Tuning parallel applications in parallel

In this paper, we present and evaluate a parallel algorithm for parameter tuning of parallel applications. We discuss the impact of performance variability on the accuracy and efficiency of the optimization algorithm and propose a strategy to minimize the impact of this variability. We evaluate our algorithm within the Active Harmony system, an automated online/offline tuning framework. We study its performance on three benchmark codes: PSTSWM, HPL and POP. Compared to the Nelder–Mead algorithm, our algorithm finds better configurations up to seven times faster. For POP, we were able to improve the performance of a production sized run by 59%.     

Detection of local community structures in complex dynamic networks with random walks

Identification of interaction patterns in complex networks via community structures has gathered a lot of attention in recent research studies. Local community structures provide a better measure to understand and visualise the nature of interaction when the global knowledge of networks is unknown. Recent research on local community structures, however, lacks the feature to adjust itself in the dynamic networks and heavily depends on the source vertex position. In this study the authors propose a novel approach to identify local communities based on iterative agglomeration and local optimisation. The proposed solution has two significant improvements: (i) in each iteration, agglomeration strengthens the local community measure by selecting the best possible set of vertices, and (ii) the proposed vertex and community rank criterion are suitable for the dynamic networks where the interactions among vertices may change over time. In order to evaluate the proposed algorithm, extensive experiments and benchmarking on computer generated networks as well as real-world social and biological networks have been conducted. The experiment results reflect that the proposed algorithm can identify local communities, irrespective of the source vertex position, with more than 92% accuracy in the synthetic as well as in the real-world networks.     

Solving distributed FMS scheduling problems subject to maintenance: Genetic algorithms approach

In general, distributed scheduling problem focuses on simultaneously solving two issues: (i) allocation of jobs to suitable factories and (ii) determination of the corresponding production scheduling in each factory. The objective of this approach is to maximize the system efficiency by finding an optimal planning for a better collaboration among various processes. This makes distributed scheduling problems more complicated than classical production scheduling ones. With the addition of alternative production routing, the problems are even more complicated. Conventionally, machines are usually assumed to be available without interruption during the production scheduling. Maintenance is not considered. However, every machine requires maintenance, and the maintenance policy directly affects the machine's availability. Consequently, it influences the production scheduling. In this connection, maintenance should be considered in distributed scheduling. The objective of this paper is to propose a genetic algorithm with dominant genes (GADG) approach to deal with distributed flexible manufacturing system (FMS) scheduling problems subject to machine maintenance constraint. The optimization performance of the proposed GADG will be compared with other existing approaches, such as simple genetic algorithms to demonstrate its reliability. The significance and benefits of considering maintenance in distributed scheduling will also be demonstrated by simulation runs on a sample problem.     

Thermal performance of “still on roof” system

This paper presents an analysis of periodic heat flux through a roof, on which a solar still has been placed. It is seen that on a typical hot day in Delhi, for high reflectivity of the bottom of the basin (on account of deposits or otherwise) the daily heat flux in the room gets reduced by 40% and the production of distilled water is 0.6 kg/m² day; the produced swings in the heat flux also get reduced in magnitude. For a typical cold day in Delhi, if a black dye is mixed with basin water the daily heat flux in the room increases by a factor of two and the yield of the distillate becomes 5.0 kg/m² day.     

Early user involvement in the development of information technology-related products for older people

The UTOPIA project (Usable Technology for Older People—Inclusive and Appropriate) is focused on developing effective methods for the early involvement of older people in the development of information technology-related products for people aged 60 and over, and on providing industry with tools to assist in the development of information technology products for such older people. An essential part of this methodology is building a diverse user base, forming a long-lasting partnership with older people, and developing approaches for effective interaction with this target user group. Our experiences with eliciting information from groups of older people about technology is described, together with a report on seminars for Scottish industry designed to raise an awareness of these issues.     

Effect of a thermal trap on the performance of a solar sand collector

The effects of different parameters—e.g. the thickness of the trap material, the flow rate of the water and the depth of the heat-retrieval plane—on the water temperature have been investigated. A comparison of the present system with a conventional solar sand collector was also made.     

Effect of a booster mirror on the performance of a ‘built-in’ storage solar water heater

In this paper, the performance of a ‘built-in’ storage solar water heater-flat mirror system has been presented. Numerical calculations have been made for a typical cold day (viz. 28 Jan. 1980) at Delhi. The booster mirror causes a minimum temperature rise during the moring and a temperature difference of 7°C excess with respect to the reference panel occurred. The reflectance of the mirror is taken as 0·88.     

Process control in CNC manufacturing for discrete components: A STEP-NC compliant framework

With today's highly competitive global manufacturing marketplace, the pressure for right-first-time manufacture has never been so high. New emerging data standards combined with machine data collection methods, such as in-process verification lead the way to a complete paradigm shift from the traditional manufacturing and inspection to intelligent networked process control. Low-level G and M codes offer very limited information on machine capabilities or work piece characteristics which consequently, results in no information being available on manufacturing processes, inspection plans and work piece attributes in terms of tolerances, etc. and design features to computer numerically controlled (CNC) machines. One solution to the aforementioned problems is using STEP-NC (ISO 14649) suite of standards, which aim to provide higher-level information for process control. In this paper, the authors provide a definition for process control in CNC manufacturing and identify the challenges in achieving process control in current CNC manufacturing scenario. The paper then introduces a STEP-compliant framework that makes use of self-learning algorithms that enable the manufacturing system to learn from previous data and results in eliminating the errors and consistently producing quality products. The framework relies on knowledge discovery methods such as data mining encapsulated in a process analyser to derive rules for corrective measures to control the manufacturing process. The design for the knowledge-based process analyser and the various process control mechanisms conclude the paper.