MACAD – Machine-Assisted Anomaly Detection for Cybersecurity in Distributed Control Systems (DCS) Within Power Generation
保存先:
| 出版年: | ProQuest Dissertations and Theses (2025) |
|---|---|
| 第一著者: | |
| 出版事項: |
ProQuest Dissertations & Theses
|
| 主題: | |
| オンライン･アクセス: | Citation/Abstract Full Text - PDF |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 抄録: | Due to the rapid evolution of cyber threats, advanced anomaly detection mechanisms are crucial for Industrial Control Systems (ICS), especially in Distributed Control System (DCS) networks. This work examines the use of Machine-to-Machine (M2M) communication for real-time anomaly detection in power generation facilities, with a focus on cyberattack diagnostics based on baseline behavior and deviation. The connection of DCS with Programmable Logic Controllers (PLCs) in large-scale energy building systems presents numerous research opportunities but also introduces new operational and security challenges when integrating various energy generation systems. This work highlights cybersecurity weaknesses within ICS and the resulting exploitability caused by fundamental vulnerabilities in PLC systems. To address these challenges, research presents the Machine-assisted Anomaly Cybersecurity Assessment (MACAD) for DCS and PLC-based multi-network infrastructures (MACAD) architecture. This innovative framework combines logical rules and policy violations with a detection model capable of identifying more complex breaches and responding flexibly to increasingly sophisticated threats. By integrating cybersecurity intelligence with the control layer, MACAD embodies the secure-by-design principle in the cyber-physical security of Distributed Energy Systems (DES), addressing key limitations of existing cybersecurity schemes for ICS. |
|---|---|
| ISBN: | 9798290963860 |
| ソース: | ProQuest Dissertations & Theses Global |