CEDoc UM6P-CC: Enhancing Cybersecurity in Photovoltaic Systems through Advanced Intrusion Detection

CEDoc UM6P-CC: Enhancing Cybersecurity in Photovoltaic Systems through Advanced Intrusion Detection

1. Introduction UM6P

Mohammed VI Polytechnic University is an institution dedicated to research and innovation in Africa and aims to position itself among world-renowned universities in its fields The University is engaged in economic and human development and puts research and innovation at the forefront of African development. A mechanism that enables it to consolidate Morocco's frontline position in these fields, in a unique partnership-based approach and boosting skills training relevant for the future of Africa. Located in the municipality of Benguerir, in the very heart of the Green City, Mohammed VI Polytechnic University aspires to leave its mark nationally, continentally, and globally.

2. Context

The integration of Photovoltaic (PV) systems into modern energy infrastructures has significantly advanced the adoption of renewable energy. However, this integration has also introduced new cybersecurity challenges. PV systems, often comprising interconnected inverters, controllers, and communication networks, are increasingly susceptible to cyberattacks that can compromise system integrity, data accuracy, and overall grid stability. Traditional cybersecurity measures, such as firewalls and encryption, are insufficient to address the dynamic and distributed nature of PV systems. Therefore, the development of robust Intrusion Detection Systems (IDS) tailored for PV applications is imperative to safeguard these critical infrastructures.

Intrusion Detection Systems (IDS) are designed to monitor, detect, and respond to suspicious activities in a network or system. In the context of PV systems, IDS can be used to monitor the various components, such as solar panels, inverters, and controllers, to detect abnormal behavior, unauthorized access, or attacks that could compromise the integrity and performance of the system. IDS can classify attacks based on predefined patterns (signature-based IDS) or detect new, unknown attack vectors by analyzing system behavior (anomaly-based IDS).

Given the dynamic nature of PV systems and the increasing sophistication of cyberattacks, traditional IDS methods can struggle to keep up. This is where Artificial Intelligence (AI) can enhance the detection and prevention capabilities of IDS. AI techniques, particularly machine learning (ML) and deep learning (DL), enable the IDS to learn from vast amounts of data, identify complex patterns, and adapt to evolving threats over time. For example, anomaly detection models powered by AI can identify subtle deviations from normal system behavior that might indicate an attack, even if that attack has never been seen before.

3. Research Methodology

To achieve the goals of this research, a combination of the following methodologies will be employed:

1. State-of-the-Art Review: A comprehensive literature review will be conducted to survey the latest advancements in IDS for renewable energy systems, with a specific focus on PV systems.
2. Dataset Creation and Evaluation: The development of a robust, publicly available dataset tailored to PV systems will be a critical component. This dataset will include both normal and attack data from different components of PV systems.
3. Design of IDS Framework: Based on the state-of-the-art review, a tailored IDS architecture will be designed specifically for PV systems. This framework will incorporate advanced machine learning techniques (e.g., deep learning, anomaly detection), optimized for real-time operation without compromising energy efficiency.
4. Simulation and Testing: Various attack scenarios, will be simulated in a controlled environment to test the effectiveness of the IDS framework.
5. Deployment in a Testbed: The final IDS solution will be deployed in a small-scale testbed of PV components to validate its real-world performance.

4. Admission Criteria

This project is funded by Green Energy Park (GEP). The PhD candidate for this project should have the following qualifications and skills:

• A strong background in cybersecurity, renewable energy systems (specifically PV systems), or electrical engineering is necessary.
• Proficiency in programming languages, e.g., Python.
• The candidate should demonstrate strong analytical skills and an ability to develop innovative solutions to complex, interdisciplinary problems.
• Strong written and verbal communication skills are required, as the candidate will need to publish research findings and collaborate with interdisciplinary teams.

5. References

J. Zhang et al., "Machine Learning-Based Cyber-Attack Detection in Photovoltaic Farms," in IEEE Open Journal of Power Electronics, vol. 4, pp , 2023, doi: /OJPEL

M. Ahmadzadeh, A. Abazari, M. Ghafouri, A. Ameli and S. M. Muyeen, "A Deep Convolutional Neural Network-Based Approach to Detect False Data Injection Attacks on PV-Integrated Distribution Systems," in IEEE Access, vol. 12, pp , 2024, doi: /ACCESS

Ali, W., et al A Comprehensive Review of Intrusion Detection Systems for Smart Grids. arXiv. Link.

Bashir, M., Aslam, N., & Li, G Cybersecurity for renewable energy systems: Vulnerabilities, threats, and defenses. Renewable and Sustainable Energy Reviews, 132, Link.

Kumar, P., et al Cybersecurity for decentralized energy systems: Current challenges and future directions. CMC: Computers, Materials & Continua, 77(1), Link.

Liu, S., et al False Data Injection Attacks and Countermeasures in Power Grid. IEEE Transactions on Power Systems, 35(4), Link.

Rojas, D., et al Injection of Malicious Code in Energy Systems: Attacks and Countermeasures. ScienceDirect. Link.

Wang, J., et al A Survey of False Data Injection Attacks and Defenses for Renewable Energy Systems. Journal of Renewable and Sustainable Energy, 13(2), 1-15. Link.

Zhang, X., et al Cybersecurity challenges in PV systems: Vulnerabilities, attacks, and machine learning-based defense strategies. MDPI Electronics, 14(3), 546. Link.

Zhang, Y., et al Unauthorized Access Attacks in Critical Infrastructure: The Case of Energy Systems. IEEE Transactions on Industrial Informatics, 17(5),

How to Apply:

Interested candidates are invited to submit their applications in the portal, including a detailed CV, academic transcripts and recommendations. Applications should be sent to Prof. Anas Motii