Workforce Development for Future Smart Energy Systems

NSF CyberTraining Project: Secure, Resilient Cyber-Physical Energy System Workforce Pathways via Data-Centric, Hardware-in-the-Loop Training (2023 - 2027)

Florida Atlantic University leads the workforce development for future smart energy systems and prepares future STEM scientists and engineers. This is in collaboration with the University of South Florida, Florida International University, and the University of Central Florida.

Students and professionals are provided with mentored, hands-on training combining expertise across electrical engineering, communication, data science, and security. Participants develop and refine the multi-disciplinary skillsets needed for the data-centric power and energy industry using unique, remotely connected smart grid cyberinfrastructure. Participants extend their academic research portfolios, strengthening their career competitiveness as future cyberinfrastructure professionals and users. The project thus serves the national interest, as stated by NSF's mission: to promote the progress of science and to secure the national defense.

Our training program includes the following key areas:

Artificial Intelligence and Data Analytics
Communication, Network, and Hardware Security
Sensor Networks and Internet-of-Things
Renewable Energy Modeling and Simulation
Real-Time Learning and Microgrid Optimization
Multi-Level Decision-Making Process of Intelligent Systems

Smart Grid and Renewable Energy (Infographic description)

Internet of Energy (Infographic description)

YOUR FLORIDA EXPERIENCE

This paid, nine-day program focuses on virtual/remote training and providing students and professionals with an exciting experience that will prepare them for research or careers in engineering and science.
This program welcomes professionals (e.g., power engineer or software engineer working in a related industry) to apply.
Participants will typically work 9 a.m. to 5 p.m. each day. Participants are paid a $700/week stipend (total $1,400).
Additional paid, project-based training opportunities are also available after the nine-day training. Please see the project descriptions below.

2021 TRAINING PROGRAMS

Two-Week Training (Preliminary Schedule):

Days	Training Topics	Instructor
Monday	Morning: a short course that covers the background of electric power systems and the develoment of smart grid (e.g., renewable energy integration). Power load demand and renewable energy prediction will also be introduced. Afternoon: a hands-on project for renewable energy generation prediction using data-driven techniques. Off-the-shelf time series prediction techniques and AI technologies will be leveraged.	Yufei Tang, Ph.D.
Tuesday	Morning: a tutorial on basic knowledge of communication and network security, common vulnerabilities, and security attacks. Afternoon: communication and security designs for smart grid systemss, including two-way communication architecture, security attack generation, security setting, as well as data collection.	Zhuo Lu, Ph.D.
Wednesday	Morning: a short course on renewable energy generation, with a focus on modeling, conversion, and the impacts of this power on the grid. Afternoon: a hands-on laboratory where participants will write software to model different environmental conditions, such as turbulence levels and mean flow speeds, and turbine systems and then run the simulator using these numerical models.	James VanZwieten, Ph.D.
Thursday	Morning: an intensive training section to introduce machine learning concepts, neural networks, and deep learning models. The training will help students build theoretical foundations and knowledge base that they need to cultivate their interests into hand-on skills. Afternoon: a hands-on data science training section to teach programming, experiment designs, and reporting skills (using Python) for object detection and text classification, as well as anomaly detection.	Hill Zhu, Ph.D.
Friday	Morning: multiple industry representatives will be invited to provide short breakout courses. The session will conclude with a structured networking session, allowing students to actively discuss content and career paths with industry partners and recruiters. Afternoon: two tutorials will be provided. The first will provide students with an understanding of the social significance of securing IoT and energy systems, placing these technical systems into a broader social context. The second session will cover communication and inclusion in the cybersecurity workforce, drawing on a history of hacking.	Nathan Fisk, Ph.D.
Monday	Morning: a short course on IoT that provides basic background in the history of distributed sensing and actuation, IoT architectures, and programming fundamentals. Afternoon: a hands-on laboratory focused on developing a complete IoT application. The laboratory will build upon the short-course, leveraging Raspberry Pi sensing kits and Telit’s cloud-based IoT platform to construct a basic monitoring system for smart home applications.	Jason Hallstrom, Ph.D.
Tuesday	Morning: a short course on the introduction of microgrid energy systems. This course will have discussions on the key components and algorithms of microgrid and its applications to data center and other criticial infrastructures. Afternoon: a hands-on project on the microgrid energy mangement with AI methods. In the project, students will study how to apply learning methods for microgrid energy operation, bettery manegement and community load incentive designs.	Zhen Ni, Ph.D.
Wednesday	Morning: a short course on wide-area monitoring system (WAMS) for power systems. This course will have discussions on the key measurement device in WAMS, namely the phasor measurement unit (PMU) and the various applications using the synchrophasor data provided by WAMS. Afternoon: a hands-on project on the power system state estimation by synchrophasor data. In the project, students will learn how to build the state estimation model for power systems with synchrophasor data and compare different algorithms for state estimation.	Dongliang Duan, Ph.D.
Thursday	Morning: a short course on data-centric network science and graph signal processing with applications in security and reliability analysis of smart grids. This course will discuss a data-centric network-based modeling, visualization and analysis of energy data and measurement timeseries of smart grids. Afternoon: a hands-on network analytics project that will provide a practice on how the physical structure of the smart grid and the embedded structures and patterns in energy data and measurement timeseries can be modeled using networks and analyzed using network analytics techniques to address reliability and security challenges in smart grids.	Mahshid R. Naeini, Ph.D.
Friday	Morning: a hands-on project on attack and defense design and analytics of the smart grid using deep learning. High-resolution spatial-temporal dataset will be collected from benchmark smart grid testbeds and provided to the students. Data samples will be collected in normal, faulty, and attacked scenarios based on accurate representation of real-world events through incorporating the cybersecurity module. Participants will be asked to use the attack detection algorithms developed previously for this probelm. Afternoon: Yufei Tang, Ph.D. and Zhuo Lu, Ph.D. will review the training activities. All of the workshop participants will present one of their mini-projects to the team, followed by certification and award ceremony.	Yufei Tang, Ph.D. and Zhuo Lu, Ph.D.

