Scholarlink

<p>In the dynamic realm of renewable energy systems (RES), ensuring strong network security is crucial. This research investigates the integration of machine learning (ML) and blockchain technology to enhance RES network security. Specifically, we employ Federated Learning (FL) combined with blockchain-based smart contracts to create a decentralized, secure system for real-time threat detection and mitigation. FL allows multiple nodes to learn from shared data while preserving privacy and blockchain ensures immutability and transparency. We implement a novel FL algorithm tailored for RES security, trained on distributed datasets to detect anomalies and cyber threats, achieving a Precision of 95%, Recall of 93%, F1-measure of 94%, and the Area Under the Curve (AUC) of 0.97. The blockchain framework provides a tamper-proof log of security events and automated responses via smart contracts, enhancing the security and reliability of the system. Our approach not only strengthens RES network security but also sets a foundation for integrating advanced ML algorithms with blockchain in critical infrastructure. This research presents a cutting-edge solution for RES security, with significant implications for enhancing the safety and dependability of global energy networks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent and Energy-efficient Security Architecture for Renewable Energy Systems Based on Blockchain and Machine Learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月16日

查看全文
  • A. Thilagavathy,
  • C. Balakrishna Moorthy,
  • J. Ramprabu,
  • N. Alangudi Balaji

摘要

In the dynamic realm of renewable energy systems (RES), ensuring strong network security is crucial. This research investigates the integration of machine learning (ML) and blockchain technology to enhance RES network security. Specifically, we employ Federated Learning (FL) combined with blockchain-based smart contracts to create a decentralized, secure system for real-time threat detection and mitigation. FL allows multiple nodes to learn from shared data while preserving privacy and blockchain ensures immutability and transparency. We implement a novel FL algorithm tailored for RES security, trained on distributed datasets to detect anomalies and cyber threats, achieving a Precision of 95%, Recall of 93%, F1-measure of 94%, and the Area Under the Curve (AUC) of 0.97. The blockchain framework provides a tamper-proof log of security events and automated responses via smart contracts, enhancing the security and reliability of the system. Our approach not only strengthens RES network security but also sets a foundation for integrating advanced ML algorithms with blockchain in critical infrastructure. This research presents a cutting-edge solution for RES security, with significant implications for enhancing the safety and dependability of global energy networks.