A load balancing algorithm for web based server grids

Load balance is a critical issue in distributed systems, such as server grids. In this paper, we propose a Balanced Load Queue (BLQ) model, which combines the queuing theory and hydro-dynamic theory, to model load balance in server grids. Base on the BLQ model, we claim that if the system is in the state of global fairness, then the performance of the whole system is the best. We propose a load balanced algorithm based on the model: the algorithm tries its best to keep the system in the global fairness status using job deviation. We present three strategies: best node, best neighbour, and random selection, for job deviation. A number of experiments are conducted for the comparison of the three strategies, and the results show that the best neighbour strategy is the best among the proposed strategies. Furthermore, the proposed algorithm with best neighbour strategy is better than the traditional round robin algorithm in term of processing delay, and the proposed algorithm needs very limited system information and is robust.

High reliability replication technique for Web-server cluster systems

Providing reliable and efficient services are primary goals in designing a web server system. Data replication can be used to improve the reliability of the system. However, mapping mechanism is one of the primary concerns to data replication. In this paper, we propose a mapping mechanism model called enhanced domain name server (E-DNS) that dispatches the user requests through the URL-name to IP-address under Neighbor Replica Distribution Technique (NRDT) to improve the reliability of the system.

Towards the development of a project decision support framework for adoption of an integrated building information model using a model server

This chapter discusses an action research study towards the development of a decision framework to support a fully integrated multi disciplinary Building Information Model (BIM) using a Model Server. The framework was proposed to facilitate multi disciplinary collaborative BIM adoption through, informed selection of a project specific BIM approach and tools contingent upon project collaborators’ readiness, tool capabilities and workflow dependencies. The aim of the research was to explore the technical concerns in relation to Model Servers to support multi disciplinary model integration and collaboration; however it became clear that there were both technical and non technical issues that needed consideration. The evidence also suggests that there are varying levels of adoption which impacts upon further diffusion of the technologies. Therefore the need for a decision framework was identified based on the findings from an exploratory study conducted to investigate industry expectations. The study revealed that even the market leaders who are early technology adopters in the Australian industry in many cases have varying degrees of practical experiential knowledge of BIM and hence at times low levels of confidence of the future diffusion of BIM technology throughout the industry. The study did not focus on the benefits of BIM implementation as this was not the intention, as the industry partners involved are market leaders and early adopters of the technology and did not need convincing of the benefits. Coupled with this there are various other past studies that have contributed to the ‘benefits’ debate. There were numerous factors affecting BIM adoption which were grouped in to two main areas; technical tool functional requirements and needs, and non technical strategic issues. The need for guidance on where to start, what tools were available and how to work through the legal, procurement and cultural challenges was evidenced in the exploratory study. Therefore a BIM decision framework was initiated, based upon these industry concerns. Eight case studies informed the development of the framework and a summary of the key findings is presented. Primary and secondary case studies from firms that have adopted a structured approach to technology adoption are presented. The Framework consists of four interrelated key elements including a strategic purpose and scoping matrix, work process mapping, technical requirements for BIM tools and Model Servers, and framework implementation guide. The BIM framework was presented in draft format again to key industry stakeholders and considered in comparison with current best practice BIM adoption to further validate the framework. There was no request to change any part of the Framework. However, it is an ongoing process and it will be presented again to industry through the various project partners. The Framework may be refined within the boundaries of the action research process as an ongoing activity as more experiential knowledge can be incorporated.

