DDoS Traffic Modeling, Identification and Attack Mitigation to Cloud Hosted servers by Drift plus Penalty methods

Abstract

During DDoS attack to a cloud hosted server, to counter the attack, more resources should be assigned to it. In this paper we first develop a mathematical formula for input packet rate during DDoS attack, and propose a method to identify the botnet that created the attack. We introduce two algorithms for resource assignments to protect cloud hosted servers. The drift plus penalty algorithm minimizes the average cost of resource assignment, and stabilizes the queue size. The modified version of this algorithm is drift plus extended penalty, which minimizes the average cost and compensate penalty function by considering delay.

Keywords

• ddos generated traffic modeling
• cloud computing
• drift plus penalty
• drift plus extended penalty
• dynamic resource allocation