VoIP Traffic Modelling using Gaussian Mixture Models, Gaussian Processes and Interactive Particle Algorithms

Scientific Conference (2015, December 05)

The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able to understand and predict the structure of traffic over some given period of time. VoIP traffic has a time ... [more ▼]

The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able to understand and predict the structure of traffic over some given period of time. VoIP traffic has a time variant structure, e.g. due to sudden peaks, daily or weekly moving patterns of activities, which in turn makes prediction difficult. Obtaining insights about the structure and trends of traffic has important implications when dealing with the nowadays cloud-deployed VoIP services. Prediction techniques are applied to anticipate the incoming traffic, for an efficient distribution of the traffic in the system and allocation of resources. The article looks in a critical manner at a series of machine learning techniques. We namely compare and review (using real VoIP data) the results obtained when using a Gaussian Mixture Model (GMM), Gaussian Processes (GP), and an evolutionary like Interacting Particle Systems based (sampling) algorithm. The experiments consider different setups as to verify the time variant traffic assumption. [less ▲]

Dynamic MixVoIP

Scientific Conference (2013, July)

Dynamic optimization based on incoming load analysis and prediction is considered to be an innovative approach in order to prevent the overload of the servers in a Voice over IP system. The ongoing ... [more ▼]

Dynamic optimization based on incoming load analysis and prediction is considered to be an innovative approach in order to prevent the overload of the servers in a Voice over IP system. The ongoing project is in an early stage of study and the followings are the current vision and concept regarding it. The information gathered by inspecting the real system of an IT company, MixVoIP, (probe server and sensors spread inside the cloud) and by analyzing the data provided by the predictive algorithm, will be used to optimize load distribution and resource allocation. The implementation in the real-life environment should lead to an improvement of the service offered but also to a sensible reduction of the associated carbon emissions, e.g. as a result of an improved load management, reduced idle CPU times or optimally exploited resources. [less ▲]