Correction to: Deep reinforcement learning for multi-objective placement of virtual machines in cloud datacenters

Caviglione, Luca; Gaggero, Mauro; Paolucci, Massimo; Ronco, Roberto

doi:10.1007/s00500-020-05536-w

Search citation statements

Order By: Relevance

Paper Sections

Select...

Proposed Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

Publication Types

Select...

Preprint1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can also improve the performance by collecting feedback in the form of a scalar reward or penalty. [22]Trial and error search and cumulative reward are the two main pillars of reinforcement learning. It is based on dynamic programming algorithms used to solve optimization issues in problems.…”

Section: Proposed Workmentioning

confidence: 99%

Prevention of DDoS Attack in Cloud Computing using Fuzzy Q – Learning Algorithm

Kumar¹,

Dutta²,

Pranav³

2022

Preprint

View full text Add to dashboard Cite

Cloud computing technology created a revolution in IT Industry that provides on-demand resources, flexibility, scalability, and lower maintenance to infrastructure costs. Distributed Denial of Service (DDoS) attack blocks the services by flooding high or low volume of malicious traffic to exhaust the servers, resources, etc of cloud. In today’s era, they are even difficult to detect because of low rate traffic and its hidden approach in cloud. The study of all DDoS attack with their possible solution is essential to protect cloud computing environment. In this paper, we have proposed a Fuzzy Q Learning algorithm and Chebyshev’s Inequality principle to counter the problem of DDoS attacks. The Proposed framework follows the inclusion of Chebyshew’s inequality for work load prediction in cloud in the analysis phase and fuzzy QLearning in planning phase .Experimental results proves that in our proposed FQBDDA model, prevent DDoS attack.

show abstract

Section: Proposed Workmentioning

confidence: 99%