False Data Injection Attacks on Reinforcement Learning-Based Charging Coordination in Smart Grids and a Countermeasure

被引:3
作者
Elshazly, Amr A. [1 ]
Elgarhy, Islam [2 ,3 ]
Eltoukhy, Ahmed T. [4 ,5 ]
Mahmoud, Mohamed [2 ]
Eberle, William [1 ]
Alsabaan, Maazen [6 ]
Alshawi, Tariq [7 ]
机构
[1] Tennessee Technol Univ, Dept Comp Sci, Cookeville, TN 38505 USA
[2] Tennessee Technol Univ, Dept Elect & Comp Engn, Cookeville, TN 38505 USA
[3] Ain Shams Univ, Fac Comp & Informat Sci, Dept Comp Syst, Cairo 11566, Egypt
[4] Univ South Carolina Aiken, Comp Sci & Engn Dept, Aiken, SC 29801 USA
[5] Al Azhar Univ, Fac Engn, Dept Elect Engn, Cairo 11884, Egypt
[6] King Saud Univ, Coll Comp & Informat Sci, Dept Comp Engn, Riyadh 11451, Saudi Arabia
[7] King Saud Univ, Coll Engn, Dept Elect Engn, Riyadh 11421, Saudi Arabia
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 23期
关键词
security; false data injection; reinforcement learning; charging coordination; smart grid; VEHICLES; ENERGY;
D O I
10.3390/app142310874
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Reinforcement learning (RL) is proven effective in optimizing home battery charging coordination within smart grids. However, its vulnerability to adversarial behavior poses a significant challenge to the security and fairness of the charging process. In this study, we, first, craft five stealthy false data injection (FDI) attacks that under-report the state-of-charge (SoC) values to deceive the RL agent into prioritizing their charging requests, and then, we investigate the impact of these attacks on the charging coordination system. Our evaluations demonstrate that attackers can increase their chances of charging compared to honest consumers. As a result, honest consumers experience reduced charging levels for their batteries, leading to a degradation in the system's performance in terms of fairness, consumer satisfaction, and overall reward. These negative effects become more severe as the amount of power allocated for charging decreases and as the number of attackers in the system increases. Since the total available power for charging is limited, some honest consumers with genuinely low SoC values are not selected, creating a significant disparity in battery charging levels between honest and malicious consumers. To counter this serious threat, we develop a deep learning-based FDI attack detector and evaluated it using a real-world dataset. Our experiments show that our detector can identify malicious consumers with high accuracy and low false alarm rates, effectively protecting the RL-based charging coordination system from FDI attacks and mitigating the negative impacts of these attacks.
引用
收藏
页数:23
相关论文
共 30 条
[1]  
Ajiboye PO, 2024, Journal of Engineering and Applied Science, V71, DOI [10.1186/s44147-024-00422-w, 10.1186/s44147-024-00422-w, DOI 10.1186/S44147-024-00422-W]
[2]   Charging Ahead: A Hierarchical Adversarial Framework for Counteracting Advanced Cyber Threats in EV Charging Stations [J].
Al-Mehdhar, Mohammed ;
Albaseer, Abdullatif ;
Abdallah, Mohamed ;
Al-Fuqaha, Ala .
2024 IEEE 99TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2024-SPRING, 2024,
[3]   Detecting State of Charge False Reporting Attacks via Reinforcement Learning Approach [J].
Alomrani, Mhd Ali ;
Tushar, Mosaddek Hossain Kamal ;
Kundur, Deepa .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (10) :10467-10476
[4]   Hierarchical Optimization for User-Satisfaction-Driven Electric Vehicles Charging Coordination in Integrated MV/LV Networks [J].
Arias, Nataly Banol ;
Sabillon, Carlos ;
Franco, John Fredy ;
Quiros-Tortos, Jairo ;
Rider, Marcos J. .
IEEE SYSTEMS JOURNAL, 2023, 17 (01) :1247-1258
[5]  
Ausgrid, Solar Home Electricity Data
[6]  
Bhadani U., 2024, Int. Res. J. Eng. Technol. (IRJET), V11, P801
[7]   Securing Space Cognitive Communication with Blockchain [J].
Bhuva, Dipen ;
Kumar, Sathish .
2023 IEEE COGNITIVE COMMUNICATIONS FOR AEROSPACE APPLICATIONS WORKSHOP, CCAAW, 2023,
[8]   A novel continuous authentication method using biometrics for IOT devices [J].
Bhuva, Dipen R. ;
Kumar, Sathish .
INTERNET OF THINGS, 2023, 24
[9]   Exploring Symmetry-Induced Divergence in Decentralized Electric Vehicle Scheduling [J].
Chen, Weijia ;
Wang, Jianxiao ;
Zhang, Tiance ;
Li, Gengyin ;
Jin, Yihang ;
Ge, Leijiao ;
Zhou, Ming ;
Tan, Chin-Woo .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2024, 60 (01) :1117-1128
[10]   Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors [J].
El-Toukhy, Ahmed T. ;
Mahmoud, Mohamed M. E. A. ;
Bondok, Atef H. ;
Fouda, Mostafa M. ;
Alsabaan, Maazen .
IEEE ACCESS, 2023, 11 :97373-97390