Hamzeh Khazaei

Performance Analysis of Cloud Computing Centers Using M/G/m/m+r Queuing Systems

Successful development of cloud computing paradigm necessitates accurate performance evaluation of cloud data centers. As exact modeling of cloud centers is not feasible due to the nature of cloud centers and diversity of user requests, we describe a novel approximate analytical model for performance evaluation of cloud server farms and solve it to obtain accurate estimation of the complete probability distribution of the request response time and other important performance indicators. The model allows cloud operators to determine the relationship between the number of servers and input buffer size, on one side, and the performance indicators such as mean number of tasks in the system, blocking probability, and probability that a task will obtain immediate service, on the other.

A Fine-Grained Performance Model of Cloud Computing Centers

Accurate performance evaluation of cloud computing resources is a necessary prerequisite for ensuring that quality of service parameters remain within agreed limits. In this paper, we employ both the analytical and simulation modeling to addresses the complexity of cloud computing systems. Analytical model is comprised of distinct functional submodels, the results of which are combined in an iterative manner to obtain the solution with required accuracy. Our models incorporate the important features of cloud centers such as batch arrival of user requests, resource virtualization, and realistic servicing steps, to obtain important performance metrics such as task blocking probability and total waiting time incurred on user requests. Also, our results reveal important insights for capacity planning to control delay of servicing users requests.

Performance analysis of IEEE 802.15.6 under saturation condition and error-prone channel

Due to lack of an appropriate wireless technology which satisfies all the requirements of Wireless Body Area Networks (WBANs) the IEEE 802.15.6 Task Group introduced the IEEE 802.15.6 communication standard optimized for low power devices and operation on, in or around the human body. In this work we develop an analytical model for performance evaluation of an IEEE 802.15.6-based WBAN under saturation condition and error prone channel. We model the backoff procedure as specified in the standard employing a probabilistic approach. We validate results of the analytical model with a simulation model. Our results indicate that under saturation condition the medium is mostly utilized by the nodes with highest priority while other user priorities are starving.

Analysis of a Pool Management Scheme for Cloud Computing Centers

In this paper, we propose an analytical performance model that addresses the complexity of cloud centers through distinct stochastic submodels, the results of which are integrated to obtain the overall solution. Our model incorporates the important aspects of cloud centers such as pool management, compound requests (i.e., a set of requests submitted by one user simultaneously), resource virtualization and realistic servicing steps. In this manner, we obtain not only a detailed assessment of cloud center performance, but also clear insights into equilibrium arrangement and capacity planning that allows servicing delays, task rejection probability, and power consumption to be kept under control.

IEEE 802.15.6 under saturation: Some problems to be expected

Because currently available wireless technologies are not appropriate for wireless body area networks (WBANs), the IEEE 802.15.6 standard was introduced by the IEEE 802.15.6 Task Group to satisfy all the requirements for a monitoring system that operates on, in, or around the human body. In this work, we develop an analytical model for evaluating the performance of an IEEE 802.15.6-based WBAN under saturation condition and a noisy channel. We employ a three-dimensional Markov chain to model the backoff procedure as specified in the standard. Probability generating functions (PGFs) are used to compute the performance descriptors of the network. The results obtained from the analytical model are validated by simulation results. Our results indicate that under saturation condition, the medium is accessed by the highest user priority nodes at the vast majority of time while the other nodes are starving.

Performance of Cloud Centers with High Degree of Virtualization under Batch Task Arrivals

In this paper, we evaluate the performance of cloud centers with high degree of virtualization and Poisson batch task arrivals. To this end, we develop an analytical model and validate it with an independent simulation model. Task service times are modeled with a general probability distribution, but the model also accounts for the deterioration of performance due to the workload at each node. The model allows for calculation of important performance indicators such as mean response time, waiting time in the queue, queue length, blocking probability, probability of immediate service, and probability distribution of the number of tasks in the system. Furthermore, we show that the performance of a cloud center may be improved if incoming requests are partitioned on the basis of the coefficient of variation of service time and batch size.

Modelling of Cloud Computing Centers Using M/G/m Queues

Cloud computing is a new computing paradigm, whereby shared resources such as infrastructure, hardware platform, and software applications are provided to users on-demand over the internet (Cloud) as services. Successful provision of infrastructure-as-a-service (IaaS) and, consequently, widespread adoption of cloud computing necessitates accurate performance evaluation that allows service providers to dimension their resources in order to fulfil the service level agreements with their customers. In this paper, we describe an analytical model for performance evaluation of cloud server farms, and demonstrate the manner in which important performance indicators such as request response time and number of tasks in the system may be assessed with sufficient accuracy.

Performance Analysis of Cloud Centers under Burst Arrivals and Total Rejection Policy

Quality of service, QoS, has a great impact on wider adoption of cloud computing. Maintaining the QoS at an acceptable level for cloud users requires an accurate and well adapted performance analysis approach. In this paper, we describe a new approximate analytical model for performance evaluation of cloud server farms under burst arrivals and solve it to obtain important performance indicators such as mean request response time, blocking probability, probability of immediate service and probability distribution of number of tasks in the system. This model allows cloud operators to tune the parameters such as the number of servers and/or burst size, on one side, and the values of blocking probability and probability that a task request will obtain immediate service, on the other.

Availability analysis of cloud computing centers

Accurate availability and performance analysis are important requirements to guarantee quality of services (QoS) for cloud users. In this paper, we integrate an availability model in overall analytical sub-models of cloud system. Each sub-model captures a specific aspect of cloud centers. The key performance metrics such as task blocking probability and total delay incurred on user tasks are obtained. Our results can be used by an admission control to prevent the cloud center from entering unstable regime of operation. The results also reveal practical insights into capacity planning for cloud computing centers.

An intrusion detection system for smart grid neighborhood area network

Smart grid is expected to improve the efficiency, reliability and economics of current energy systems. Using two-way flow of electricity and information, smart grid builds an automated, highly distributed energy delivery network. In this paper, we present the requirements for intrusion detection systems (IDSs) in neighborhood area network (NAN) as a component of smart grid. We propose an IDS that is implemented in a distributed fashion with respect to NANs communication and computation needs. An analytical approach is employed for detecting Wormhole attacks. We validate our NAN IDS scheme using OPNET Modeler [1]. The analytical part of the solution is developed in Maple [2] and integrated with OPNET.