Adaptive SLA-based elasticity management algorithms for a virtualized IP multimedia subsystem

Nemati, Hani; Singhvi, Arjun; Kara, Nadjia; Barachi, May El

doi:10.1109/glocomw.2014.7063377

Cited by 16 publications

(8 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similar to the approach used in [23], the detected face is normalized to an image of size 200 × 200 pixels. The location of each face is identified by a square using the 15 facial features and reference points that are illustrated in Table 1.…”

Section: A Faces' Location and Reference Pointsmentioning

confidence: 99%

A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events

Mathew

Alkhatib

Barachi

2021

JCOMSS

View full text Add to dashboard Cite

Smart city analytics requires the harnessing and analysis of emotions and sentiments conveyed by images and video footage. In recent years, facial sentiment analysis attracted significant attention for different application areas, including marketing, gaming, political analytics, healthcare, and human computer interaction. Aiming at contributing to this area, we propose a deep learning model enabling the accurate emotion analysis of crowded scenes containing complete and partially occluded faces, with different angles, various distances from the camera, and varying resolutions. Our model consists of a sophisticated convolutional neural network (CNN) that is combined with pooling, densifying, flattening, and Softmax layers to achieve accurate sentiment and emotion analysis of facial images. The proposed model was successfully tested using 3,750 images containing 22,563 faces, collected from a large consumer electronics trade show. The model was able to correctly classify the test images which contained faces with different angles, distances, occlusion areas, facial orientation and resolutions. It achieved an average accuracy of 90.6% when distinguishing between seven emotions (Happiness, smiling, laughter, neutral, sadness, anger, and surprise) in complete faces, and 86.16% accuracy in partially occluded faces. Such model can be leveraged for the automatic analysis of attendees' engagement level in events. Furthermore, it can open the door for many useful applications in smart cities, such as measuring employees' satisfaction and citizens' happiness.

show abstract

Section: A Faces' Location and Reference Pointsmentioning

confidence: 99%

A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events

Mathew

Alkhatib

Barachi

2021

JCOMSS

View full text Add to dashboard Cite

show abstract

“…An adaptive SLA-based elasticity method has been proposed in [8]. In their method, the IMS network Call Setup Delay is being used as an end-to-end metric to scale up and scale down the number of CPU cores and their frequency.…”

Section: Related Workmentioning

confidence: 99%

VM processes state detection by hypervisor tracing

Nemati

Dagenais

2018

2018 Annual IEEE International Systems Conference (SysCon)

Self Cite

View full text Add to dashboard Cite

The diagnosis of performance issues in cloud environments is a challenging problem, due to the different levels of virtualization, the diversity of applications and their interactions on the same physical host. Moreover, because of privacy, security, ease of deployment and execution overhead, an agent-less method, which limits its data collection to the physical host level, is often the only acceptable solution.In this paper, a precise host-based method, to recover wait state for the processes inside a given Virtual Machine (VM), is proposed. The virtual Process State Detection (vPSD) algorithm computes the state of processes through host kernel tracing. The state of a virtual Process (vProcess) is displayed in an interactive trace viewer (Trace Compass) for further inspection. Our proposed VM trace analysis algorithm has been opensourced for further enhancements and for the benefit of other developers. Experimental evaluations were conducted using a mix of workload types (CPU, Disk, and Network), with different applications like Hadoop, MySQL, and Apache. vPSD, being based on host hypervisor tracing, brings a lower overhead (around 0.03%) as compared to other approaches.

show abstract

“…In their approach, VMs and the Host hypervisor should be traced, which adds more overhead. An adaptive SLA-based elasticity method has been proposed in [12]. In their method, an end-to-end metric is used to scale up and scale down the resources.…”

Section: Related Workmentioning

confidence: 99%

Wait analysis of virtual machines using host kernel tracing

Nemati

Bastieny

Dagenaisz

2018

2018 IEEE International Conference on Consumer Electronics (ICCE)

Self Cite

View full text Add to dashboard Cite

An agent-less method to understand virtual machines (VMs) behavior its evolution during the VM life-cycle is an essential task for IaaS provider. It allows the IaaS provider to better scale the VMs resources by properly allocating the physical resources. On the other hand, because of privacy, security, ease of deployment and execution overhead issues, the method presented limits its data collection to the physical host level, without internal access to the VMs.We propose a host-based, precise method to recover wait states for the virtual CPUs (vCPUs) of a given VM. The Wait Analysis Algorithm (W2A) computes the state of vCPUs through the host kernel trace. The state of vCPUs is displayed in an interactive trace viewer (TraceCompass) for further inspection. Our proposed VM trace analysis algorithm has been open-sourced for further enhancements and to the benefit of other developers. Our new technique is being evaluated with representative workloads, generated by different benchmarking tools. These approaches are based on host hypervisor tracing, which brings a lower overhead (around 0.03%) as compared to other approaches.

show abstract

Adaptive SLA-based elasticity management algorithms for a virtualized IP multimedia subsystem

Cited by 16 publications

References 6 publications

A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events

A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events

VM processes state detection by hypervisor tracing

Wait analysis of virtual machines using host kernel tracing

Contact Info

Product

Resources

About