Performance evaluation of cloud service considering fault recovery

Cloud computing is a recent trend in IT, which has attracted lots of attention. In cloud computing, service reliability and service performance are two important issues. To improve cloud service reliability, fault tolerance techniques such as fault recovery may be used, which in turn has impact on cloud service performance. Such impact deserves detailed research. Although there exist some researches on cloud/grid service reliability and performance, very few of them addressed the issues of fault recovery and its impact on service performance. In this paper, we conduct detailed research on performance evaluation of cloud service considering fault recovery. We consider recovery on both processing nodes and communication links. The commonly adopted assumption of Poisson arrivals of users’ service requests is relaxed, and the interarrival times of service requests can take arbitrary probability distribution. The precedence constraints of subtasks are also considered. The probability distribution of service response time is derived, and a numerical example is presented. The proposed cloud performance evaluation models and methods could yield results which are realistic, and thus are of practical value for related decision-makings in cloud computing.     

On the validity of the arithmetic–geometric mean method to locate the optimal solution in a supply chain system

Cardenas-Barron [Cardenas-Barron, L.E. (2010) ‘A Simple Method to Compute Economic order Quantities: Some Observations’, Applied Mathematical Modelling, 34, 1684–1688] indicates that there are several functions in which the arithmetic–geometric mean method (AGM) does not give the minimum. This article presents another situation to reveal that the AGM inequality to locate the optimal solution may be invalid for Teng, Chen, and Goyal [Teng, J.T., Chen, J., and Goyal S.K. (2009), ‘A Comprehensive Note on: An Inventory Model under Two Levels of Trade Credit and Limited Storage Space Derived without Derivatives’, Applied Mathematical Modelling, 33, 4388–4396], Teng and Goyal [Teng, J.T., and Goyal S.K. (2009), ‘Comment on ‘Optimal Inventory Replenishment Policy for the EPQ Model under Trade Credit Derived without Derivatives’, International Journal of Systems Science, 40, 1095–1098] and Hsieh, Chang, Weng, and Dye [Hsieh, T.P., Chang, H.J., Weng, M.W., and Dye, C.Y. (2008), ‘A Simple Approach to an Integrated Single-vendor Single-buyer Inventory System with Shortage’, Production Planning and Control, 19, 601–604]. So, the main purpose of this article is to adopt the calculus approach not only to overcome shortcomings of the arithmetic–geometric mean method of Teng et al. (2009), Teng and Goyal (2009 Teng, JT, Chen, J and Goyal, SK. 2009. A Comprehensive Note on: An Inventory Model under Two Levels of Trade Credit and Limited Storage Space Derived without Derivatives. Applied Mathematical Modelling, 33: 4388–4396. [Crossref], [Web of Science ®] , [Google Scholar]) and Hsieh et al. (2008), but also to develop the complete solution procedures for them.     

Performance analysis of an inventory–production system with shipment consolidation in the production facility

We consider an inventory–production system consisting of a warehouse and a production facility. The warehouse is used to store products to satisfy customer demands, and its inventory is controlled by an (r,Q)$(r,Q)$ policy. Products ordered by the warehouse are processed in the production facility on a one-by-one basis, and finished products are consolidated into batches to be shipped from the production facility to the warehouse. Using the matrix-analytic methods, explicit solutions are obtained and computational methods are developed for analyzing system performance measures.     

Analysis of the unloading performance considering dimple–flexure behavior in HDD

Currently, almost all hard disk drives (HDDs) have adopted a loading/unloading mechanism that increases their recording capacity and improves their reliability. However, these mechanisms still create a few scratches or defects in the loading/unloading zone. Slipping at the dimple–flexure interface was recently reported as one of the causes. In this research, we first analyzed the relative behavior of dimple–flexure based on fretting wear marks. We determined that the dimple–flexure behavior included both slipping and rotating motion simultaneously. We then verified the distinct slipping and rolling phenomenon at the moment of ramp contact using finite-element method (FEM) analysis. An experimental setup was constructed, and an unloading experiment was carried out to obtain the ramp contact characteristics corresponding to various unloading velocities. Based on the verified FEM, the characteristics of dimple–flexure relative behavior were investigated for various suspension design parameters, ramp contact characteristics, and unloading velocities. A higher ramp contact force and shorter contact duration resulted in larger slip displacements and roll angles between the dimple and the flexure. Finally, we analyzed the unloading performance of an HDD for various design parameters using quasi-static approximation while considering the relative behavior between the dimple and flexure. The quasi-static analysis indicated a change of approximately 15?% in the flying height at an unloading velocity of 40?in. per second when the relative motion between the dimple and flexure was considered during the unloading process. Even, slider–disk contact occurred at an unloading velocity of 50 ISP.     

Phase diagram and thermodynamic properties of the LaI3–RbI binary system

Differential Scanning Calorimetry (DSC) method was used to determine phase equilibria in the LaI₃–RbI binary system, and heat capacity of LaI₃ and compounds existing in the system under investigation. Two compounds were identified in the solid phase of this system. First of them, Rb₂LaI₅, melts incongruently at 809 K. The second one, Rb₃LaI₆, forms at 686 K from Rb₂LaI₅ and RbI, undergoes a solid-solid transition at 706 K and melts congruently at 864 K. The compositions of RbI–Rb₃LaI₆ and Rb₂LaI₅–LaI₃ eutectics corresponding to LaI₃ mole fraction of x = 0.177 (T = 789 K) and x = 0.472 (T = 773 K), respectively were found from Tammann's diagrams. The LaI₃–RbI pseudobinary system was also optimized by CAPLHAD method. Thermodynamic properties of the liquid phase were modelled using Associate Solution Model.     

