Israel Cidon

In high-speed networks it is desirable to interleave routing and resource (such as bandwidth) reservation. The PNNI standard for private ATM networks is an example of an algorithm that does this using a sequential crank-back mechanism. We suggest the implementation of resource reservation along several routes in parallel. We present an analytical model that demonstrates that when there are several

Modern high speed networks (and ATM networks in particular) use resource reservation as a basic means of establishing communications. One-way on-the-fly reservation is a method for allocating resources for short bursts of data when regular reservation is too costly. The first such algorithms were recently suggested by Turner. We investigate two examples that are characteristic to the way traffic streams

TechLAN is a cheap high-speed ATM network being developed at the Computer Networks Laboratory in the Department of Electrical Engineering at the Technion. Its purpose is twofold; to provide a low cost solution to sharing an ATM switch connection among several ATM users, and to serve as a LAN which provides local interconnection between ATM users without interfering with the

Those who cannot remember the past, are condemned to repeat it." (Philosopher George Santayana) In this paper we show that keeping track of history enables significant improvements in the communication complexity of dynamic networks protocols. We improve the communication complexity for solving any graph problem from \Theta(E) to \Theta(V ), thus achieving the lower bound. Moreover, O(V ) is also our amortized complexity of solving any function (not only graph functions) defined on the local inputs of the nodes. This proves, for the first time, that amortized communication complexity, i.e. incremental cost of adapting to a single topology change, can be smaller than the communication complexity of solving the problem from scratch. This also has a practical importance: in real networks the topology and the local inputs of the nodes change.

In this paper, we show that keeping track of history enables significant improvements in the communication complexity of dynamic network protocols. We present a communication optimal maintenance of a spanning tree in a dynamic network. The amortized (on the number of topological changes) message complexity is O(V), where V is the number of nodes in the network. The message size used by the algorithm is O(log |ID|) where |ID | is the size of the name space of the nodes. Typically, log |ID | = O(log V). Previous algorithms that adapt to dynamic networks involved Ω(E) messages per topological change—inherently paying for re-computation of the tree from scratch. Spanning trees are essential components in many distributed algorithms. Some examples include broadcast (dissemination of messages to all network nodes), multicast, reset (general adaptation of static algorithms to dynamic networks), routing, termination detection, and more. Thus, our efficient maintenance of a spanning tree imp...

Broadcast networks are often used in modern communication systems. A common broadcast network is a single hop shared media system, where a transmitted message is heard by all neighbors, such as some LAN networks. In this work we consider a more complex environment, in which a transmitted message is heard only by a group of neighbors, such as Ad-Hoc networks, satellite and radio networks, as well as wireless multistation backbone system for mobile communication. It is important to design efficient algorithms for such environments. Our main result is a new Leader Election algorithm, with O(n) time complexity and O(n*lg(n)) message transmission complexity. Our distributed solution uses a propagation of information with feedback (PIF) building block tuned to the broadcast media, and a special counting and joining approach for the election procedure phase. The latter is required for achieving the linear time. It is demonstrated that the broadcast model requires solutions which are differ...

WebGL is a browser feature that enables JavaScript-based control of the graphics processing unit (GPU) to render interactive 3D and 2D graphics, without the use of plug-ins. Exploiting WebGL for attacks will affect billions of users since browsers serve as the main interaction mechanism with the world wide web. This paper explores the potential threats derived from the recent move by browsers from WebGL 1.0 to the more powerful WebGL 2.0. We focus on two possible abuses of this feature: distributed password cracking and distributed cryptocurrency mining. Our evaluation of the attacks also includes the practical aspects of successful attacks, such as stealthiness and user-experience. Considering the danger of WebGL abuse, as observed in the experiments, we designed and evaluated a proactive defense. We implemented a Chrome extension that proved itself effective in detecting and blocking WebGL. We demonstrate in our experiments the major improvements of WebGL 2.0 over WebGL 1.0 both i...

In this paper we present a new model for routing that occurs in high-speed ATM networks. Within this model we define a general routing problem, called a virtual path layout. Given a network of nodes (switches) and links, one must find a set of paths in the network, termed the virtual path layout, whereby each pair of nodes may connect using a route that is a concatenation of a small number of virtual paths and is also short in terms of the network links it traverses. Each such layout implies a utilization of the routing tables in the network''s nodes. Our goal is to find a layout that minimizes this utilization, assuming that each such node has a central routing table. We prove that this problem is NP-complete, and consequently focus on a simpler problem, in which it is required to connect all nodes to a single switch. Next, we prove that even this problem is NP-complete, and restrict some of the assumptions to yield a practical subproblem, for which we present a polynomial-...

The emerging hybrid cloud architecture allows organizations to optimize their computation needs and costs by maintaining their private computational infrastructure at high utilization and meeting peak requirements by offloading selected tasks to the public cloud. Consequently, there is a need to devise efficient systems equipped with online task cloudbursting algorithms that optimize the overall cost while maintaining adequate quality of service. Such algorithms must take into account the difference in communication and computational requirements associated with different tasks. For example, it is clear that when two tasks have the same local computational requirements, the one with the lower cloudbursting cost is a better candidate to be off-loaded and sent to the cloud. In this paper, we address the case in which arriving tasks have the same computational cost but different communication costs. We design scheduling system based on online decision algorithms driven by the user'...

