Collective sampling and analysis of high order tensors for chatroom communications

This work investigates the accuracy and efficiency tradeoffs between centralized and collective (distributed) algorithms for (i) sampling, and (ii) n-way data analysis techniques in multidimensional stream data, such as Internet chatroom communications. Its contributions are threefold. First, we use the Kolmogorov-Smirnov goodness-of-fit test to show that statistical differences between real data obtained by collective sampling in time dimension from multiple servers and that of obtained from a single server are insignificant. Second, we show using the real data that collective data analysis of 3-way data arrays (users x keywords x time) known as high order tensors is more efficient than centralized algorithms with respect to both space and computational cost. Furthermore, we show that this gain is obtained without loss of accuracy. Third, we examine the sensitivity of collective constructions and analysis of high order data tensors to the choice of server selection and sampling window size. We construct 4-way tensors (users x keywords x time x servers) and analyze them to show the impact of server and window size selections on the results.

Effect of Selfish Node Behavior on Efficient Topology Design

The problem of topology control is to assign per-node transmission power such that the resulting topology is energy efficient and satisfies certain global properties such as connectivity. The conventional approach to achieve these objectives is based on the fundamental assumption that nodes are socially responsible. We examine the following question: if nodes behave in a selfish manner, how does it impact the overall connectivity and energy consumption in the resulting topologies? We pose the above problem as a noncooperative game and use game-theoretic analysis to address it. We study Nash equilibrium properties of the topology control game and evaluate the efficiency of the induced topology when nodes employ a greedy best response algorithm. We show that even when the nodes have complete information about the network, the steady-state topologies are suboptimal. We propose a modified algorithm based on a better response dynamic and show that this algorithm is guaranteed to converge to energy-efficient and connected topologies. Moreover, the node transmit power levels are more evenly distributed, and the network performance is comparable to that obtained from centralized algorithms.

Distributed static linear Gaussian models using consensus

Algorithms for distributed agreement are a powerful means for formulating distributed versions of existing centralized algorithms. We present a toolkit for this task and show how it can be used systematically to design fully distributed algorithms for static linear Gaussian models, including principal component analysis, factor analysis, and probabilistic principal component analysis. These algorithms do not rely on a fusion center, require only low-volume local (1-hop neighborhood) communications, and are thus efficient, scalable, and robust. We show how they are also guaranteed to asymptotically converge to the same solution as the corresponding existing centralized algorithms. Finally, we illustrate the functioning of our algorithms on two examples, and examine the inherent cost-performance tradeoff.

Distributed optimization in transportation and logistics networks

Many important problems in communication networks, transportation networks, and logistics networks are solved by the minimization of cost functions. In general, these can be complex optimization problems involving many variables. However, physicists noted that in a network, a node variable (such as the amount of resources of the nodes) is connected to a set of link variables (such as the flow connecting the node), and similarly each link variable is connected to a number of (usually two) node variables. This enables one to break the problem into local components, often arriving at distributive algorithms to solve the problems. Compared with centralized algorithms, distributed algorithms have the advantages of lower computational complexity, and lower communication overhead. Since they have a faster response to local changes of the environment, they are especially useful for networks with evolving conditions. This review will cover message-passing algorithms in applications such as resource allocation, transportation networks, facility location, traffic routing, and stability of power grids.

Algorithms for Routing and Centralized Scheduling in IEEE 802.16 Mesh Networks

IEEE 802.16 standards for Wireless Metropolitan Area Networks (WMANs) include a mesh mode of operation for improving the coverage and throughput of the network. In this paper, we consider the problem of routing and centralized scheduling for such networks. We first fix the routing, which reduces the network to a tree. We then present a finite horizon dynamic programming framework. Using it we obtain various scheduling algorithms depending upon the cost function. Next we consider simpler suboptimal algorithms and compare their performances.

Real-World Extensions To Scheduling Algorithms Based On Lagrangian Relaxation

Recently, efficient scheduling algorithms based on Lagrangian relaxation have been proposed for scheduling parallel machine systems and job shops. In this article, we develop real-world extensions to these scheduling methods. In the first part of the paper, we consider the problem of scheduling single operation jobs on parallel identical machines and extend the methodology to handle multiple classes of jobs, taking into account setup times and setup costs, The proposed methodology uses Lagrangian relaxation and simulated annealing in a hybrid framework, In the second part of the paper, we consider a Lagrangian relaxation based method for scheduling job shops and extend it to obtain a scheduling methodology for a real-world flexible manufacturing system with centralized material handling.

Performance Study of a Centralized Concurrency Control Algorithm for Distributed Database Systems using SIMULA

The stimulation technique has gained much importance in the performance studies of Concurrency Control (CC) algorithms for distributed database systems. However, details regarding the simulation methodology and implementation are seldom mentioned in the literature. One objective of this paper is to elaborate the simulation methodology using SIMULA. Detailed studies have been carried out on a centralised CC algorithm and its modified version. The results compare well with a previously reported study on these algorithms. Here, additional results concerning the update intensiveness of transactions and the degree of conflict are obtained. The degree of conflict is quantitatively measured and it is seen to be a useful performance index. Regression analysis has been carried out on the results, and an optimisation study using the regression model has been performed to minimise the response time. Such a study may prove useful for the design of distributed database systems.

