Mustafa K. Mehmet Ali

Neural networks for shortest path computation and routing in computer networks

The application of neural networks to the optimum routing problem in packet-switched computer networks, where the goal is to minimize the network-wide average time delay, is addressed. Under appropriate assumptions, the optimum routing algorithm relies heavily on shortest path computations that have to be carried out in real time. For this purpose an efficient neural network shortest path algorithm that is an improved version of previously suggested Hopfield models is proposed. The general principles involved in the design of the proposed neural network are discussed in detail. Its computational power is demonstrated through computer simulations. One of the main features of the proposed model is that it will enable the routing algorithm to be implemented in real time and also to be adaptive to changes in link costs and network topology.

A Performance Modeling of Connectivity in Vehicular Ad Hoc Networks

In this paper, we study the statistical properties of the connectivity of vehicular ad hoc networks (VANETs) with user mobility. It is assumed that the nodes travel along a multilane highway that allows vehicles to pass each other. The nodes arrive at the highway through one of the traffic entry points according to a Poisson process and then travel in the same direction according to a user mobility model until they reach their exit points. The nodes on the highway may be able to communicate with each other. We derive the probability distribution of the node population size on the highway and the nodes location distribution. Then, we determine the mean cluster size and the probability that the nodes will form a single cluster. The analysis of this paper also applies to any path in a network of highways, as well as to two-way traffic. The numerical results show the significance of mobility on the connectivity of VANETs. We also present simulation results that confirm the accuracy of the analysis. The results of this paper may be used to study the routing algorithms, throughput, or delay in VANETs.

A performance analysis of a discrete-time priority queueing system with correlated arrivals

We present performance analysis of a discrete-time system with two priority queues and correlated arrivals. The arrival process to each priority queue consists of the superposition of the traffic generated by independent binary Markov sources with the arrivals to the two queues being independent of one another. The first step is the determination of the busy period of a queue with correlated arrivals. Next, the joint probability generating function of the two queue lengths is derived and the unknown boundary function is determined using the busy period of the high-priority queue. The next step is to determine closed form expressions for the mean and variance of the queue lengths. Finally, the results are extended to multiple priority queueing systems with multiple types of traffic sources. Numerical results that demonstrate the impact of the correlated arrival process in the system are presented.

Performance analysis of cyclic-priority input access method for a multicast switch

A study of the performance of a cyclic-priority input access mechanism for a multicast switch is carried out. The method is a derivative of the ring token reservation method which eliminates the unfairness of the ordinary ring token reservation. It has the further advantage of being simple and easy to implement. The primary performance measurements are the switch throughput and the packet delay. A key assumption is that all copies of the same packet must be switched in the same slot.<<ETX>>

Modeling of the resource allocation in cloud computing centers

Cloud computing offers on-demand network access to the computing resources through virtualization. This paradigm shifts the computer resources to the cloud, which results in cost savings as the users leasing instead of owning these resources. Clouds will also provide power constrained mobile users accessibility to the computing resources. In this paper, we develop performance models of these systems. We assume that jobs arrive to the system according to a Poisson process and they may have quite general service time distributions. Each job may consist of multiple numbers of tasks with each task requiring a virtual machine (VM) for its execution. The size of a job is determined by the number of its tasks, which may be a constant or a variable. The jobs with variable sizes may generate new tasks during their service times. In the case of constant job size, we allow different classes of jobs, with each class being determined through their arrival and service rates and number of tasks in a job. In the variable case a job generates randomly new tasks during its service time. The latter requires dynamic assignment of VMs to a job, which will be needed in providing service to mobile users. We model the systems with both constant and variable size jobs using birth-death processes. In the case of constant job size, we determined joint probability distribution of the number of jobs from each class in the system, job blocking probabilities and distribution of the utilization of resources for systems with both homogeneous and heterogeneous types of VMs. We have also analyzed tradeoffs for turning idle servers off for power saving. In the case of variable job sizes, we have determined distribution of the number of jobs in the system and average service time of a job for systems with both infinite and finite amount of resources. We have presented numerical results and any approximations are verified by simulation. The results of the paper may be used in the dimensioning of cloud computing centers.

