Evaluation of loadsharing algorithms for heterogeneous distributed systems

The performance of loadsharing algorithms for heterogeneous distributed systems is investigated by simulation. The systems considered are networks of workstations (nodes) which differ in processing power. Two parameters are proposed for characterising system heterogeneity, namely the variance and skew of the distribution of processing power among the network nodes. A variety of networks are investigated, with the same number of nodes and total processing power, but with the processing power distributed differently among the nodes. Two loadsharing algorithms are evaluated, at overall system loadings of 50% and 90%, using job response time as the performance metric. Comparison is made with the ideal situation of ‘perfect sharing’, where it is assumed that the communication delays are zero and that complete knowledge is available about job lengths and the loading at the different nodes, so that an arriving job can be sent to the node where it will be completed in the shortest time. The algorithms studied are based on those already in use for homogeneous networks, but were adapted to take account of system heterogeneity. Both algorithms take into account the differences in the processing powers of the nodes in their location policies, but differ in the extent to which they ‘discriminate’ against the slower nodes. It is seen that the relative performance of the two is strongly influenced by the system utilisation and the distribution of processing power among the nodes.

Distributed belief revision as applied within a descriptive model of jury deliberations

Belief revision is a well-research topic within AI. We argue that the new model of distributed belief revision as discussed here is suitable for general modelling of judicial decision making, along with extant approach as known from jury research. The new approach to belief revision is of general interest, whenever attitudes to information are to be simulated within a multi-agent environment with agents holding local beliefs yet by interaction with, and influencing, other agents who are deliberating collectively. In the approach proposed, it's the entire group of agents, not an external supervisor, who integrate the different opinions. This is achieved through an election mechanism, The principle of "priority to the incoming information" as known from AI models of belief revision are problematic, when applied to factfinding by a jury. The present approach incorporates a computable model for local belief revision, such that a principle of recoverability is adopted. By this principle, any previously held belief must belong to the current cognitive state if consistent with it. For the purposes of jury simulation such a model calls for refinement. Yet we claim, it constitutes a valid basis for an open system where other AI functionalities (or outer stiumuli) could attempt to handle other aspects of the deliberation which are more specifi to legal narrative, to argumentation in court, and then to the debate among the jurors.

Pneumatic contactless microfeeder design refinement through CFD simulation

A new contactless pneumatic microfeeder based on distributed manipulation is proposed. By cooperation of dynamically programmable microactuators, the part to be conveyed floats over an air cushion and is moved to the desired location with the desired orientation. CFD simulations are used to test the validity of the proposed concept and refine the design of the microactuators

2-D R-matrix propagation: A large scale electron scattering simulation dominated by the multiplication of dynamically changing matrices

We examine the computational aspects of propagating a global R-matrix, R, across sub-regions in a 2-D plane. This problem originates in the large scale simulation of electron collisions with atoms and ions at intermediate energies. The propagation is dominated by matrix multiplications which are complicated because of the dynamic nature of R, which changes the designations of its rows and columns and grows in size as the propagation proceeds. The use of PBLAS to solve this problem on distributed memory HPC machines is the main focus of the paper.

Measurements, modeling and simulation of the off-body radio channel for the implementation of bodyworn antenna diversity at 868 MHz

This paper presents a systematic measurement campaign of diversity reception techniques for use in multiple-antenna wearable systems operating at 868 MHz. The experiments were performed using six time-synchronized bodyworn receivers and considered mobile off-body communications in an anechoic chamber, open office area and a hallway. The cross-correlation coefficient between the signal fading measured by bodyworn receivers was dependent upon the local environment and typically below 0.7. All received signal envelopes were combined in post-processing to study the potential benefits of implementing receiver diversity based upon selection combination, equal-gain and maximal-ratio combining. It is shown that, in an open office area, the 5.7 dB diversity gain obtained using a dual-branch bodyworn maximal-ratio diversity system may be further improved to 11.1 dB if a six-branch system was used. First-and second-order theoretical equations for diversity reception techniques operating in Nakagami fading conditions were used to model the postdetection combined envelopes. Maximum likelihood estimates of the Nakagami-parameter suggest that the fading conditions encountered in this study were generally less severe than Rayleigh. The paper also describes an algorithm that may be used to simulate the measured output of an M-branch diversity combiner operating in independent and identically-distributed Nakagami fading environments.

