| Title | A hybrid evolutionary and machine learning approach for smart city planning: Digital twin approach |
|---|---|
| ID_Doc | 41729 |
| Authors | Ji, CX; Niu, Y |
| Title | A hybrid evolutionary and machine learning approach for smart city planning: Digital twin approach |
| Year | 2024 |
| Published | |
| Abstract | The amalgamation of Internet of Things (IoT) and communication systems within Smart Grid Control Systems (SGCS) has amplified their susceptibility to cyber-attacks, posing a significant threat. Traditional intrusion detection systems (IDSs), originally designed for securing IT systems, exhibit limitations in SGCS due to reliance on predefined structures and training on specific cyber-attack patterns. This study addresses the challenge by proposing a deep learning (DL) framework to establish balanced representations for the inherently asymmetric SGCS datasets. These representations are seamlessly integrated into a dedicated DL -based model for attack detection within the SGCS environment. Utilizing Support Vector Machines (SVM) and K -Nearest Neighbors (KNN), the model identifies novel cyber-attack representations. Performance evaluation through 10 -fold crossvalidation on two real SGCS datasets reveals the proposed approach's superiority over traditional methods like Random Forest (RF) and Deep Neural Networks (DNN). Additionally, the generalized method can be effortlessly implemented in existing SGCS infrastructures with minimal complexity. This study introduces a novel cybersecurity enhancement method for Smart Grid Control Systems by integrating a Cyber-Physical Digital Twin with a deep learning -based IDS. This approach intricately models both physical and cyber components, facilitating real-time training and fine-tuning of the intrusion detection model using synthetic cyber threats. The digital twin undergoes rigorous testing to assess the model's effectiveness, employing scenario analyses to identify vulnerabilities and formulate response strategies. The adaptive digital twin fosters a proactive cybersecurity stance by implementing security measures such as access controls and cyber range simulation. Real-time monitoring, analytics, and stakeholder collaboration enhance incident response readiness. The lifecycle simulation, spanning from model development to deployment, ensures alignment with regulations. This integrated approach not only detects but proactively responds to cyber threats, fortifying Smart Grid Control Systems against evolving risks. |
Similar Articles
| ID | Score | Article |
|---|---|---|
39081
|
Almuqren, L; Aljameel, SS; Alqahtani, H; Alotaibi, SS; Hamza, MA; Salama, AS A White Shark Equilibrium Optimizer with a Hybrid Deep-Learning-Based Cybersecurity Solution for a Smart City Environment(2023)Sensors, 23, 17 | |
| 41832
|
Gupta, SK; Tripathi, M; Grover, J Hybrid optimization and deep learning based intrusion detection system(2022) | |
| 37333
|
Almasri, MM; Alajlan, AM A novel-cascaded ANFIS-based deep reinforcement learning for the detection of attack in cloud IoT-based smart city applications(2023)Concurrency And Computation-Practice & Experience, 35.0, 22 | |
| 43178
|
Li, B; Yang, XY; Wu, XG Role of net-zero renewable-based transportation systems in smart cities toward enhancing cultural diversity: Realistic model in digital twin(2024) | |
| 37359
|
Al-Taleb, N; Saqib, NA Towards a Hybrid Machine Learning Model for Intelligent Cyber Threat Identification in Smart City Environments(2022)Applied Sciences-Basel, 12.0, 4 | |
| 40658
|
Yong, Y; Ye, KH Novel cyber-physical architecture for optimal operation of renewable-based smart city considering false data injection attacks: Digital twin technologies for smart city infrastructure management(2024) | |
| 41739
|
Tan, ZW; Li, Z Digital twins for sustainable design and management of smart city buildings and municipal infrastructure(2024) | |
| 38272
|
Saba, T; Khan, AR; Sadad, T; Hong, SP Securing the IoT System of Smart City against Cyber Threats Using Deep Learning(2022) | |
| 36314
|
Rashid, MM; Kamruzzaman, J; Hassan, MM; Imam, T; Wibowo, S; Gordon, S; Fortino, G Adversarial training for deep learning-based cyberattack detection in IoT-based smart city applications(2022) | |
| 36837
|
Elsaeidy, AA; Jamalipour, A; Munasinghe, KS A Hybrid Deep Learning Approach for Replay and DDoS Attack Detection in a Smart City(2021) |