Intelligent technologies for nuclear power systems: heuristic and neural tools

The consecutive, partly overlapping emergence of expert systems and then neural computation methods among intelligent technologies, is reflected in the evolving scene of their application to nuclear engineering. This paper provides a bird's eye view of the state of the application in the domain, along with a review of a particular task, the one perhaps economically more important: refueling design in nuclear power reactors.

Self-adaptability and man-in-the-loop: a dilemma in autonomic computing systems

This paper addresses some controversial issues relating to two main questions. Firstly, we discuss 'man-in-the loop' issues in SAACS. Some people advocate this must always be so that man's decisions can override autonomic components. In this case, the system has two subsystems - man and machine. Can we, however, have a fully autonomic machine - with no man in sight; even for short periods of time? What kinds of systems require man to always be in the loop? What is the optimum balance in self-to-human control? How do we determine the optimum? How far can we go in describing self-behaviour? How does a SAACS system handle unexpected behaviour? Secondly, what are the challenges/obstacles in testing SAACS in the context of self/human dilemma? Are there any lesson to be learned from other programmes e.g. Star-wars, aviation and space explorations? What role human factors and behavioural models play whilst in interacting with SAACS?.

Natural inspiration for self-adaptive systems

The emergent behaviour of autonomic systems, together with the scale of their deployment, impedes prediction of the full range of configuration and failure scenarios; thus it is not possible to devise management and recovery strategies to cover all possible outcomes. One solution to this problem is to embed self-managing and self-healing abilities into such applications. Traditional design approaches favour determinism, even when unnecessary. This can lead to conflicts between the non-functional requirements. Natural systems such as ant colonies have evolved cooperative, finely tuned emergent behaviours which allow the colonies to function at very large scale and to be very robust, although non-deterministic. Simple pheromone-exchange communication systems are highly efficient and are a major contribution to their success. This paper proposes that we look to natural systems for inspiration when designing architecture and communications strategies, and presents an election algorithm which encapsulates non-deterministic behaviour to achieve high scalability, robustness and stability.

Generic support for policy-based self-adaptive systems

This paper presents a policy definition language which forms part of a generic policy toolkit for autonomic computing systems in which the policies themselves can be modified dynamically and automatically. Targeted enhancements to the current state of practice include: policy self-adaptation where the policy itself is dynamically modified to match environmental conditions; improved support for non autonomics-expert developers; and facilitating easy deployment of adaptive policies into legacy code. The policy definition language permits powerful expression of self-managing behaviours and facilitates a diverse policy behaviour space. Features include support for multiple versions of a given policy type, multiple configuration templates, and meta policies to dynamically select between policy instances. An example deployment scenario illustrates advanced functionality in the context of a multi policy stock trading system which is sensitive to environmental volatility.

Exploring adaptation & self-adaptation in autonomic computing systems

This panel paper sets out to discuss what self-adaptation means, and to explore the extent to which current autonomic systems exhibit truly self-adaptive behaviour. Many of the currently cited examples are clearly adaptive, but debate remains as to what extent they are simply following prescribed adaptation rules within preset bounds, and to what extent they have the ability to truly learn new behaviour. Is there a standard test that can be applied to differentiate? Is adaptive behaviour sufficient anyway? Other autonomic computing issues are also discussed.

Web-based course support systems: an essential tool for supporting flexible learning environment

In Higher Education web-based course support systems are essential for supporting flexible learning environments. They provide tools to enable the interaction between student and tutor to reinforce transfer of theory to understanding particularly in an academic environment, therefore this paper will examine issues associated with the use of curriculum and learning resources within Web-based course support systems and the effectiveness of the resulting flexible learning environments This paper is a general discussion about flexible learning and in this case how it was applied to one of the courses at undergraduate level one. The first section will introduce what is flexible learning and the importance of flexible learning in Higher Education followed by the description of the course and why the flexible learning concepts is important in such a course and finally, how the flexibility was useful for this particular instance.

