Cloud service providers enable enterprises with the ability to place their business applications into availability zones across multiple locations worldwide. While this capability helps achieve higher availability with smaller failure rates, business applications deployed across these independent zones may experience different quality of service (QoS) due to heterogeneous physical infrastructures. Since the perceived QoS against specific requirements are not usually advertised by cloud providers, selecting an availability zone that would best satisfy the user requirements is a challenge. In this paper, we introduce a predictive approach to identify the cloud availability zone that maximizes satisfaction of an incoming request against a set of requirements. The prediction models are built from historical usage data for each availability zone and are updated as the nature of the zones and requests change. Simulation results show that our method successfully predicts the unpublished zone behavior from historical data and identifies the availability zone that maximizes user satisfaction against specific requirements.

Cloud service providers enable enterprises with the ability to place their business applications into availability zones across multiple locations worldwide. While this capability helps achieve higher availability with smaller failure rates, business applications deployed across these independent zones may experience different Quality of Service (QoS) due to heterogeneous physical infrastructures. Since the perceived QoS against specific requirements are not usually advertised by cloud providers, selecting an availability zone that would best satisfy the user requirements is a challenge. In this paper, we introduce a predictive approach to identify the cloud availability zone that maximizes satisfaction of an incoming request against a set of requirements. The predictive models are built from historical usage data for each availability zone and are updated as the nature of the zones and requests change. Simulation results show that our method successfully predicts the unpublished zone behavior from historical data and identifies the availability zone that maximizes user satisfaction against specific requirements.

We consider the problem of admitting sets of, possibly heterogenous, virtual machines (VMs) with stochastic resource demands onto physical machines (PMs) in a Cloud environment. The objective is to achieve a specified quality-of-service related to the probability of resource over-utilization in an uncertain loading condition, while minimizing the rejection probability of VM requests. We introduce a method which relies on approximating the probability distribution of the total resource demand on PMs and estimating the probability of over-utilization. We compare our method to two simple admission policies: admission based on maximum demand and admission based on average demand. We investigate the efficiency of the results of using our method on a simulated Cloud environment where we analyze the effects of various parameters (commitment factor, coefficient of variation etc.) on the solution for highly variate demands.

In today's complex business environment, applications span across loosely coupled systems generating massive amounts of business artifacts at various levels of granularity. Monitoring and analyzing these artifacts enables access to critical process information to improve the effectiveness of business operations. Tracking, capturing, storing and processing such large volumes of data, however, is difficult and resource intensive with current relational database technologies. Hence, designers are forced to make trade-offs in deciding the type and the granularity level of the data to be captured. Nevertheless, the amount of historical data that carries important insight about the business processes that need to be captured is growing. A solution that is capable of handling massive business provenance data is necessary. In this paper, using cloud as opposed to relational databases to manage this massive amount of business provenance data is proposed and a cloud-based business provenance architecture based on HBase/Hadoop technology is introduced.

The classical definition of knowledge management promises to get the right knowledge to the right people at the right time so they can make the best decision [G. Petrash, 1996]. Autonomic systems, on the other hand, are expected to find and apply the right knowledge for self-managing purposes without human intervention. This article discusses the components to be built around a system to enable self-healing and managing capabilities. These are defined and described in this article as self-knowledge, self-monitoring, self-learning, problem detection, diagnosis, and search and solution components. Interaction of these system components to make knowledge available for self-healing purposes is also discussed.

An emerging application of mobile computing and communication is the delivery of information related to the transportation system to drivers and travelers. Such real-time information would be very valuable in providing services such as pre-trip planning, route guidance, intermodal transportation, yellow pages, and ride matching and reservation. This so-called advanced traveler information system (ATIS) is an important subset of an intelligent transportation system (ITS). The authors are developing an ATIS operational field test called SWIFT (Seattle wide-area information for travelers) in the Seattle metropolitan area which uses technological advances in wireless communication, personal digital assistants (PDA), and traffic modeling and analysis. SWIFT uses an advanced 19 kbps FM subcarrier broadcast medium for the delivery of transportation information as well as personal paging information. Preliminary description of the logical and physical architecture of the SWIFT system along with communication loading analysis for this system, are presented.

The performance of a control (CNTR) and information (INF) frame multiplexer which intermixes control and information traffic by accommodating the relatively short CNTR frames between two consecutive INF frames is investigated. It is shown that the delay performance of one class can be improved at the price of degrading the performance of the other. The delay performance of a transaction between two nodes of the communication subsystem can be improved by selecting the parameters of this multiplexer appropriately. The relative importance of CNTR and INF frame delays for a transaction is determined. The results of a simulation study give insight into the behavior of this multiplexer. Based on these results, it is concluded that if the control traffic intensity is high, or the relative importance of control delay is high, then larger values of gap length improve the performance.

The performance of voice and video services is evaluated for isochronous LANs or systems that have time division multiplexing (TDM) channels with fixed bandwidth for real-time traffic. The isochronous bandwidth resources are shared by voice and video traffic which have different bandwidth requirements. The blocking probabilities for voice and video arrivals are obtained analytically for the case where channels are allocated randomly without using a policy. Two policies for bandwidth allocation of voice and video traffics under various traffic load conditions are evaluated. The simulation results show that substantial improvements can be achieved if efficient allocation policies are used.