Phase diagram and thermodynamic properties of the GdBr3–CsBr binary system

Phase diagram of the GdBr₃-CsBr binary system was established by Differential Scanning Calorimetry (DSC) method. This system exhibits three stoichiometric compounds, namely Cs₃GdBr₆, Cs₃Gd₂Br₉ and CsGd₂Br_7; and three eutectics located at GdBr₃ molar fraction x = 0.11 (T = 847 K), x = 0.52 (T = 798 K) and x = 0.72 (T = 859 K), respectively. Cs₃GdBr₆ undergoes a solid–solid phase transition at 701 K and melts congruently at 1077 K. Cs₃Gd₂Br₉ melts incongruently at 841 K and finally CsGd₂Br₇ undergoes a solid–solid phase transition at 788 K and melts congruently at 880 K. Experimentally determined phase diagram was optimized by CALPHAD method and thermodynamic properties of compounds existing in the system were estimated. Phase transition of pure GdBr₃were determined at 533 K and ΔH_tr = 0.41 kJ mol^-1.     

Hybrid lean–agile manufacturing system technical facet,in automotive sector

In the automotive sector, planners have a difficult balancing act. They benefit from commonality of vehicle parts, yet they must meet more niche demands. The challenge is to strike a balance between these extremes in a cost-effective way without compromising quality. Lean strategies could increase competitiveness and profitability by reducing manufacturing costs. Concurrently, agile strategies could enable enterprises to cope with fluctuations. A hybrid lean–agile approach can be an optimal strategic blend for a manufacturing enterprise to meet this challenge. Flexible focused factory, globalized fractal E-manufacturing, innovative value chain strategies, and designing dynamic manufacturing strategies are the four technical pillars of the proposed hybrid lean–agile manufacturing system technical facet. The study shows that hybridizing the lean and agile systems together is technically valid and can be implemented in an industrial setting. It shows how strategically a hybrid lean–agile system can be implemented. It also shows that about one third of the variation in successfully dealing with the sources of competitive advantage in automotive industry can be explained by adopting the technical facet of the hybrid lean–agile manufacturing system.     

Simulation of metal–polymer coating system for service life prediction

A degradation model of a metal-protective coating system is given. Prediction calculations of protective coating systems service life using the experimental data of non-adhesion area are executed. Comparative analysis of the coating service life values calculated and those under operating conditions has shown the adequacy of the offered prediction parities.     

Expert system applications in business: A review and analysis of the literature (1977–1993)

A survey of expert system (ES) business application papers published between 1977 and 1993 indicates that an increasing amount of ES research is being conducted for a diverse range of business activities. The classification of literature by (1) year of publication, (2) application area, (3) generic problem area addressed, (4) problem domain, (5) level of management, (6) level of task interdependence, (7) means of development, (8) corporate/academic interaction in development, and (9) technology integration provides some insights in the trend. Implications to ES developers are discussed.     

Two-echelon fuzzy stochastic supply chain for the manufacturer–buyer integrated production–inventory system

This paper deals with two-echelon integrated procurement production model for the manufacturer and the buyer integrated inventory system. The manufacturer procures raw material from outside suppliers (not a part of supply chain) then proceed to convert it as finished product, and finally delivers to the buyer, who faces imprecise and uncertain, called fuzzy random demand of customers. The manufacturer and the buyer work under joint channel, in which a centralized decision maker makes all decisions to optimize the joint total relevant cost (JTRC) of entire supply chain. In this account, in one production cycle of the manufacturer we determine an optimal multi-ordering policy for the buyer. To be part of this, we first derive the JTRC in stochastic framework, and then extend it in fuzzy stochastic environment. In order to scalarize the fuzzy stochastic JTRC, we use an evaluation method wherein randomness is estimated by probabilistic expectation and fuzziness is estimated by possibilistic mean based on possibility evaluation measure. To derive the optimal policies for both parties, an algorithm is proposed. A numerical illustration addresses the situations of paddy procurement, conversion to rice and fulfillment of uncertain demand of rice. Furthermore, sensitivity of parameters is examined to illustrate the model and algorithm.     

Efficient application scheduling in mobile cloud computing based on MAX–MIN ant system

Combining the advantages of mobile computing and cloud computing, Mobile Cloud Computing (MCC) greatly enriches the types of applications on mobile devices and enhances the quality of service of the applications. Under various circumstances, researchers have put forward several MCC architectures. However, it still remains a challenging task of how to design a reasonable mobile cloud model with efficient application processing structure for some particular environment. This paper firstly presents a Hybrid Local Mobile Cloud Model (HLMCM) with detailed application scheduling structure. Secondly, a scheduling algorithm for HLMCM based on MAX–MIN Ant System is put forward. Finally, the effectiveness and suitability of our proposed algorithms are evaluated through a series of simulation experiments.