Research & Projects

Figure Project 1: The hierarchical control structure operates at three levels to meet the microgrid’s operator objectives.

Project 1

Distributed Energy Resource Management Systems (DERMS) Tertiary Controls Development

As a lead engineer in the DERMS Center of Excellence at Eaton, I played a pivotal role in the development of the global Energy Management System (EMS). I delivered the optimizer and forecasting algorithms, utilizing the open-source program Pyomo to manage various DER assets within the microgrid intelligently. This optimization significantly enhanced the system's efficiency, sustainability, and resiliency. To provide accurate input to the optimizer, load and solar forecasting algorithms were developed using well-established models such as artificial neural networks, LSTM, and XGBoost. These models were trained with data from different microgrid sites and validated through extensive real-world test scenarios, ensuring robust performance.

Figure Project 2: Illustration of the control mechanisms for the proposed controller in a typical microgrid setup. Cyber anomalies were injected into the communication network’s voltages and frequency signals.

Project 2

An Explainable Intelligent Framework for Anomaly Mitigation in Cyber-Physical Inverter-Based Systems

Inverter-based microgrids essentially constitute an extensive communication layer that makes them vulnerable to cyber anomalies. The distributed cooperative controllers implemented at the secondary control level of such systems exchange information among physical nodes using the cyber layer to meet the control objectives. The cyber anomalies targeting the communication network may distort normal operation, therefore, an effective cyber anomaly mitigation technique using an Artificial Neural Network (ANN) is proposed in this paper. The intelligent anomaly mitigation control is modeled using a dynamic neural network that employs a nonlinear autoregressive network with exogenous inputs. The effects of false data injection on the distributed cooperative controller at the secondary control level are considered. The training data for designing the neural network are generated by multiple simulations of the designed microgrid under various operating conditions using MATLAB/Simulink. An explainable framework is employed to interpret the output generated by the trained neural network-based controller after the neural network has been trained offline and validated online in the simulated microgrid. The proposed technique is applied as secondary voltage and frequency control of distributed cooperative control-based microgrid to regulate the voltage under various operating conditions. The performance of the proposed control technique is verified by injecting various types of false data injection-based cyber anomalies. The proposed ANN-based secondary controller maintained the normal operation of the microgrid under various cyber anomalies as demonstrated on a real-time digital simulator.

Read the full article.

Figure Project 3: The potential targets of cyber-attacks include the communication networks in the cyber layer and the intelligent devices in the physical layer of the microgrids.

Project 3

A Review of AI-Based Cyber-Attack Detection and Mitigation in Microgrids

In this paper, the application and future vision of Artificial Intelligence (AI)-based techniques in microgrids are presented from a cyber-security perspective of physical devices and communication networks. The vulnerabilities of microgrids are investigated under a variety of cyber-attacks targeting sensor measurements, control signals, and information sharing. With the inclusion of communication networks and smart metering devices, the attack surface has increased in microgrids, making them vulnerable to various cyber-attacks. The negative impact of such attacks may render the microgrids out-of-service, and the attacks may propagate throughout the network due to the absence of efficient mitigation approaches. AI-based techniques are being employed to tackle such data-driven cyber-attacks due to their exceptional pattern recognition and learning capabilities. AI-based methods for cyber-attack detection and mitigation that address the cyber-attacks in microgrids are summarized. A case study is presented showing the performance of AI-based cyber-attack mitigation in a distributed cooperative control-based AC microgrid. Finally, future potential research directions are provided that include the application of transfer learning and explainable AI techniques to increase the trust of AI-based models in the microgrid domain.

Access the full article.

Figure Project 4: Real-time setup to evaluate the proposed resilient anomalies identification design is shown.

Project 4

Intelligent anomaly identification in cyber-physical inverter-based systems

Modern cyber-physical systems have become more autonomous and distributed with the inclusion of advanced control architectures and communication networks. Power electronics-based inverters that employ extensive communication structures are integral part of such systems. The controllers for inverter-based systems rely on communication networks that make them vulnerable to cyber-physical anomalies. The cyber anomalies occur due to malicious attacks targeting the communication layer and physical anomalies are caused by power system faults in the physical layer of the microgrid. In this work, an intelligent anomaly identification (IAI) technique for such systems is presented utilizing data-driven artificial intelligence tools that employ multi-class support vector machines (MSVM) for anomaly classification and localization. The effects of cyber anomalies such as false data injection and denial of service attacks that target the communication network are considered in this work. In addition, the physical anomalies due to power system faults are also considered. The proposed technique utilizes statistical features extracted from measurements for optimal learning of a dual of MSVM classifiers. The mean absolute percentage error is used as a performance metric and the results are validated by comparing to an artificial neural network, Naive Bayes classification, and using real-time simulations in OPAL-RT.

Read the article.

Figure Project 5: Short-term load prediction performance comparison for weekdays, Saturdays, and Sundays.

Project 5

Ensemble Method for Short-Term Load Forecasting Using LSTM, SVR, and FFNN Taking into Account Seasonal Dependency

Short-term load forecasting (STLF) is used by building operators to make informed decisions about electricity usage and purchase. Recently, research has investigated the potential of ensemble learning for improving forecast accuracy with researchers often combining several of the same type of learning machines into an ensemble. In this paper, a novel diversified ensemble learning method is proposed and implemented for a small library building in San Antonio, Texas. Three different machine learning models – feedforward neural network (FFNN), long short-term memory (LSTM) network, and support vector regression (SVR) – are trained separately and their outputs are combined using an ensemble FFNN using the back-propagation training method to further reduce the prediction error of the load forecast. The proposed model is tested using smart meter data including outdoor temperature and total building electrical load at 15-minute intervals. The model is tested using data gathered from four different seasons of the same year and is shown to capture the seasonal dependencies, with a mean absolute percentage error of 7%, while it outperforms the individual prediction models in the majority of the tested cases.