Optimal power allocation and load distribution for multiple heterogeneous multicore server processors across clouds and data centers

For multiple heterogeneous multicore server processors across clouds and data centers, the aggregated performance of the cloud of clouds can be optimized by load distribution and balancing. Energy efficiency is one of the most important issues for large-scale server systems in current and future data centers. The multicore processor technology provides new levels of performance and energy efficiency. The present paper aims to develop power and performance constrained load distribution methods for cloud computing in current and future large-scale data centers. In particular, we address the problem of optimal power allocation and load distribution for multiple heterogeneous multicore server processors across clouds and data centers. Our strategy is to formulate optimal power allocation and load distribution for multiple servers in a cloud of clouds as optimization problems, i.e., power constrained performance optimization and performance constrained power optimization. Our research problems in large-scale data centers are well-defined multivariable optimization problems, which explore the power-performance tradeoff by fixing one factor and minimizing the other, from the perspective of optimal load distribution. It is clear that such power and performance optimization is important for a cloud computing provider to efficiently utilize all the available resources. We model a multicore server processor as a queuing system with multiple servers. Our optimization problems are solved for two different models of core speed, where one model assumes that a core runs at zero speed when it is idle, and the other model assumes that a core runs at a constant speed. Our results in this paper provide new theoretical insights into power management and performance optimization in data centers.

GENESIS: an efficient, transparent and easy to use cluster operating system

Present operating systems are not built to support parallel computing––they do not provide services to manage parallelism, i.e., to globally manage parallel processes and computational resources. The cluster operating environments that are used to assist the execution of parallel applications do not provide support for both programming paradigms, message passing (MP) or distributed shared memory (DSM)––they are mainly offered as separate components implemented at the user level as library and independent server processes. Due to poor operating systems users must deal with clusters as a set of independent computers rather than to see this cluster as a single powerful computer. A single system image (SSI) of the cluster is not offered to users. There is a need for an operating system for clusters. We claim and demonstrate in this paper that it is possible to develop a cluster operating system that is able to efficiently manage parallelism; use cluster resources efficiently; support MP in the form of standard MP and PVM, and DSM; offer SSI; and make it easy to use. We show that to achieve these aims this operating system should inherit many features of a distributed operating system and provide new services which address the needs of parallel processes, cluster's resources, and application developers. In order to substantiate the claim the first version of a cluster operating system managing parallelism and offering SSI, called GENESIS, has been developed.

Accessing database information using mobile agents

Many real-world applications on the Internet require accessing database information and typical technology employed is client/server plus Web (C/S + Web). Although past few years saw many success applications by using this technique, there are still some drawbacks that need to be overcome. One of the drawbacks is that the transaction often fails if the network connection is unstable. Another disadvantage is high bandwidth requirement and latency. This paper argues that mobile agent technology provide an easy way to overcome the shortcomings in CIS + Web in database access on the Internet. A success case study using mobile agents to admit new students to China's institutions is then presented. The mobile agent was created by using IBM's Aglets Software Development Kit (SDK). Based on the experimental results, it is evident that mobile agent technology is well suited for such applications.

An efficient reliable architecture for application layer anycast service

Anycast is a new service in IPv6, and there are some open issues about the anycast service. In this paper, we focus on efficient and reliable aspects of application layer anycast. We apply the requirement based probing routing algorithm to replace the previous period based probing routingalgorithm for anycast resolvers. We employ the twin server model among the anycast servers, therefore, try to present a reliable service in the Internet environment. Our theoretical analysis shows that the proposed architecture works well, and it offers a more efficient routing performance and fault tolerance capability.

Australian sweet lupin flour addition reduces the glycaemic index of a white bread breakfast without affecting palatability in healthy human volunteers

