More Like this

1. Model-driven Per-panel Solar Anomaly Detection for Residential Arrays

   https://doi.org/10.1145/3460236  

   Feng, Menghong ; Bashir, Noman ; Shenoy, Prashant ; Irwin, David ; Kosanovic, Beka ( October 2021 , ACM Transactions on Cyber-Physical Systems)

   null (Ed.)

   There has been significant growth in both utility-scale and residential-scale solar installations in recent years, driven by rapid technology improvements and falling prices. Unlike utility-scale solar farms that are professionally managed and maintained, smaller residential-scale installations often lack sensing and instrumentation for performance monitoring and fault detection. As a result, faults may go undetected for long periods of time, resulting in generation and revenue losses for the homeowner. In this article, we present SunDown, a sensorless approach designed to detect per-panel faults in residential solar arrays. SunDown does not require any new sensors for its fault detection and instead uses a model-driven approach that leverages correlations between the power produced by adjacent panels to detect deviations from expected behavior. SunDown can handle concurrent faults in multiple panels and perform anomaly classification to determine probable causes. Using two years of solar generation data from a real home and a manually generated dataset of multiple solar faults, we show that SunDown has a Mean Absolute Percentage Error of 2.98% when predicting per-panel output. Our results show that SunDown is able to detect and classify faults, including from snow cover, leaves and debris, and electrical failures with 99.13% accuracy, and can detect multiple concurrent faults with 97.2% accuracy. 

   more » « less
2. Invited paper: An Efficient Energy Management Solution for Renewable Energy Based IoT Devices

   https://doi.org/10.1145/3571306.3571387  

   Liri, Elizabeth ; Ramakrishnan, K. K. ; Kar, Koushik ; Lyon, Geoff ; Sharma, Puneet ( January 2023 , ICDCN '23: Proceedings of the 24th International Conference on Distributed Computing and Networking)

   Multi-sensor IoT devices enable the monitoring of different phenomena using a single device. Often deployed over large areas, these devices have to depend on batteries and renewable energy sources for power. Therefore, efficient energy management solutions that maximize device lifetime and information utility are important. We present SEMA, a smart energy management solution for IoT applications that uses a Model Predictive Control (MPC) approach to optimize IoT energy use and maximize information utility by dynamically determining task values to be used by the IoT device’s sensors. Our solution uses the current device battery state, predicted available solar energy over the short-term, and task energy and utility models to meet the device energy goals while providing sufficient monitoring data to the IoT applications. To avoid the need for executing the MPC optimization at a centralized sink (from which the task values are downloaded to the SEMA devices), we propose SEMA-Approximation (SEMA-A), which uses an efficient MPC Approximation that is simple enough to be run on the IoT device itself. SEMA-A decomposes the MPC optimization problem into two levels: an energy allocation problem across the time epochs, and task-dependent sensor scheduling problem, and finds efficient algorithms for solving both problems. Experimental results show that SEMA is able to adapt the task values based on the available energy, and that SEMA-A closely approximates SEMA in sensing performance. 

   more » « less
3. A cyber-physical system approach for photovoltaic array monitoring and control

   https://doi.org/10.1109/IISA.2017.8316458  

   Rao, S. ; Katoch, S. ; Turaga, P. ; Spanias, A. ; Tepedelenlioglu, C. ; Ayyanar, R. ; Braun, H. ; Lee, J. ; Shanthamallu, U. ; Banavar, M. ; et al ( August 2017 , IEEE IISA 2017)

   In this paper, we describe a Cyber-Physical system approach to Photovoltaic (PV) array control. A machine learning and computer vision framework is proposed for improving the reliability of utility scale PV arrays by leveraging video analysis of local skyline imagery, customized machine learning methods for fault detection, and monitoring devices that sense data and actuate at each individual panel. Our approach promises to improve efficiency in renewable energy systems using cyber-enabled sensory analysis and fusion. 

   more » « less
4. Recent Advances in Cyberattack Detection and Mitigation Techniques for Renewable Photovoltaic Distributed Energy CPS

   Jessica Whitaker and Danda B. Rawat ( June 2023 , Computing Conference)

   Cyberattacks targeted to the energy cyber-physical system (ECPS), also known as the smart grid, could interrupt the electricity supply with major ramifications. Attackers identify and exploit any vulnerable portion of the energy power grid, including the inverters with solar-powered photovoltaic (PV) panels. PV presents unique challenges as electricity consumers have also become providers of solar energy for utilities. As mandates require increased PV penetration across the world for positive environmental impacts, increased cyberattacks targeted at PV systems impact reliability and efficiency within the ECPS. The new technologies continuously being introduced to manage the ECPS and ensure bi-directional communications and energy flow between components also lead to more attack surfaces, system vulnerabilities, and heightened malicious attacks. Data integrity attacks are increasing within PV systems. In this paper, we present a survey of different methods that are proposed and explored for identifying and preventing cyberattacks targeted at PV systems. The attack detection methods include voltage control, data diodes, and voltage measurement algorithms. Furthermore, we present blockchain, cyber switching, and other attack mitigation techniques for PV systems. 

   more » « less
5. An REU/RET Project: IoT Platform and Network Data Visualization

   Toutsop, O. ( November 2021 , 2021 Fall ASEE Middle Atlantic Section Meeting)

   Internet of Things (IoT) is a connected network of devices that exchange data using different protocols. The application of IoT ranges from intelligent TVs and intelligent Refrigerators to smart Transportation. This research aims to provide students with hands-on training on how to develop an IoT platform that supports device management, connectivity, and data management. People tend to build interconnected devices without having a basic understanding of how the IoT platform backend function. Studying the Arm Pelion will help to understand how IoT devices operate under the hood. This past summer, Morgan State University has hosted undergraduate engineering students and high school STEM teachers to conduct IoT security research in the Cybersecurity Assurance & Policy (CAP) Center. The research project involved integrating various hardware sensor devices and real-time data monitoring using the Arm Pelion IoT development platform. Some of the student/teacher outcomes from the project include: 1) Learning about IoT Technology and security; 2) Programming an embedded system using Arm Mbed development board and IDE; 3 3) Developing a network of connected IoT devices using different protocols such as LWM2M, MQTT, CoAP; 4) Investigating the cybersecurity risks associated with the platform; and 5) Using data analysis and visualization to understand the network data and packet flow. First, the student/teacher must consider the IoT framework to understand how to address the security. The IoT framework describes the essential functions of an IoT network, breaking it down into separate layers. These layers include an application layer, middleware layer, and connectivity layer. The application layer allows the users to access the platform via a smartphone or any other dashboard. The Middleware layer represents the backend system that provides edge devices with data management, messaging, application services, and authentication. Finally, the connectivity layer includes devices that connect the user to the network, including Bluetooth or WiFi. The platform consists of several commercial IoT devices such as a smart camera, baby monitor, smart light, and other devices. We then create algorithms to classify the network data flow; to visualize the packets flow in the network and the structure of the packets data frame over time. 

   more » « less