2021 Training Outcomes: 29 participants have been virtually trained for two weeks in the summer of 2021.

2022 TRAINING PROGRAMS

Two-Week Training:

Days	Training Topics	Instructor
May 31, Tuesday	Morning: program overview, followed by a short course on electric power systems and smart grids (e.g., renewable energy integration). Afternoon: a hands-on project on attack and defense design and analytics of the smart grid using deep learning. High-resolution spatial-temporal datasets will be collected from benchmark smart grids. Data samples will be in normal, faulty, and attacked scenarios based on accurate representation of real-world events.	Yufei Tang, Ph.D.
June 1, Wednesday	Morning: a tutorial on basic knowledge of communication and network security, common vulnerabilities, and security attacks. Afternoon: communication and security designs for smart grid systems, including two-way communication architecture, attack generation, security setting, and data collection.	Zhuo Lu, Ph.D.
June 2, Thursday	Morning: a short course on renewable energy generation, with a focus on modeling and conversion. Afternoon: a hands-on project of marine renewable energy numerical simulation to model different environmental conditions, such as turbulence levels and mean flow speeds, and turbine systems and then run the simulator using these numerical models.	James VanZwieten, Ph.D.
June 3, Friday	Morning: an intensive training section to introduce machine learning concepts, neural networks, and deep learning models. The training will help students build theoretical foundations and knowledge base that they need to cultivate their interests into hands-on skills. Afternoon: a hands-on data science training section to teach programming, experiment designs, and reporting skills (using Python) for object detection and text classification, as well as anomaly detection.	Hill Zhu, Ph.D.
June 6, Monday	Morning: a short course on IoT that provides a basic background in the history of distributed sensing and actuation, IoT architectures, and programming fundamentals. Afternoon: a hands-on laboratory focused on developing a complete IoT application. The laboratory will build upon the short course, leveraging Raspberry Pi sensing kits and Telit's cloud-based IoT platform to construct a basic monitoring system.	Jason Hallstrom, Ph.D.
June 7, Tuesday	Morning: a short course on the introduction of microgrid energy systems. This course will have discussions on the key components and algorithms of microgrids and their applications to data centers and other critical infrastructures. Afternoon: a hands-on project on microgrid energy management with AI methods. In the project, students will study how to apply reinforcement learning methods for microgrid energy operation, battery management, and community load incentive designs.	Zhen Ni, Ph.D.
June 8, Wednesday	Morning: a short course on wide-area monitoring systems (WAMS) for power systems. This course will have discussions on the key measurement device in WAMS, namely the phasor measurement unit and the various applications using the synchrophasor data provided by WAMS. Afternoon: a hands-on project on the power system state estimation by synchrophasor data. In the project, students will learn how to build the state estimation model for power systems with synchrophasor data and compare different algorithms for state estimation.	Dongliang Duan, Ph.D.
June 9, Thursday;	Morning: a short course on network science and graph signal processing with applications in smart grids, such as security and reliability analysis of smart grids. Afternoon: two hands-on network analytics projects for smart grid reliability and security. The projects will provide practice on how the physical structure of the smart grid and the embedded structures and patterns in energy data and measurement time series can be modeled using networks and analyzed using network analytics techniques to address reliability and security challenges in smart grids.	Mahshid R. Naeini, Ph.D.
June 10, Friday	Morning: industry representatives will be invited to provide short breakout courses, followed by a short course and discussion of the social significance of securing IoT and energy systems.	Nathan Fisk, Ph.D.

