A genetic approach to Markovian characterisation of H.264 scalable video

Abstract

We propose an algorithm for multivariate Markovian characterisation of H.264/SVC scalable video traces at the sub-GoP (Group of Pictures) level. A genetic algorithm yields Markov models with limited state space that accurately capture temporal and inter-layer correlation. Key to our approach is the covariance-based fitness function. In comparison with the classical Expectation Maximisation algorithm, ours is capable of matching the second order statistics more accurately at the cost of less accuracy in matching the histograms of the trace. Moreover, a simulation study shows that our approach outperforms Expectation Maximisation in predicting performance of video streaming in various networking scenarios.

Performance analysis of a decoupling stock in a Make-to-Order system

“…To model the burstiness in the arrival process of the semifinished products, we replace the Poisson processes by a Markovian arrival process (Buchholz et al, 2010;Fiems et al, 2011). We here limit the presentation to interrupted Poisson processes, but the methodology easily extends to general Markovian arrival processes.…”

“…In contrast, no such assumption is imposed on the queue of backlogged orders. As in (De Cuypere and Fiems, 2011), we study the decoupling stock in a Markovian environment. This allows for studying the effect of variability in the production process on the performance of the decoupling stock.…”

Performance Evaluation of a Kitting Process

“…To account for burstiness in the arrival process of the parts in the different queues, the modulating chain allows to mitigate Poissonian arrival assumptions: We can replace the Poisson processes by a two-class Markovian arrival processes. Multi-class Markovian arrival processes allow for intricate correlation and can be efficiently characterised from trace data [3,4]. As we have two types of arrivals, the Markovian arrival process is described by the generator matrix Λ 1 of transitions with arrivals in queue 1, the generator matrix Λ 2 with arrivals in queue 2 and the generator matrix Λ 0 without arrivals.…”

Statistical QoS guarantee for wireless multi-homing video transmission

“…The frame size PMF is the same given the frame type (I, P, or B) across different GoPs. The PMF, f C f (c f ), can be calculated for different video contents and frame types as in [18]. The frame size, C f , for I, P, or B frames is constant within one time slot and varies from one time slot to another.…”