Centralized vs. Distributed Connection Management Schemes under Different Traffic Patterns in Wavelength-Convertible Optical Networks

Centralized and Distributed methods are two connection management schemes in wavelength convertible optical networks. In the earlier work, the centralized scheme is said to have lower network blocking probability than the distributed one. Hence, much of the previous work in connection management has focused on the comparison of different algorithms in only distributed scheme or in only centralized scheme. However, we believe that the network blocking probability of these two connection management schemes depends, to a great extent, on the network traffic patterns and reservation times. Our simulation results reveal that the performance improvement (in terms of blocking probability) of centralized method over distributed method is inversely proportional to the ratio of average connection interarrival time to reservation time. After that ratio increases beyond a threshold, those two connection management schemes yield almost the same blocking probability under the same network load. In this paper, we review the working procedure of distributed and centralized schemes, discuss the tradeoff between them, compare these two methods under different network traffic patterns via simulation and give our conclusion based on the simulation data.

Management and routing algorithms for ad-hoc and sensor networks

Large scale wireless adhoc networks of computers, sensors, PDAs etc. (i.e. nodes) are revolutionizing connectivity and leading to a paradigm shift from centralized systems to highly distributed and dynamic environments. An example of adhoc networks are sensor networks, which are usually composed by small units able to sense and transmit to a sink elementary data which are successively processed by an external machine. Recent improvements in the memory and computational power of sensors, together with the reduction of energy consumptions, are rapidly changing the potential of such systems, moving the attention towards datacentric sensor networks. A plethora of routing and data management algorithms have been proposed for the network path discovery ranging from broadcasting/floodingbased approaches to those using global positioning systems (GPS). We studied WGrid, a novel decentralized infrastructure that organizes wireless devices in an adhoc manner, where each node has one or more virtual coordinates through which both message routing and data management occur without reliance on either flooding/broadcasting operations or GPS. The resulting adhoc network does not suffer from the deadend problem, which happens in geographicbased routing when a node is unable to locate a neighbor closer to the destination than itself. WGrid allow multidimensional data management capability since nodes' virtual coordinates can act as a distributed database without needing neither special implementation or reorganization. Any kind of data (both single and multidimensional) can be distributed, stored and managed. We will show how a location service can be easily implemented so that any search is reduced to a simple query, like for any other data type. WGrid has then been extended by adopting a replication methodology. We called the resulting algorithm WRGrid. Just like WGrid, WRGrid acts as a distributed database without needing neither special implementation nor reorganization and any kind of data can be distributed, stored and managed. We have evaluated the benefits of replication on data management, finding out, from experimental results, that it can halve the average number of hops in the network. The direct consequence of this fact are a significant improvement on energy consumption and a workload balancing among sensors (number of messages routed by each node). Finally, thanks to the replications, whose number can be arbitrarily chosen, the resulting sensor network can face sensors disconnections/connections, due to failures of sensors, without data loss. Another extension to {WGrid} is {W*Grid} which extends it by strongly improving network recovery performance from link and/or device failures that may happen due to crashes or battery exhaustion of devices or to temporary obstacles. W*Grid guarantees, by construction, at least two disjoint paths between each couple of nodes. This implies that the recovery in W*Grid occurs without broadcasting transmissions and guaranteeing robustness while drastically reducing the energy consumption. An extensive number of simulations shows the efficiency, robustness and traffic road of resulting networks under several scenarios of device density and of number of coordinates. Performance analysis have been compared to existent algorithms in order to validate the results.

Efficient asynchronous scheduling algorithms for cost-effective buffered crossbar switches

Buffered crossbar switches have recently attracted considerable attention as the next generation of high speed interconnects. They are a special type of crossbar switches with an exclusive buffer at each crosspoint of the crossbar. They demonstrate unique advantages over traditional unbuffered crossbar switches, such as high throughput, low latency, and asynchronous packet scheduling. However, since crosspoint buffers are expensive on-chip memories, it is desired that each crosspoint has only a small buffer. This dissertation proposes a series of practical algorithms and techniques for efficient packet scheduling for buffered crossbar switches. To reduce the hardware cost of such switches and make them scalable, we considered partially buffered crossbars, whose crosspoint buffers can be of an arbitrarily small size. Firstly, we introduced a hybrid scheme called Packet-mode Asynchronous Scheduling Algorithm (PASA) to schedule best effort traffic. PASA combines the features of both distributed and centralized scheduling algorithms and can directly handle variable length packets without Segmentation And Reassembly (SAR). We showed by theoretical analysis that it achieves 100% throughput for any admissible traffic in a crossbar with a speedup of two. Moreover, outputs in PASA have a large probability to avoid the more time-consuming centralized scheduling process, and thus make fast scheduling decisions. Secondly, we proposed the Fair Asynchronous Segment Scheduling (FASS) algorithm to handle guaranteed performance traffic with explicit flow rates. FASS reduces the crosspoint buffer size by dividing packets into shorter segments before transmission. It also provides tight constant performance guarantees by emulating the ideal Generalized Processor Sharing (GPS) model. Furthermore, FASS requires no speedup for the crossbar, lowering the hardware cost and improving the switch capacity. Thirdly, we presented a bandwidth allocation scheme called Queue Length Proportional (QLP) to apply FASS to best effort traffic. QLP dynamically obtains a feasible bandwidth allocation matrix based on the queue length information, and thus assists the crossbar switch to be more work-conserving. The feasibility and stability of QLP were proved, no matter whether the traffic distribution is uniform or non-uniform. Hence, based on bandwidth allocation of QLP, FASS can also achieve 100% throughput for best effort traffic in a crossbar without speedup.