Providing QoS for networked peers in distributed haptic virtual environments

Haptic information originates from a different human sense (touch), therefore the quality of service (QoS) required to supporthaptic traffic is significantly different from that used to support conventional real-time traffic such as voice or video. Each type ofnetwork impairment has different (and severe) impacts on the user’s haptic experience. There has been no specific provision of QoSparameters for haptic interaction. Previous research into distributed haptic virtual environments (DHVEs) have concentrated onsynchronization of positions (haptic device or virtual objects), and are based on client-server architectures.We present a new peerto-peer DHVE architecture that further extends this to enable force interactions between two users whereby force data are sent tothe remote peer in addition to positional information. The work presented involves both simulation and practical experimentationwhere multimodal data is transmitted over a QoS-enabled IP network. Both forms of experiment produce consistent results whichshow that the use of specific QoS classes for haptic traffic will reduce network delay and jitter, leading to improvements in users’haptic experiences with these types of applications.

Performance Analysis of Randomized Distributed Space-Time Codes over Composite Gamma/Lognormal Fading Channels

This work investigates the end-to-end performance of randomized distributed space-time codes with complex Gaussian distribution, when employed in a wireless relay network. The relaying nodes are assumed to adopt a decode-and-forward strategy and transmissions are affected by small and large scale fading phenomena. Extremely tight, analytical approximations of the end-to-end symbol error probability and of the end-to-end outage probability are derived and successfully validated through Monte-Carlo simulation. For the high signal-to-noise ratio regime, a simple, closed-form expression for the symbol error probability is further provided.

Numerical Simulation of Tanpura String Vibrations

A numerical model of a tanpura string is presented, based on a recently developed, stability-preserving way of incorporating the non-smooth forces involved in the impactive distributed contact between the string and the bridge. By defining and modelling the string-bridge contact over the full length of the bridge, the simulated vibrations can be monitored through the force signals at both the bridge and the nut. As such it offers a reference model for both measurements and sound synthesis. Simulations starting from different types of initial conditions demonstrate that the model reproduces the main characteristic feature of the tanpura, namely the sustained appearance of a precursor in the force waveforms, carrying a band of overtones which decrease in frequency as the string vibrations decay. Results obtained with the numerical model are used to examine, through comparison, the effect of the bridge and of the thread on the vibrations.

Energy conserving schemes for the simulation of musical instrument contact dynamics

Collisions are an innate part of the function of many musical instruments. Due to the nonlinear nature of contact forces, special care has to be taken in the construction of numerical schemes for simulation and sound synthesis. Finite difference schemes and other time-stepping algorithms used for musical instrument modelling purposes are normally arrived at by discretising a Newtonian description of the system. However because impact forces are non-analytic functions of the phase space variables, algorithm stability can rarely be established this way. This paper presents a systematic approach to deriving energy conserving schemes for frictionless impact modelling. The proposed numerical formulations follow from discretising Hamilton׳s equations of motion, generally leading to an implicit system of nonlinear equations that can be solved with Newton׳s method. The approach is first outlined for point mass collisions and then extended to distributed settings, such as vibrating strings and beams colliding with rigid obstacles. Stability and other relevant properties of the proposed approach are discussed and further demonstrated with simulation examples. The methodology is exemplified through a case study on tanpura string vibration, with the results confirming the main findings of previous studies on the role of the bridge in sound generation with this type of string instrument.

Distributed Consensus Charging for Current Unbalance Reduction

Electric Vehicle (EV) technology has developed rapidly in recent years, with the result that increasing levels of EV penetration are expected on electrical grids in the near future. The increasing electricity demand due to EVs is expected to provide many challenges for grid companies, and it is expected that it will be necessary to reinforce the current electrical grid infrastructure to cater for increasing loads at distribution level. However, by harnessing the power of Vehicle to Grid (V2G) technologies, groups of EVs could be harnessed to provide ancillary services to the grid. Current unbalance occurs at distribution level when currents are unbalanced between each of the phases. In this paper a distributed consensus algorithm is used to coordinate EV charging in order to minimise current unbalance. Simulation results demonstrate that the proposed algorithm is effective in rebalancing phase currents.