The addition of some legume ingredients to bread has been associated with effects on glycaemic, insulinaemic and satiety responses that may be beneficial in controlling type 2 diabetes, cardiovascular disease and obesity. However, the effect of Australian sweet lupin (Lupinus angustifolius) flour (ASLF) is unknown. This investigation examined the effect of adding ASLF to standard white bread on post-meal glycaemic, insulinaemic and satiety responses and palatability in healthy subjects. Using a randomised, single-blind, cross-over design, 11 subjects consumed one breakfast of ASLF bread and two of standard white bread ≥ 7 days apart after fasting overnight. Each breakfast also included margarine, jam, and tea with milk and contained 50g available carbohydrate. On each test day, blood samples were taken after fasting, then several times over 2 hours post-prandially, and analysed for plasma glucose and serum insulin. Subjects rated breakfast palatability and perception of satiety, in the fasting state and over 3 hours post-prandially, after which food intake from an ad libitum buffet and for the rest of the day was recorded. Incremental areas under the curves for glucose, insulin and satiety, glycaemic index, insulinaemic index and satiety index were calculated. ASLF addition to the breakfast reduced its glycaemic index (mean ± SEM; ASLF bread breakfast = 74.0 ± 9.6. Standard white bread breakfast = 100, P=0.022), raised its insulinaemic index (ASLF bread breakfast = 127.7 ± 12.0. Standard white bread breakfast = 100, P=0.046), but did not affect palatability, satiety or food intake. ASLF addition resulted in a palatable breakfast; however, the potential benefits of the lowered glycaemic index may be eclipsed by the increased insulinaemic index.

Socio-economic factors in obesity: a case of slim chance in a fat world?

The global obesity pandemic has been well-documented and widely discussed by the public, the media, health officials, the food industry and academic researchers. While the problem is widely recognised, the potential solutions are far less clear. There is only limited evidence to guide decisions as to how best to manage obesity in individuals and in populations. While widely viewed as a clinical and public health problem in developed countries, it is now clear that many developing countries also have to grapple with this problem or face the crippling healthcare costs resulting from obesity-related morbidity. There is also abundant evidence that obesity is socio-economically distributed. In developed countries persons of lower socio-economic position are more likely to be affected, while in developing countries, it is often those of higher socio-economic position who are overweight or obese. The aim of this paper is to briefly review the evidence that links socio-economic position and obesity, to discuss what is known about underlying mechanisms, and to consider the role of social, physical, policy and cultural environments in explaining the relationships between socio-economic position and obesity. We introduce the concept of ‘resilience’ as a potential theoretical construct to guide research efforts aimed at understanding how some socio-economically disadvantaged individuals manage to avoid obesity. We conclude by considering an agenda to guide future research and programs focused on understanding and reducing obesity among those of low socio-economic position.

Obesity and undernutrition in sub-Saharan African immigrant and refugee children in Victoria, Australia

The study assessed the anthropometric status of 337 sub-Saharan African children aged between 3-12 years who migrated to Australia. These children were selected using a snowball sampling method stratified by age, gender and region of origin. The prevalence rates for overweight and obesity were 18.4% (95%CI: 14 - 23%) and 8.6% (95%CI: 6% -12%) respectively. The prevalence rates for the indicators of undernutrition were: wasting 4.3% (95%CI: 1.6%-9.1%), underweight 1.2% (95%CI: 0.3%-3.0%), and stunting 0.3 (95%CI: 0.0%-1.6%). Higher prevalence of overweight/obesity was associated with lower household income level, fewer siblings, lower birth weight, western African background, and single parent households (after controlling for demographic and socio-economic factors). Higher prevalence rates for underweight and wasting were associated with lower household income and shorter lengths of stay in Australia respectively. No effect was found for child's age, gender, parental education and occupation for both obesity and undernutrition indices. In conclusion, obesity and overweight are very prevalent in SSA migrant children and undernutrition, especially wasting, was also not uncommon in this target group.

A web-DB model on multicast and anycast

Most of the current web-based database systems suffer from poor performance, complicated heterogeneity, and synchronization issues. In this paper, we propose a novel mechanism for web-based database system on multicast and anycast protocols to deal with these issues. In the model, we put a castway, a network interface for database server, between database server and Web server. Castway deals with the multicast and anycast requests and responses. We propose a requirement-based server selection algorithm and an atomic multicast update algorithm for data queries and synchronizations. The model is independent from the Internet environment, it can synchronise the databases efficiently and automatically. Furthermore, the model can reduce the possibility of transaction deadlocks.