Performance analysis of a random packet selection policy for multicast switching

This paper studies a random packet selection policy for multicast switching. An input packet generates a fixed number of primary copies plus a random number of secondary copies. Assuming a constant number of contending packets during a slot, the system is modeled as a discrete time birth process. A difference equation describing the dynamics of this process is derived, the solution of which gives a closed form expression for the distribution of the number of packets chosen. Then this result is extended to the steady state distribution through a Markov chain analysis. It is shown that the old packets have larger fanout than the fresh packets and the copy distribution of the mixed packets is determined. The packet and copy throughput taking into account the old packets have been obtained. We determined the mean packet delay as well as an upperbound for packet loss probabilities for finite buffer sizes. The asymptotic distribution of the number of packets is also given for large switch sizes under saturation by applying results from the renewal theory. Finally, simulations are done to determine the performance of the switch under mixed (unicast plus multicast) traffic.

A Performance Modeling of Vehicular Ad Hoc Networks (VANETs)

In this paper, we study the statistical properties of the connectivity of vehicular ad hoc networks (VANETs) with user mobility at the steady state. It is assumed that the nodes travel along a single dimensional strip with finite length. The nodes arrive at the service strip through one of the traffic entry points following a Poisson process and move along the strip in the same direction according to a user mobility model until they reach their exit point. The service strip allows the users with different speeds to pass each other. The nodes, which are within the service strip, are able to participate in communications. We derive the probability distribution of the user population size within the service strip and nodes location distribution. Then, we determine the mean cluster size, fraction of nodes within the cluster and probability that nodes will form a single cluster. This work shows significance of mobility on the connectivity of ad hoc networks. The results of the paper may be used to avoid traffic congestion in the highways.

The performance analysis of an input access scheme in a high-speed packet switch

The performance analysis of an input access scheme in a high-speed packet switch for broadband ISDN is presented. In this switch, each input maintains a separate queue for each of the outputs, thus there are n/sup 2/ input queues in a (n*n) switch. Using synchronous operation, at most one packet per input and output will be transferred in any slot. The choice of the packets is done in a manner to maximize the throughput of the switch. Comparison of simulations with analytically derived upper and lower bounds show close to optimal throughput. The mean packet delay is also derived and its variance is bounded. This input access scheme may be implemented using neural networks.<<ETX>>

Optimal multi-dimensional dynamic resource allocation in mobile cloud computing

In this paper, we propose a model for mobile application profiles, wireless interfaces, and cloud resources. First, an algorithm to allocate wireless interfaces and cloud resources has been introduced. The proposed model is based on the wireless network cloud (WNC) concept. Then, considering power consumption, application quality of service (QoS) profiles, and corresponding cost functions, a multi-objective optimization approach using an event-based finite state model and dynamic constraint programming method has been used to determine the appropriate transmission power, process power, cloud offloading and optimum QoS profiles. Numerical results show that the proposed algorithm saves the mobile battery life and guarantees both QoS and cost simultaneously. Moreover, it determines the best available cloud server resources and wireless interfaces for applications at the same time.

Generalized Performance Modeling of Vehicular Ad Hoc Networks (VANETs)

In this paper, we study the statistical properties of the connectivity of VANETs with user mobility at the steady state. We assume a network of highways with arbitrary topology. The nodes arrive at the network through one of the traffic entry points following a Poisson process and move within the network according to a mobility model. The path of a node within the network is determined through a routing matrix. The system is modeled as a BCMP network of queues. We derive the probability distribution of the node population size within the network. Then, we determine the probability distribution of the cluster size seen by a new node arriving along a path. The presented numericals results illustrate the effect of mobility on connectivity. The results of the paper may be used to study the routing algorithms, throughput or delay in VANETs.