Executing bag of distributed tasks on the cloud: Investigating the trade-offs between performance and cost

Bag of Distributed Tasks (BoDT) can benefit from decentralised execution on the Cloud. However, there is a trade-off between the performance that can be achieved by employing a large number of Cloud VMs for the tasks and the monetary constraints that are often placed by a user. The research reported in this paper is motivated towards investigating this trade-off so that an optimal plan for deploying BoDT applications on the cloud can be generated. A heuristic algorithm, which considers the user's preference of performance and cost is proposed and implemented. The feasibility of the algorithm is demonstrated by generating execution plans for a sample application. The key result is that the algorithm generates optimal execution plans for the application over 91% of the time.

Cost performance of Irish credit unions

There are 424 credit unions in Ireland with assets under their control of €14.3bn and a membership of 2.5m which equates to about 66% of the economically active population, the highest penetration level of any country. That said, the Irish movement sits at a critical development stage, well behind mature markets such as Canada and the US in terms of product provision, technological sophistication, fragmentation of trade bodies and regulatory environment. This study analyses relative cost efficiency or performance of Irish credit unions using the popular frontier approach which measures an entity’s efficiency relative to a frontier of best practice. Parametric techniques are utilised, with variation in inefficiency being attributed to credit union-specific factors. The stochastic cost frontier parameters and the credit-union specific parameters are simultaneously estimated to produce valid statistical inferences. The study finds that the majority of Irish credit unions are not operating at optimal levels. It further highlights the factors which drive efficiency variation across credit unions and they include technological sophistication, ‘sponsor donated’ resources, interest rate differentials and the levels of bad debt written off

Energy versus data integrity trade-offs in embedded high-density logic compatible dynamic memories

Current variation aware design methodologies, tuned for worst-case scenarios, are becoming increasingly pessimistic from the perspective of power and performance. A good example of such pessimism is setting the refresh rate of DRAMs according to the worst-case access statistics, thereby resulting in very frequent refresh cycles, which are responsible for the majority of the standby power consumption of these memories. However, such a high refresh rate may not be required, either due to extremely low probability of the actual occurrence of such a worst-case, or due to the inherent error resilient nature of many applications that can tolerate a certain number of potential failures. In this paper, we exploit and quantify the possibilities that exist in dynamic memory design by shifting to the so-called approximate computing paradigm in order to save power and enhance yield at no cost. The statistical characteristics of the retention time in dynamic memories were revealed by studying a fabricated 2kb CMOS compatible embedded DRAM (eDRAM) memory array based on gain-cells. Measurements show that up to 73% of the retention power can be saved by altering the refresh time and setting it such that a small number of failures is allowed. We show that these savings can be further increased by utilizing known circuit techniques, such as body biasing, which can help, not only in extending, but also in preferably shaping the retention time distribution. Our approach is one of the first attempts to access the data integrity and energy tradeoffs achieved in eDRAMs for utilizing them in error resilient applications and can prove helpful in the anticipated shift to approximate computing.

Systematic Review Protocol to Evaluate the Effectiveness and Cost Effectiveness of Personalised Surveillance after Colorectal Adenomatous Polypectomy

Lifetime risk of developing colorectal cancer (CRC) is 5% and five-year survival at early-stage is 92%. CRC risk following index colonoscopy should establish post-screening surveillance benefit, which may be greater in high-risk patients. This review evaluated published cost-effectiveness estimates of post-polypectomy surveillance to assess the potential for personalised recommendations by risk sub-group. Current data suggested colonoscopy identifies those at low-risk of CRC, who may not benefit from intensive surveillance, which risks unnecessary harms and inefficient use of colonoscopy resources. Meta-analyses of incidence of advanced-neoplasia post-polypectomy for low-risk was comparable to those without adenoma; both rates were under the lifetime risk of 5%. Therefore, greater personalisation through de-intensified strategies for low-risk individuals could be beneficial and could employ non-invasive testing such as faecal immunochemical tests (FIT) combined with primary prevention or chemoprevention, thereby reserving colonoscopy for targeted use in personalised risk-stratified surveillance.
This systematic review aims to:
1. Assess if there is evidence supporting a program of personalised surveillance in patients with colorectal adenoma according to risk sub-group.
2. Compare the effectiveness of surveillance colonoscopy with alternative prevention strategies.
3. Assess trade-off between costs, benefits and adverse effects which must be considered in a decision to adopt or reject personalised surveillance.

Influence of Manufacturing Tolerance on Aircraft Direct Operating Cost (DOC)

The influence of manufacturing tolerance on direct operating cost (DOC) is extrapolated from an engine nacelle to be representative of an entire aircraft body. Initial manufacturing tolerance data was obtained from the shop floor at Bombardier Aerospace Shorts, Belfast while the corresponding costs were calculated according to various recurring elements such as basic labour and overtime labour, rework, concessions, and redeployment; along with the non-recurrent costs due to tooling and machinery, etc. The relation of tolerance to cost was modelled statistically so that the cost impact of tolerance change could be ascertained. It was shown that a relatively small relaxation in the assembly and fabrication tolerances of the wetted surfaces resulted in reduced costs of production that lowered aircraft DOC, as the incurred drag penalty was predicted and taken into account during the optimisation process.

Numerical Method for Cost-Weight Optimisation of Stringer-Skin Panels

The need to integrate cost into the early product definition process as an engineering parameter is addressed. The application studied is a fuselage panel that is typical for commercial transport regional jets. Consequently, a semi-empirical numerical analysis using reference data was coupled to model the structural integrity of thin-walled structures with regard to material failure and buckling: skin, stringer, flexural, and interrivet. The optimization process focuses on direct operating cost (DOC) as a function of acquisition cost and fuel burn. It was found that the ratio of acquisition cost to fuel burn was typically 4:3 and that there was a 10% improvement in the DOC for the minimal DOC condition over the minimal weight condition because of the manufacturing cost saving from having a reduced number of larger-area stringers and a slightly thicker skin than that preferred by the minimal weight condition. Also note that the minimal manufacturing cost condition was slightly better than the minimal weight condition, which highlights the key finding: The traditional minimal weight condition is a dated and suboptimal approach to airframe structural design.

Integrating Aircraft Cost Modelling into Conceptual Design

The article presents cost modeling results from the application of the Genetic-Causal cost modeling principle. Industrial results from redesign are also presented to verify the opportunity for early concept cost optimization by using Genetic-Causal cost drivers to guide the conceptual design process for structural assemblies. The acquisition cost is considered through the modeling of the recurring unit cost and non-recurring design cost. The operational cost is modeled relative to acquisition cost and fuel burn for predominately metal or composites designs. The main contribution of this study is the application of the Genetic-Causal principle to the modeling of cost, helping to understand how conceptual design parameters impact on cost, and linking that to customer requirements and life cycle cost.