ABSTRACT Ring network architectures that employ spatial reuse permit concurrent transmissions of messages over different links. While spatial reuse increases network throughput, it may also cause starvation of nodes. To alleviate this problem, various policies have been suggested in the literature. In this paper we concentrate on a class of such policies that achieve fairness by allocating transmission quotas to nodes. For such policies, weprovide mechanisms for improving delays and increasing overall throughput without compromising fairness.

In many communication systems, the stronger of two or more overlapping packets might capture the receiver and thus be received without error. The effect of capture on collision-resolution algorithms in a slotted ALOHA type broadcasting network is investigated here. Extensions to the algorithms are suggested for both the situations in which the receiver can or cannot distinguish between success slots and capture slots. In particular, we present a class of retransmission schemes for packets that have been transmitted during capture slots but have not been received correctly. The performance analysis is confined to a simplified model in which the nodes of the network are divided into two groups and only packets sent by the nodes of one of them might be captured. For this simplified model and for each extended algorithm, explicit recursive equations are given, from which the average conditional collision-resolution interval length, as well as the maximal throughput, can be determined. As expected, we show that in the presence of capture, the performance of the network is improved and the maximal attainable throughput is increased. Extensions of the simplified model such as dividing the nodes into K groups instead of two, or considering the situation that capture depends on relative distances and transmission powers, are also discussed. For the latter situation we give simulation results.

The delivery of multimedia information over networks requires expensive high bandwidth capacity as well as fast and high storage servers. This motivates the multimedia providers to optimize the delivery distances, as well as, to optimize the electronic content allocation. In this paper we propose an algorithm for finding the optimal allocation of electronic content in a tree oriented distributed network (Such as, CATV-Tree). The proposed algorithm finds the optimal location of an electronic content over the distributed network, such that the cost of storage (storing electronic content in servers) plus the communication cost (transferring electronic content over the network to the end-users) is minimized. The algorithm is distributed, and each node requires a limited memory capacity and computation...

Ring network architectures that employ spatial reuse permit concurrent transmissions of messages over different links. While spatial reuse increases network throughput, it may also cause starvation of nodes. To alleviate this problem, various policies have been suggested in the literature. In this paper we concentrate on a class of such policies that achieve fairness by allocating transmission quotas to nodes. For such policies, weprovide mechanisms for improving delays and increasing overall throughput without compromising fairness.

It is pointed out that the high speed of communication links and the altered nature of carried traffic has considerably affected the design and implementation of packet switched networks. The authors explore the effect on the control procedures within the network, specifically focusing on the lessons learned from the prototype PARIS network. The key design philosophy for both the steady-state control and the connection control is described. It is believed that most of the conclusions are general and can be applied to any network, including ATM (asynchronous transfer mode)-based systems

We present QMesh, a software package that allows utilizing multiple geographically scat- tered Windows desktops as a wireless mesh network infrastructure with seamless user mobility support. QMesh supports its users through standard protocols, and does not require any client software installation. We optimize the solution's quality of service (QoS) by providing a cen- tralized management infrastructure, which allows an assignment of users to Internet gateways that balances between distance and load considerations. QMesh is implemented as a Windows XP kernel driver, on top of the Mesh Connectivity Layer (MCL) toolkit from Microsoft Research that provides basic routing within the mesh. To the best of our knowledge, this is the first mobile mesh solution implemented within the Win32 kernel space.

... Yigal Bejerano Israel Cidony Department of Electrical Engineering Technion - Israel Institute of Technology Haifa 32000, Israel Joseph (Se ) Naorz Bell Laboratories, Lucent Technologies 600 Mountain Ave., Murray Hill, NJ 07974. ABSTRACT ...

It is pointed out that the high speed of communication links and the altered nature of carried traffic has considerably affected the design and implementation of packet switched networks. The authors explore the effect on the control procedures within the network, specifically focusing on the lessons learned from the prototype PARIS network. The key design philosophy for both the steady-state control and the connection control is described. It is believed that most of the conclusions are general and can be applied to any network, including ATM (asynchronous transfer mode)-based systems

ATM networks will soon be moving from the experimental stage of test-beds to a commercial state where production networks are deployed and operated. The progress of ATM networks appears to be at risk due to the lack of a universal, open, and efficient ATM network control platform. The emerging Private Network to Network Interface (PNNI) standard introduces a control platform that can be used as an internetwork and possibly as an intra-network solution. However, the current PNNI still falls short in providing an acceptable universal solution, due to lack of performance optimizations for intra-network operation, limited functionality, and the lack of open interfaces for future functional extensions and services. PENET is a common portable, open, and high-performance network control platform based on performance and functional enhancements to the PNNI standard. It is vendor-independent, scalable (in terms of network size and volume of calls), high-performance (in terms of call processing latency and throughput), and extensible (in terms of integrating customer-specific and value-added services). OPENET is designed as an extension to current PNNI so it can serve as a next generation PNNI. It is compatible with PNNI in the internetworking environment allowing large networks to be partitioned according to natural topological or organizational boundaries rather than the artificial use of internetwork interfaces at vendor boundaries. This report describes the OPENET architecture. The major novelties of the OPENET architecture compared to the current PNNI are: the use of native ATM switching for the dissemination of utilization updates; lightweight call setup; take down and modification signaling; a new signaling paradigm that better supports fast reservation and multicast services; and a rich signaling infrastructure that enables the development of augmented services (such as mobility, directory, etc.), leveraging the existing functions of the network control platform.