2022 Training Outcomes: 44 participants have been virtually trained for two weeks in the summer of 2022.

Project-based Training:

We plan to provide two additional longer-term research projects for the Summer/Fall of 2022. Participants are encouraged to take the two-week training to build the basic skills. Certain amount of incentives are also provided if participants are selected on the additional projects. The projects are described below.

Community Microgrid Energy Management
Led by Zhen Ni, Ph.D.
In-Person or Remote project
Learn more

Machine Learning Techniques to Detect GPS Spoofing Attacks
Led by Dongliang Duan, Ph.D.
In-Person or Remote project
Learn more

2024 TRANING PROGRAMS

Nine-Day Training:

Days	Training Topics	Software/ Coding Environment	Instructor

May 20, Monday	Morning: program overview, followed by a short course on electric power systems and smart grids (e.g., renewable energy integration). Afternoon: a hands-on project on attack and defense design and analytics of the smart grid using deep learning. High-resolution spatial-temporal datasets will be collected from benchmark smart grids.	Python and Jupiter Notebook	Yufei Tang
May 21, Tuesday	Morning: a tutorial on basic knowledge of communication and network security, common vulnerabilities, and security attacks. Afternoon: communication and security designs for smart grid systems, including two-way communication architecture, attack generation, security setting, and data collection.	Python 3 and Scapy Library	Zhuo Lu
May 22, Wednesday	Morning: a short course on renewable energy generation, with a focus on modeling and conversion. Afternoon: a hands-on project of marine renewable energy numerical simulation to model different environmental conditions and turbine systems and then run the simulator using these numerical models.	Matlab/Simulink and WEC-Sim	James VanZwieten
May 23, Thursday	Morning: an intensive training section to introduce machine learning concepts, neural networks, and deep learning models. Afternoon: a hands-on data science training section to teach programming, experiment designs, and reporting skills (using Python) for object detection and text classification, as well as anomaly detection.	Python, Scikit-learn, and Tensorflow	Hill Zhu and Mr. Zhiqiang Wang
May 24, Friday	Morning: a short course on the introduction of microgrid energy systems. This course will have discussions on the key components and algorithms of microgrids and their applications to data centers and other critical infrastructures. Afternoon: a hands-on project on microgrid energy management with AI methods. In the project, students will study how to apply reinforcement learning methods for microgrid energy operation, battery management, and community load incentive designs.	Matlab and Python	Zhen Ni
May 27, Monday	Morning: a tutorial on basic operating principles, control, and protection of bulk power grids. Example use cases to demonstrate false data injection (FDI) in power grids will also be discussed. Afternoon: a hands-on example of a real-time power grid model, and associated control, and protection algorithms using OPAL-RT simulator, and highlights the vulnerable measurement nodes and control nodes from a cyber-attack perspective.	Matlab	Sumit Paudyal
May 28, Tuesday	Morning: a short course on network science and graph signal processing with applications in smart grids, such as security and reliability analysis of smart grids. Afternoon: two hands-on network analytics projects for smart grid reliability and security. The projects will provide practice on how the physical structure of the smart grid and the embedded structures and patterns in energy data and measurement time series can be modeled using networks and analyzed using network analytics techniques to address reliability and security challenges in smart grids.	Python and Matlab	Mahshid R. Naeini