Python PSS/E Simulation to Test Efficacy of Proposed PMU Based WAMS and Potential WAMPAC Applications

A PSS/E 32 model of a real section of the Northern Ireland electrical grid was dynamically controlled with Python 2.5. In this manner data from a proposed wide area monitoring system was simulated. The area is of interest as it is a weakly coupled distribution grid with significant distributed generation. The data was used to create an optimization and protection metric that reflected reactive power flow, voltage profile, thermal overload and voltage excursions. Step changes in the metric were introduced upon the operation of special protection systems and voltage excursions. A wide variety of grid conditions were simulated while tap changer positions and switched capacitor banks were iterated through; with the most desirable state returning the lowest optimization and protection metric. The optimized metric was compared against the metric generated from the standard system state returned by PSS/E. Various grid scenarios were explored involving an intact network and compromised networks (line loss) under summer maximum, summer minimum and winter maximum conditions. In each instance the output from the installed distributed generation is varied between 0 MW and 80 MW (120% of installed capacity). It is shown that in grid models the triggering of special protection systems is delayed by between 1 MW and 6 MW (1.5% to 9% of capacity), with 3.5 MW being the average. The optimization and protection metric gives a quantitative value for system health and demonstrates the potential efficacy of wide area monitoring for protection and control.

Interference cancellation for distributed wireless systems

O tema principal desta tese é o problema de cancelamento de interferência para sistemas multi-utilizador, com antenas distribuídas. Como tal, ao iniciar, uma visão geral das principais propriedades de um sistema de antenas distribuídas é apresentada. Esta descrição inclui o estudo analítico do impacto da ligação, dos utilizadores do sistema, a mais antenas distribuídas. Durante essa análise é demonstrado que a propriedade mais importante do sistema para obtenção do ganho máximo, através da ligação de mais antenas de transmissão, é a simetria espacial e que os utilizadores nas fronteiras das células são os mais bene ciados. Tais resultados são comprovados através de simulação. O problema de cancelamento de interferência multi-utilizador é considerado tanto para o caso unidimensional (i.e. sem codi cação) como para o multidimensional (i.e. com codi cação). Para o caso unidimensional um algoritmo de pré-codi cação não-linear é proposto e avaliado, tendo como objectivo a minimização da taxa de erro de bit. Tanto o caso de portadora única como o de multipla-portadora são abordados, bem como o cenário de antenas colocadas e distribuidas. É demonstrado que o esquema proposto pode ser visto como uma extensão do bem conhecido esquema de zeros forçados, cuja desempenho é provado ser um limite inferior para o esquema generalizado. O algoritmo é avaliado, para diferentes cenários, através de simulação, a qual indica desempenho perto do óptimo, com baixa complexidade. Para o caso multi-dimensional um esquema para efectuar "dirty paper coding" binário, tendo como base códigos de dupla camada é proposto. No desenvolvimento deste esquema, a compressão com perdas de informação, é considerada como um subproblema. Resultados de simulação indicam transmissão dedigna proxima do limite de Shannon.

Communication between nodes for autonomic and distributed management

Over the last decade, the most widespread approaches for traditional management were based on the Simple Network Management Protocol (SNMP) or Common Management Information Protocol (CMIP). However, they both have several problems in terms of scalability, due to their centralization characteristics. Although the distributed management approaches exhibit better performance in terms of scalability, they still underperform regarding communication costs, autonomy, extensibility, exibility, robustness, and cooperation between network nodes. The cooperation between network nodes normally requires excessive overheads for synchronization and dissemination of management information in the network. For emerging dynamic and large-scale networking environments, as envisioned in Next Generation Networks (NGNs), exponential growth in the number of network devices and mobile communications and application demands is expected. Thus, a high degree of management automation is an important requirement, along with new mechanisms that promote it optimally and e ciently, taking into account the need for high cooperation between the nodes. Current approaches for self and autonomic management allow the network administrator to manage large areas, performing fast reaction and e ciently facing unexpected problems. The management functionalities should be delegated to a self-organized plane operating within the network, that decrease the network complexity and the control information ow, as opposed to centralized or external servers. This Thesis aims to propose and develop a communication framework for distributed network management which integrates a set of mechanisms for initial communication, exchange of management information, network (re) organization and data dissemination, attempting to meet the autonomic and distributed management requirements posed by NGNs. The mechanisms are lightweight and portable, and they can operate in di erent hardware architectures and include all the requirements to maintain the basis for an e cient communication between nodes in order to ensure autonomic network management. Moreover, those mechanisms were explored in diverse network conditions and events, such as device and link errors, di erent tra c/network loads and requirements. The results obtained through simulation and real experimentation show that the proposed mechanisms provide a lower convergence time, smaller overhead impact in the network, faster dissemination of management information, increase stability and quality of the nodes associations, and enable the support for e cient data information delivery in comparison to the base mechanisms analyzed. Finally, all mechanisms for communication between nodes proposed in this Thesis, that support and distribute the management information and network control functionalities, were devised and developed to operate in completely decentralized scenarios.

Design and Qualitative/Quantitative Analysis of Multi-Agent Spatial Simulation Library

Thesis (Master's)--University of Washington, 2012