Volume 11, Number 6

Maintaining Cloud Performance under DDOS Attacks


Moataz H. Khalil1, 2, Mohamed Azab2, Ashraf Elsayed3, Walaa Sheta1, 2, Mahmoud Gabr3 and Adel S. Elmaghraby1, 2, 1University of Louisville, USA, 2The City of Scientific Research and Technology Applications, Egypt and
3Alexandria University, Egypt


The popularity of cloud computing has been growing where the cloud became an attractive alternative rather than classic information processing system. The distributed denial of service (DDoS) attack is one of the famous attacks to cloud computing. This paper proposes a Multiple Layer Defense (MLD) scheme to detect and mitigate DDoS attacks which due to resource depletion. The MLD consists of two layers. The first layer has an alarm system send alarms to cloud management when DDoS attacks start. The second layer includes an anomaly detection system detects VM is infected by DDoS attacks. Also,MLD tested with a different DDoS attack ratio to show scheme stability. MLD evaluated by The energy consumption and the overall SLA violations. The results show the great effect of the MLD to reduce the energy consumption and the overall SLA violation for all datasets. Also, the MLD shows acceptable stability and reactivity with different DDoS attack ratio.


Cloud Computing, Energy consumption, Service Level Agreement, DDoS attack, anomaly detection, Availability.