May 29, Wedneaday	Morning: a four-hour course on IoT/CPS security vulnerabilities and attacks. The course will take real attacks as examples to introduce various attack surfaces of IoT/CPS platforms, including the device interfaces, backends, and supply chain. Afternoon: a hands-on laboratory based on vulnerable p2p cameras, showing how to pen test the device by enumerating and exploiting the vulnerable device interfaces such as open ports or web interfaces, and how to review the security of the devices by reverse-engineering the firmware.	Python and Jupiter Notebook	Xueqiang Wang
May 30, Thursday	Morning: a tutorial on hardware security. The tutorial will discuss intellectual property protection and logic camouflaging techniques for ICs at the layout level. The tutorial will also cover the basics of methods for hardware trojan detection in ICs. Afternoon: a hands-on demonstration and design implementations of machine-learning-based hardware trojan detection for an embedded system.	Python and Jupiter Notebook	Dayane Alfenas Reis

Project-based Training:

We intend to offer an extra four long-term research projects, which can be conducted either in-person or remotely, subsequent to the completion of the training. Participants are strongly urged to undertake the nine-day training to establish foundational skills. A specified level of incentives will be extended to selected participants who participate in these supplementary projects. Further details about the projects can be found below, and individuals interested in their availability are encouraged to reach out directly to the lead faculty mentor.

Spatial-Temporal Big Data Analytics for Cyber-Physical Energy System Cybersecurity
Led by Yufei Tang, Ph.D.

Reinforcement Learning for Resilient Micro-Gird Infrastructure
Led by Zhen Ni, Ph.D.

Adaptive Defense against Malicious Network Inference in Critical Infrastructures
Led by Zhuo Lu, Ph.D.

Graph Signal Learning for Situational Awareness under Graph Uncertainties
Led by Mahshid Naeini, Ph.D.

HOW TO APPLY

Submit the following information in one email to Sasha Fung. ( cybertrainingfau@gmail.com ).

One-page statement of interest that describes your motivations, expectations, and long-term objectives.
One letter of recommendation from your advisor/mentor/supervisor.
A two-page comprehensive CV featuring essential personal details, including demographic information if available.
Complete transcript.

DATES

Application Window Opens: March 1, 2024
Application Deadline: April 19, 2024
Notification Date: On or before May 3, 2024
Nine-day Training: May 20, 2024 – May 31, 2024 (excluding weekends and holidays)

ELIGIBILITY

Preference will be given to graduates and professionals in science or engineering. Exceptional senior undergraduates will also be considered.
Minorities and women are strongly encouraged to apply.
Selections will be based on a combination of research interests, academic qualifications, and faculty recommendations.

CONTACT

For additional information please contact Yufei Tang, Ph.D. at (561) 297-4781 and tangy@fau.edu.

To print the NSF CyberTraining Flyer, click here.

FUNDING

This program is currently funded by the National Science Foundation grants OAC 2320972/2320973/2320974/2320975. This program has been funded by the National Science Foundation grants OAC 2017597/2017194 & 1949921/1923983

Let's have an adventure. Collect experiences and meet people you'll never forget. It's time to write your story, and we've got the perfect setting.