I. A. Saroit Ismail

Bio: I. A. Saroit Ismail is an academic researcher. The author has contributed to research in topics: Dynamic bandwidth allocation & Bandwidth throttling. The author has an hindex of 1, co-authored 1 publications receiving 10 citations.

Bandwidth problems in high-speed networks

Abstract: High-speed networks are capable of carrying many types of services such as voice, data, images, and video. These services have different requirements in terms of bandwidth, cell loss, delay, etc. The goal is to maximize the quality of service offered during periods of stress, as viewed by both the network provider and the customer. Many problems are created by these different requirements. This paper illustrates four bandwidth problems in high-speed networks, then describes several solutions to them. The first problem is topology design and bandwidth allocation, and it is concerned with the ability to dynamically reconfigure a network in order to efficiently benefit from network resources. The second problem is concerned with flow control and congestion avoidance. Bandwidth management (BWM) protocols are used to prevent congestion, essentially by accepting or refusing a new-arrival cell. The third problem, which is the most critical one, is bandwidth allocation, which is concerned with successful integration of link capacities through the different types of services. Given that a virtual path is a logical direct link, composed of a number of virtual circuits, between any two nodes, the last problem is concerned with how to assign bandwidth to each virtual path in the network, in order to optimize performance for all users. This paper may be a good guide to researchers concerned with high-speed networks in general.

Integration of ATM call admission control and link capacity control by distributed neural networks

Abstract: An adaptive call admission control using neural networks was recently proposed for asynchronous transfer mode (ATM) communications networks. The author proposes adaptive link capacity control using neural networks. Neural networks are trained to estimate the call loss rate from link capacity and observed traffic, and link capacity assignment is optimized by a random optimization method according to the estimated call loss rate. The integration of adaptive call admission control and adaptive link capacity control yields an efficient ATM traffic control system suitable for multimedia communication services with unknown traffic characteristics. Computer simulation results using a simple network model are also given to evaluate the accuracy and efficiency of the proposed method. >

Method and apparatus for token distribution

Abstract: A method and apparatus for token distribution include providing one or more nodes of a plurality of network nodes with a token machine that includes counters associated with each of other network nodes having a token machine. Each time a token possessing network node implicitly or explicitly passes the token to another network node having a token machine, counter values of each of the counters associated with each node having a token machine are adjusted. When a token is passed, the counter value of the receiving node is adjusted based, at least in part, on an initial token interval value, and counter values associated with other nodes are adjusted toward a threshold value. The decision as to where the token is passed may be based, at least in part, on the value of a counter and/or an assigned counter priority level. The system or method also may include priority slots in which the token is unconditionally passed to a node assigned the priority slot, and an ARQ scheme for acknowledgment of transferred information.

Capacity Assignment in Bluetooth Scatternets - Analysis and Algorithms

Abstract: Bluetooth enables portable electronic devices to communicate wirelessly via short-range ad-hoc networks. Initially Bluetooth will be used as a replacement for point-to-(multi)point cables. However, in due course, there will be a need for forming multihop ad-hoc networks over Bluetooth, referred to as scatternets. This paper investigates the capacity assignment problem in Bluetooth scatternets. The problem arises primarily from the special characteristics of the network and its solution requires new protocols. We formulate it as a problem of minimizing a convex function over a polytope contained in the matching polytope. Then, we develop an optimal algorithm which is similar to the well-known flow deviation algorithm and that calls for solving a maximum-weight matching problem at each iteration. Finally, a heuristic algorithm with a relatively low complexity is developed.

Agent-based subsystem for multimedia communications

Abstract: There are several issues in multimedia communications, such as resource allocation, quality-of-service (QoS) routing, synchronisation, playout compensation and so on, which affect the continuous and smooth running of a multimedia application. The Internet demands the design of flexible and adaptable multimedia services so as to offer better quality presentations to the user. In this context, agent technology is emerging as a promising solution to provide flexible and adaptable services in distributed environments. The authors propose a subsystem called Protocol Engineering and Technology unit – Agent-based Subsystem for Multimedia Communications (PET-ASMAC) at the client side, which is an intelligent multimedia communication assistant to facilitate multimedia presentation to Internet users. The PETASMAC comprises a set of static and mobile agents, which perform certain autonomous tasks (QoS routing, resource allocation, synchronisation and playout) that satisfy the full-service requirements of an application, and coordinate with each other to provide smooth and continuous multimedia presentations. PET-ASMAC is simulated in several network scenarios to evaluate its effectiveness. The subsystem considers presentations from a single server to a client. However, it can be easily extended for multipoint-to-point communication. The results are encouraging and the observed benefits of the agent technology in multimedia communications are flexibility, adaptability, customisability, maintainability, re-usability and support to component-based software engineering.

Adaptive bandwidth reservation scheme for multimedia traffic using mobile agents

Abstract: The bandwidth reservation for multimedia traffic poses technical challenges due to the bursty and delay sensitive nature of applications. The objectives of bandwidth reservation schemes are: optimize network utilization, and minimize the packet losses and delays. The growth of multimedia services on the Internet and the possible discovery of programmable networks has made us investigate new techniques for resolving bandwidth issues in multimedia communication. Mobile agent technology seems to be a promising solution for network management and QoS control. In this paper, we consider joint problems of adaptive bandwidth reservation and link rearrangement (rerouting) for multimedia traffic under the event of congestion/failures of link, and propose a mobile agent based approach to achieve these objectives. The scheme is simulated using a multimedia traffic model. Simulation results show that the use of agents increases the network utilization, acceptance ratio of applications, flexibility and efficiency of bandwidth reservation. The flexibility in using agent technology is that the policies can be changed and implemented easily by encoding in the agents.