Bayesian Service Demand Estimation with Gibbs Sampling

Provided by: Imperial College London
Topic: Big Data
Format: PDF
Performance modeling of web applications involves the task of estimating service demands of requests at physical resources, such as CPUs. In this paper, the authors propose a service demand estimation algorithm based on a Markov Chain Monte Carlo (MCMC) technique, Gibbs sampling. Their methodology is widely applicable as it requires only queue length samples at each resource, which are simple to measure. Additionally, since they use a Bayesian approach, their method can use prior information on the distribution of parameters, a feature not available with existing demand estimation approaches.

Find By Topic