Multilayer cyberattacks identification and classification using machine learning in internet of blockchain...

Area of Science:

• Computer Science
• Electrical Engineering
• Cybersecurity

Background:

• Global energy demand is increasing, driven by population growth and economic expansion.
• Fossil fuel combustion for energy exacerbates climate change and poses health risks.
• Transitioning to renewable energy sources via smart grids (SG) introduces new cybersecurity challenges.

Purpose of the Study:

• To address the critical need for advanced cyber threat detection and prevention in smart grid environments.
• To develop and apply a novel hybrid machine learning (HML) model for identifying cyberattacks.
• To leverage big data from blockchain-based renewable energy systems for enhanced security.

Main Methods:

• Collected big data from solar and wind-powered distributed energy systems within blockchain-based smart grids.
• Developed a hybrid machine learning (HML) model integrating Deep Learning (DL) and Long-Short-Term Memory (LSTM) characteristics.
• Applied the HML model to identify patterns of Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks.

Main Results:

• Successfully identified unique patterns indicative of DoS and DDoS cyberattacks across power generation, transmission, and distribution.
• The HML model demonstrated effectiveness in classifying cyberattacks within the smart grid infrastructure.
• The generated big datasets are crucial for accurate energy system behavior prediction.

Conclusions:

• The developed HML model provides an effective solution for detecting and preventing cyber threats in smart grids.
• Utilizing big data from renewable energy systems enhances the security and reliability of smart grid operations.
• This research contributes to securing the future of energy by safeguarding smart grid systems against cyberattacks.