Modeling for Cloud

Here you can find the datasets containing the latency measurements we performed in several Cloud Computing platforms. We obtained the data by running multiple instances of our measurement agent in Linux VMs placed in different datacenters within a vendor-specific platform and recording the results. Amazon Web Services (AWS) Between December 2016 and February 2017 we ran a campaign of measurements to analyze the communication latency between software components running in the main datacenters of the Amazon Web Services Cloud Computing platform. More specifically, the dataset contains a set of latency measurements campaigns, which in turn were performed between the following datacenters. Here is the map between the filenames where data related to a single campaign was recorded and the corresponding AWS datacenters: File                           ...

For many applications with inter-datacenter Cloud deployments it is important to rely on an accurate model of delay times across different geolocations. Unfortunately, such a model is currently not available to researchers and practitioners. To fill that gap, we analyzed real-life latency values collected between different Amazon datacenter locations, and propose a novel Gaussian mixture approximation model of the round-trip time distribution based on Relaxed Boxed Approximation (RBA) algorithm. The proposed model can be effectively used for emulation/simulation of cross-Cloud application and service deployments. A Gaussian Mixture Model (GMM) for latency modeling Starting from a dataset of measured RTTs, our solution applies a Gaussian  mixture approximation to estimate the RTT probability density function (PDF):  where t is the RTT expressed in milliseconds; a_i is the amplitude coefficient of the i-th Gaussian component, incorporating the weight w i and varia...