Learn more about this work.

Figure Project 6: The architecture of networked microgrids with cyber vulnerabilities is shown.

Project 6

Cyber Vulnerabilities of Modern Power Systems

Modernpowersystemsheavily relyonInternet-of-Things(IoT) and emerging wide-area sensor networks that expose them to cyber vulnerabilities such as network failures and cyber-attacks. Some practical network failure examples include North America (2003) due to state estimator and alarm system failure, Austria (2013) due to network congestion caused by a software bug, and Switzerland (2005) due to information overload. Ukraine’s power system went down in December 2015 leaving thousands of homes and facilities out of power due to a cyber-attack caused by a malware, identified as BlackEnergy, in control center computers. Such failures and cyber-attacks will leave the majority of customers without a power supply and may cause significant damage to highly sensitive and mission-critical equipment. In the case of power electronics-intensive microgrids, the after-effects of the cyber-attacks are even more detrimental due to comparatively weaker and fragile distribution grid, highly dynamic source and load profiles, and meager generational inertia. Cyber vulnerabilities are divided into two main categories, i.e., cyber-attacks and network failures. An overview of such cyber vulnerabilities, practical limitations of modern power systems, and relevant prevention measures, and a case study are presented.

Read the chapter.

FIGURE Project 7: Flow chart with the steps involved in the training of the ANN model.

Project 7

Intelligent Anomaly Mitigation in Cyber-Physical Inverter-based Systems

The distributed cooperative controllers for inverter-based systems rely on communication networks that make them vulnerable to cyber anomalies. In addition, the distortion effects of such anomalies may also propagate throughout inverter-based cyber-physical systems due to the cooperative cyber layer. In this paper, an intelligent anomaly mitigation technique for such systems is presented utilizing data driven artificial intelligence tools that employ artificial neural networks. The proposed technique is implemented in secondary voltage control of distributed cooperative control-based microgrid, and results are validated by comparison with existing distributed secondary control and real-time simulations on real-time simulator OPAL-RT.

Learn more about this work.

Figure Project 8: Steps for Processing of Health-Related Tweets to Detect Misinformation

Project 8

Case Study on Detecting COVID-19 Health-Related Misinformation in Social Media

The COVID-19 pandemic has generated what public health officials called an infodemic of misinformation. As social distancing and stay-at-home orders came into effect, many turned to social media for socializing. This increase in social media usage has made it a prime vehicle for the spreading of misinformation. This paper presents a mechanism to detect COVID-19 health-related misinformation in social media following an interdisciplinary approach. Leveraging social psychology as a foundation and existing misinformation frameworks, we defined misinformation themes and associated keywords incorporated into the misinformation detection mechanism using applied machine learning techniques. Next, using the Twitter dataset, we explored the performance of the proposed methodology using multiple state-of-the-art machine learning classifiers. Our method shows promising results with at most 78% accuracy in classifying health-related misinformation versus true information using uni-gram-based NLP feature generations from tweets and the Decision Tree classifier. We also provide suggestions on alternatives for countering misinformation and ethical considerations for the study.

See the full article.

Figure Project 9: Number of countries with net-metering/net-billing policy.

Project 9

The Penetration of Renewable and Sustainable Energy in Asia: A State-of-the-Art Review on Net-Metering

Conventional fossil-fuel energy resources are being drastically depleted; thus, the current shift towards renewable energy (RE) resources has become imperative. However, there are many impediments to the adoption of renewable power generation. These impediments can be overcome by enacting policies to encourage the acceptance of sustainable energy resources. For instance, the net-metering policy can provide the necessary incentives to promote the development of local distributed energy sources, primarily solar photovoltaic and wind generators. While there has been significant advancement and development in net-metering in Asia with the increased penetration of RE, at present there is a lack of systematic review in this area. This paper aims to present an in-depth review on net-metering advances and challenges, current RE shares, and future RE targets in the Asian region. Additionally, a case study is performed and an economic analysis of net-metering regulations in an Asian country is carried out. In this study, the monetary benefits of net-metering policies for residential consumers are proved. It is envisaged that the information gathered in this paper will be a valuable one-stop source of information for Asian researchers working on this topic.

Read the full article.

Project 10

Robust Control of Hybrid Distributed Generation for Frequency Regulation

This paper presents the frequency regulation in the hybrid distributed generation system (HDGS). Being a critical problem it directly affects the reliability and quality of the HDGS. Therefore a robust controller is designed for the frequency regulation of HDGS. The proposed hybrid system consists of a conventional thermal source and distributed generation resources including a wind turbine, fuel cell, aqua electrolyzer, diesel engine generator, and super capacitor. H-infinity controller for frequency regulation is considered using linear matrix inequalities. The robustness of this controller is presented in the proposed hybrid power system with varying load and wind power conditions. The performance of the proposed controller is verified by performing simulations.

Read the article.

Page updated

Google Sites

Report abuse