The paper describes work carried out to reduce the pessimism in distributedsystems timing analysis. The starting point for the paper is the need to prove that the timing properties of a system are met in an efficient...
详细信息
The paper describes work carried out to reduce the pessimism in distributedsystems timing analysis. The starting point for the paper is the need to prove that the timing properties of a system are met in an efficient and effective manner. The paper shows that an exact approach to the analysis can be intractable, and other approaches are too pessimistic. Using extensive simulation, based on realistic requirements from the domain of interest, a new approach to distributed timing analysis is developed using an integrated approach to task attribute assignment and timing analysis. The new approach is up to 20% more effective than previous tractable approaches. An additional benefit is the approach has a greater resilience to change than the other approaches considered. The results contained within the paper demonstrate the effectiveness of our approach.
Reactive computer control systems need to track the behaviour of their inherently parallel physical environment. Hence, most non-trivial industrial applications may depend on concurrent modelling techniques to handle ...
详细信息
Reactive computer control systems need to track the behaviour of their inherently parallel physical environment. Hence, most non-trivial industrial applications may depend on concurrent modelling techniques to handle system complexities including hard real-time constraints. Failure of such systems can lead to unacceptable consequences and can therefore be deemed as safety-related with respect to their application. Parallel and distributedsystems can exhibit undesirable behaviours, e.g. deadlock, which could render a control system unsafe. The paper proposes that a set of undesirable parallel behaviours can be classified as unsafe for all applications and reviews a technique that can be employed to avoid or mitigate against them, The approach needed by software engineers of parallel and distributedsystems to facilitate this and meet the minimal safety standards is also given.
There is an emerging desire among agent researchers to move away from developing point solutions to point problems in favour of developing methodologies and tool-kits for building distributed multi-agent systems. This...
There is an emerging desire among agent researchers to move away from developing point solutions to point problems in favour of developing methodologies and tool-kits for building distributed multi-agent systems. This philosophy has led to the development of the ZEUS agent building tool-kit, which facilitates the engineering of collaborative agent applications through the provision of a library of agent-level components and an environment to support the agent building process. The ZEUS tool-kit is a synthesis of established agent technologies with some novel solutions that provide an integrated environment for rapid software engineering of collaborative agent applications.
This paper describes an advanced scheduling system and method for generating large volumes of calls to be used for testing a telecommunications network. The system is capable of preparing large scale and complex netwo...
This paper describes an advanced scheduling system and method for generating large volumes of calls to be used for testing a telecommunications network. The system is capable of preparing large scale and complex network tests by viewing the task as a scheduling problem. The various requirements of the scheduling problem are analysed and represented as constraints or optimisation criteria. A fast heuristic method is proposed for solving the problem. The approach is based on a greedy algorithm for constructing solutions and if incorporates limited backtracking and dynamic value-ordering heuristics. The algorithm and system are currently being used for call charge verification in BT's PSTN and CSP networks.
Quality-of-service (QoS) routing satisfies application performance requirements and optimizes network resource usage but effective path-selection schemes require the distribution of link-state information, which can i...
详细信息
Quality-of-service (QoS) routing satisfies application performance requirements and optimizes network resource usage but effective path-selection schemes require the distribution of link-state information, which can impose a significant burden on the bandwidth and processing resources in the network. We investigate the fundamental trade-off between network overheads and the quality of routing decisions in the context of the source-directed link-state routing protocols proposed for future IP and ATM networks. Through extensive simulation experiments with several representative network topologies and traffic patterns, we uncover the effects of stale link-state information, random fluctuations in traffic load, and variations of the link-cost metric on the routing and signalling overheads. The paper concludes by summarizing our key results as a list of guidelines for designing efficient quality-of-service routing policies in large backbone networks.
SNMPv2 management tools for networks based on Novell NetWare and TCP/IP facilitate management of individual network workstations which allows a very detailed description of the network operation to be constructed. Usi...
There is a need for information exchange and communication between management applications that are distributed over a large system. In this situation, a fundamental problem is how the management systems should cooper...
We describe the autonomous robot ARBIB, which uses biologically-motivated forms of learning to adapt to its environment. The "nervous system" of ARBIB has a nonhomogeneous population of spiking neurons, and ...
详细信息
We describe the autonomous robot ARBIB, which uses biologically-motivated forms of learning to adapt to its environment. The "nervous system" of ARBIB has a nonhomogeneous population of spiking neurons, and uses both nonassociative (habituation, sensitization) and associative (classical conditioning) forms of learning to modify pre-existing ("hard-wired") reflexes. As a result of interaction with its environment, interesting and "intelligent" light-seeking and collision-avoidance behaviors emerge which were not pre-programmed into the robot-or "animat". These behaviors are similar to those described by other workers who have generally used behaviorally-motivated reinforcement learning rather than biologically-based associative learning. The complexity of observed behavior is remarkable given the extreme simplicity of ARBIB's "nervous system", having just 33 neurons. It does not even have a brain! We take this to indicate that great potential exists to explore further "the animat path to AI".
We present an application of evolutionary-fuzzy prediction in inter-domain routing of broadband network connections with quality of services requirements in the case of an integrated ATM and SDH networking architectur...
详细信息
We present an application of evolutionary-fuzzy prediction in inter-domain routing of broadband network connections with quality of services requirements in the case of an integrated ATM and SDH networking architecture. The higher-layer nature of inter-domain routing requires us to review the whole routing process in order to maximize performance at low decision making cost, a clear case for fuzzy-set logic based algorithms. In order to probabilistically avoid shortage of resources, besides effectively computing the feasible paths for an incoming connection request, under uncertainty, these paths should be compared in terms of the negative impact in resource supply which may be caused by other connections. To do this, besides enriching the protocol with vectors of per-class shadow cost metrics, quantized using fuzzy-set theory, we used a subset-interactive autoregressive time-series predictor which is based on fuzzy measures to evaluate path costs under supply metrics that change over time. Moreover, as the connections we are dealing with are semi-permanent, we must take into account the connections lifetime. The complete system is part of the MISA (Management of Integrated SDH and ATM) network architecture and will be implemented and evaluated in the global broadband connection service of the pan-European test-bed.
By combining properties of fuzzy systems and neural networks, neurofuzzy modelling is ideally suited to many system identification and data modelling applications. Recently, data-driven model construction algorithms h...
详细信息
By combining properties of fuzzy systems and neural networks, neurofuzzy modelling is ideally suited to many system identification and data modelling applications. Recently, data-driven model construction algorithms have been developed to identify these models. These algorithms have proved essential for producing accurate parsimonious models. However, due to problems with sparse data and restricted model structures, models with high model variance are often produced. Thus resulting in models which generalise poorly. In this paper local Bayesian inference techniques are applied to neurofuzzy models, multiple prior probability density functions are placed on the weights and superfluous model variance is controlled. This gives a form of regularisation where Bayesian estimation produces simple re-estimation formulae which identify a suitable bias/variance balance from the data. This approach is considered a post-processing step to model construction, the merits of which are demonstrated by the application to a real world data set.
暂无评论