The FUELCON meta-architecture, in the landscape of intelligent technologies for refuelling

The conception of the FUELCON architecture, of a composite tool for the generation and validation of patterns for assigning fuel assemblies to the positions in the grid of a reactor core section, has undergone an evolution throughout the history of the project. Different options for various subtask were possible, envisioned, or actually explored or adopted. We project these successive, or even concomitant configurations of the architecture, into a meta-architecture, which quite not by chance happens to reflect basic choices in the field's history over the last decade.

The FUELGEN alternative: an evolutionary approach. The architecture

This paper introduces a few architectural concepts from FUELGEN, that generates a "cloud" of reload patterns, like the generator in the FUELCON expert system, but unlike that generator, is based on a genetic algorithm. There are indications FUELGEN may outperform FUELCON and other tools as reported in the literature, in well-researched case studies, but careful comparisons have to be carried out. This paper complements the information in two other recent papers on FUELGEN. Moreover, a sequel project is outlined.

The FUELCON meta-architecture, II: alternatives for parameter prediction

We continue the discussion of the decision points in the FUELCON metaarchitecture. Having discussed the relation of the original expert system to its sequel projects in terms of an AND/OR tree, we consider one further domain for a neural component: parameter prediction downstream of the core reload candidate pattern generator, thus, a replacement for the NOXER simulator currently in use in the project.

A forum on case-based reasoning. Guest editorial

Guest editorial

An intelligent assistant for design and material engineers in the submarine cable industry

This paper describes an industrial application of case-based reasoning in engineering. The application involves an integration of case-based reasoning (CBR) retrieval techniques with a relational database. The database is specially designed as a repository of experiential knowledge and with the CBR application in mind such as to include qualitative search indices. The application is for an intelligent assistant for design and material engineers in the submarine cable industry. The system consists of three components; a material classifier and a database of experiential knowledge and a CBR system is used to retrieve similar past cases based on component descriptions. Work has shown that an uncommon retrieval technique, hierarchical searching, well represents several search indices and that this techniques aids the implementation of advanced techniques such as context sensitive weights. The system is currently undergoing user testing at the Alcatel Submarine Cables site in Greenwich. Plans are for wider testing and deployment over several sites internationally.

Exploring genetic alternative concepts for FUELGEN

This paper describes new crossover operators and mutation strategies for the FUELGEN system, a genetic algorithm which designs fuel loading patterns for nuclear power reactors. The new components are applications of new ideas from recent research in genetic algorithms. They are designed to improve the performance of FUELGEN by using information in the problem as yet not made explicit in the genetic algorithm's representation. The paper introduces new developments in genetic algorithm design and explains how they motivate the proposed new components.

Load sharing in cluster service provision

The factors that are driving the development and use of grids and grid computing, such as size, dynamic features, distribution and heterogeneity, are also pushing to the forefront service quality issues. These include performance, reliability and security. Although grid middleware can address some of these issues on a wider scale, it has also become imperative to ensure adequate service provision at local level. Load sharing in clusters can contribute to the provision of a high quality service, by exploiting both static and dynamic information. This paper is concerned with the presentation of a load sharing scheme, that can satisfy grid computing requirements. It follows a proactive, non preemptive and distributed approach. Load information is gathered continuously before it is needed, and a task is allocated to the most appropriate node for execution. Performance and reliability are enhanced by the decentralised nature of the scheme and the symmetric roles of the nodes. In addition, the scheme exhibits transparency characteristics that facilitate integration with the grid.

SOFT – generating highly flexible object code from XML specifications

Many code generation tools exist to aid developers in carrying out common mappings, such as from Object to XML or from Object to relational database. Such generated code tends to possess a high binding between the Object code and the target mapping, making integration into a broader application tedious or even impossible. In this paper we suggest XML technologies and the multiple inheritance capabilities of interface based languages such as Java, offer a means to unify such executable specifications, thus building complete, consistent and useful object models declaratively, without sacrificing component flexibility.