems in industrial control systems (ICSs) are commonly known as a network traffic monitoring scheme for detecting abnormal activities. However, a network-based intrusion detection system can be deceived by attackers that imitate the system’s normal activity. In this work, we proposed a novel solution to this problem based on measurement data in the supervisory control and data acquisition (SCADA) system. The proposed approach is called measurement intrusion detection system (MIDS), which enables the system to detect any abnormal activity in the system even if the attacker tries to conceal it in the system’s control layer. A supervised machine learning model is generated to classify normal and abnormal activities in an ICS to evaluate the MIDS performance. A hardware-in-the-loop (HIL) testbed is developed to simulate the power generation units and exploit the attack dataset. In the proposed approach, we applied several machine learning models on the dataset, which show remarkable performances in detecting the dataset’s anomalies, especially stealthy attacks. The results show that the random forest is performing better than other classifier algorithms in detecting anomalies based on measured data in the testbed.

    

   more » « less
3. Security Vulnerabilities of Smart Meters in Smart Grid

   https://doi.org/10.1109/IECON.2019.8926992  

   Gui, Yutian ; Siddiqui, Ali Shuja ; Tamore, Suyash Mohan ; Saqib, Fareena ( October 2019 , Security Vulnerabilities of Smart Meters in Smart Grid)

   Integration of complex and high-speed electronic components in the state of art electric power system enhances the need for improved security infrastructure and resilience against invasive and non-invasive attacks on the smart grid. A modern smart grid system integrates a variety of instruments and standards to achieve cost-effective and time-effective energy measurement and management. As the fundamental component in the smart grid, the smart meter supports real-time monitoring, automatic control, and high-speed communication along with power consumption recording. However, the wide use of smart meters also increases privacy and security concerns. In this paper, we demonstrate the vulnerability of side-channel attacks on secure communication in smart grids for software-based and hardware-based implementations. 

   more » « less
4. Safety Analysis of AMI Networks Through Smart Fraud Detection

   https://doi.org/10.1109/CNS.2019.8802845  

   Jakaria, A H ; Rahman, Mohammad Ashiqur ; Moula Mehedi Hasan, Md Golam ( June 2019 , IEEE Conference on Communications and Network Security (CNS))

   Advanced metering infrastructure (AMI)is a critical part of a modern smart grid that performs the bidirectional data flow of sensitive power information such as smart metering data and control commands. The real-time monitoring and control of the grid are ensured through AMI. While smart meter data helps to improve the overall performance of the grid in terms of efficient energy management, it has also made the AMI an attractive target of cyber attackers with a goal of stealing energy. This is performed through the physical or cyber tampering of the meters, as well as by manipulating the network infrastructure to alter collected data. Proper technology is required for the identification of energy fraud. In this paper, we propose a novel technique to detect fraudulent data from smart meters based on the energy consumption patterns of the consumers by utilizing deep learning techniques. We also propose a method for detecting the suspicious relay nodes in the AMI infrastructure that may manipulate the data while forwarding it to the aggregators. We present the performance of our proposed technique, which shows the correctness of the models in identifying the suspicious smart meter data. 

   more » « less
5. Enabling Opportunistic Low-cost Smart Cities By Using Tactical Edge Node Placement

   https://doi.org/10.23919/WONS51326.2021.9415579  

   Madamori, Oluwashina ; Max-Onakpoya, Esther ; Erhardt, Gregory D. ; Baker, Corey E. ( January 2021 , 2021 16th Annual Conference on Wireless On-demand Network Systems and Services Conference (WONS))

   null (Ed.)

   Smart city projects aim to enhance the management of city infrastructure by enabling government entities to monitor, control and maintain infrastructure efficiently through the deployment of Internet-of-things (IoT) devices. However, the financial burden associated with smart city projects is a detriment to prospective smart cities. A noteworthy factor that impacts the cost and sustainability of smart city projects is providing cellular Internet connectivity to IoT devices. In response to this problem, this paper explores the use of public transportation network nodes and mules, such as bus-stops as buses, to facilitate connectivity via device-to-device communication in order to reduce cellular connectivity costs within a smart city. The data mules convey non-urgent data from IoT devices to edge computing hardware, where data can be processed or sent to the cloud. Consequently, this paper focuses on edge node placement in smart cities that opportunistically leverage public transit networks for reducing reliance on and thus costs of cellular connectivity. We introduce an algorithm that selects a set of edge nodes that provides maximal sensor coverage and explore another that selects a set of edge nodes that provide minimal delivery delay within a budget. The algorithms are evaluated for two public transit network data-sets: Chapel Hill, North Carolina and Louisville, Kentucky. Results show that our algorithms consistently outperform edge node placement strategies that rely on traditional centrality metrics (betweenness and in-degree centrality) by over 77% reduction in coverage budget and over 20 minutes reduction in latency. 

   more » « less