Batch: Machine learning inference serving on serverless platforms with adaptive batching
Serverless computing is a new pay-per-use cloud service paradigm that automates resource
scaling for stateless functions and can potentially facilitate bursty machine learning serving …
scaling for stateless functions and can potentially facilitate bursty machine learning serving …
ATOM: Model-driven autoscaling for microservices
Microservices based architectures are increasingly widespread in the cloud software
industry. Still, there is a shortage of auto-scaling methods designed to leverage the unique …
industry. Still, there is a shortage of auto-scaling methods designed to leverage the unique …
Characterizing, modeling, and generating workload spikes for stateful services
Evaluating the resiliency of stateful Internet services to significant workload spikes and data
hotspots requires realistic workload traces that are usually very difficult to obtain. A popular …
hotspots requires realistic workload traces that are usually very difficult to obtain. A popular …
Workload generators for web-based systems: Characteristics, current status, and challenges
The growth and evolution of the World Wide Web (WWW) has been rapid over the last ten
years and this has been caused mainly by factors such as the social Web and mobile …
years and this has been caused mainly by factors such as the social Web and mobile …
Energy efficient virtual machines placement over cloud-fog network architecture
Fog computing is an emerging paradigm that aims to improve the efficiency and QoS of
cloud computing by extending the cloud to the edge of the network. This paper develops a …
cloud computing by extending the cloud to the edge of the network. This paper develops a …
Burstiness-aware resource reservation for server consolidation in computing clouds
In computing clouds, burstiness of a virtual machine (VM) workload widely exists in real
applications, where spikes usually occur aperiodically with low frequency and short …
applications, where spikes usually occur aperiodically with low frequency and short …
Sponge: Fast reactive scaling for stream processing with serverless frameworks
Streaming workloads deal with data that is generated in real-time. This data is often
unpredictable and changes rapidly in volume. To deal with these fluctuations, current …
unpredictable and changes rapidly in volume. To deal with these fluctuations, current …
Exploiting VM migration for the automated power and performance management of green cloud computing systems
Cloud computing is an emerging computing paradigm in which “Everything is as a Service”,
including the provision of virtualized computing infrastructures (known as Infrastructure-as-a …
including the provision of virtualized computing infrastructures (known as Infrastructure-as-a …
BURSE: A bursty and self-similar workload generator for cloud computing
J Yin, X Lu, X Zhao, H Chen… - IEEE Transactions on …, 2014 - ieeexplore.ieee.org
As two of the most important characteristics of workloads, burstiness and self-similarity are
gaining more and more attention. Workload generation, which is a key technique for …
gaining more and more attention. Workload generation, which is a key technique for …
Energy-efficient resource management for cloud computing infrastructures
Cloud computing is growing in popularity among computing paradigms for its appealing
property of considering" Everything as a Service". The goal of a Cloud infrastructure provider …
property of considering" Everything as a Service". The goal of a Cloud infrastructure provider …