Optimization of energy consumption in cloud computing datacenters

Cloud computing has emerged as a practical paradigm for providing IT resources, infrastructure and services. This has led to the establishment of datacenters that have substantial energy demands for their operation. This work investigates the optimization of energy consumption in cloud datacenter using energy efficient allocation of tasks to resources. The work seeks to develop formal optimization models that minimize the energy consumption of computational resources and evaluates the use of existing optimization solvers in testing these models. Integer linear programming (ILP) techniques are used to model the scheduling problem. The objective is to minimize the total power consumed by the active and idle cores of the servers’ CPUs while meeting a set of constraints. Next, we use these models to carry out a detailed performance comparison between a selected set of Generic ILP and 0-1 Boolean satisfiability based solvers in solving the ILP formulations. Simulation results indicate that in some cases the developed models have saved up to 38% in energy consumption when compared to common techniques such as round robin. Furthermore, results also showed that generic ILP solvers had superior performance when compared to SAT-based ILP solvers especially as the number of tasks and resources grow in size.

Fabrication of 3D Bone Scaffolds Functionalized With Spatiotemporal Release of BMP-2 Growth Factor via iCVD to Enhance Osteoregeneration

3D scaffolds are known to be used in bone tissue engineering applications due to their great potential of providing multi-functionalized environment for cells. Different production techniques have been used focusing on changing geometrical features or adding biological/chemical compounds to improve the functionality of current 2D/3D scaffolds. A critical component to this functionalization relates to the effect of endogenous and exogeneous growth factors (GF) in the bone regeneration process that could be incorporated to the scaffolds via Initiated Chemical Vapor Deposition (iCVD) which is a solvent free method that requires low energy while also containing a wide variety of monomer choices for the layer by layer coating of polymers with individual functionality choices. However, GFs come with several difficulties such as rapid deactivation, low protein stability profile and little time of half-life, hence ideal environments that can overcome these issues are yet to be defined. Towards that goal, in this study we develop a computational framework based on the implementation of the advection-diffusion-reaction Partial Differential Equations (PDE) in a Finite Element Analysis (FEA) solver in COMSOL Multiphysics software. The goal is to develop a tool and conduct an initial analysis to be utilized for the simulation of multi-layer scaffold functionalized using encapsulation and immobilization of GFs inside nanoparticles possibly via iCVD. In this paper we focus on the analysis of two typical GF (BMP-2 and TGF) release mechanisms based on the effect of key material and geometrical parameters such as thickness of layers, initial GF concentration, diffusion coefficient, release function and uptake rate (absorption coefficient). The ultimate goal is to develop a model that can be used for future bone scaffold design studies when integrated to more advanced optimization methodologies. This model with further integration and updates of chemical and biological parameter measurements and inclusion of presence of antibodies should lay down a valuable basis for directing possible experimental functionalization efforts and their effects on the healing process of bone tissue. Initial results indicate that the proposed computational model can be utilized to predict the response of multi-layered bone scaffolds in terms of the concentration profiles of the GFs. Results of the parametric study presented in this paper prompt for the relative importance of each parameter in tuning the GF release profiles and point towards the need for formal optimization studies to achieve desired GF release responses considering all factors simultaneously. Among them, the diffusion coefficient is a key parameter with both a dominant effect on the GF profile and its ability to characterize different coatings using iCVD methods. As a next step, the developed framework will be updated to incorporate more detailed surface reactions and morphological data to simulate iCVD coated growth factors and verified with possible in-vitro studies before its integration to a formal optimization methodology.

MULTI-CRITERIA OPTIMIZATION AS KEY TO YACHT PERFORMANCE IMPROVEMENT

The paper describes the application of multi-criteria optimization to monohull and multihull yacht configurations. The paper outlines the process (involving concept exploration, formal optimization and simulations), key techniques, employed software tools and results. The analyses combine efficient low-fidelity design exploration with high-fidelity CFD simula-tions for accurate results. The process allows advancing unconventional designs in relatively short time exploiting the power of parallel computing and virtual prototyping. For yachts, “performance” improvement encompasses besides energy efficiency also aspects of passenger comfort. Examples, sometimes anonymized, from industry practice are used to illus-trate approach and possible achievements.

Optimizing Skyscrapers' Spatial Integrated DSF-MTMD System Under Wind Loads

<p>From a structural engineering point of view, wind effects pose one of the major challenges to tall buildings. From a performance/architectural point of view, climatologic aspects pose a major challenge. Remedies for each challenge separately have been proposed. One of the remedies for wind effects is the Tunes-Mass-Damper (TMD) or multiple TMD's. To mitigate climatological issues, the Double-Skin-Façade (DSF) has been developed. Recently it has been suggested to take advantage of the space between the two skins of the DSF system to allocate TMD's.</p><p>In this work, another step is taken towards a single remedy for both challenges. A modified version of the TMD-DSF system proposed by Moon (2016) is presented. That is, parts of the mass of the DSF envelope itself are used as part of a multiple TMD (MTMD) system. This is obtained by connecting these parts to the building using springs and dampers while allowing the DSF to move parallel to the floor edges. Furthermore, the DSF-MTMD system is optimized using a formal optimization approach. The optimization indicates which parts of the envelope should be connected to the building rigidly and which should be used as TMD's. Furthermore, the properties of the springs and the dampers are determined by minimizing the cost associated with transforming the DSF system to a DSF-MTMD system and limiting wind responses to desired values.</p>

The Risk of Optimization in Marketing Campaigns

In marketing one of the most common important tasks is to assign campaigns to sets of customers. These sets of customers, the target groups, consist of persons with similar properties, for example a high buying affinity for a certain product. Database marketers would not only assign a campaign by general economic or promotional consideration, but they take into account learning from databases by algorithms. The basic assumptions are already determined clusters to which campaigns, representing the products, should be assigned. The assignment can be done in the most optimal way by formal optimization, which is usually stochastic due to unknown campaign success in the future. The authors model the financial risk of the campaign success for enterprise practice. Their proposal is to use triangular distributions, known from financial and supply chain management applications. In an example, they demonstrate the benefits of the proposed procedure for the marketing task.

Advanced Simulations = Better Results. Really?

This paper looks at selected applications of advanced hydrodynamic simulations in the offshore oil & gas industry. Progress in computational techniques and hardware has opened the door to more advanced simulations. But do more advanced field equations really lead to better results? Or should we employ proven potential-flow codes along with the engineering insight and experience, as they are cheaper and faster? The answer is not trivial and needs to be found and justified for each application. But the paper shows applications of viscous flow simulations (RANSE) where potential flow simulations ruled supreme. Traditional arguments concerning computational time are eroded by massive parallel computation. The applications shown concern: second-order forces in waves, formal optimization of offshore structures, impact loads, short-crested irregular sea in RANSE simulations and vortex-induced vibration analyses.

A Novel Latin Hypercube Algorithm via Translational Propagation

Metamodels have been widely used in engineering design to facilitate analysis and optimization of complex systems that involve computationally expensive simulation programs. The accuracy of metamodels is directly related to the experimental designs used. Optimal Latin hypercube designs are frequently used and have been shown to have good space-filling and projective properties. However, the high cost in constructing them limits their use. In this paper, a methodology for creating novel Latin hypercube designs via translational propagation and successive local enumeration algorithm (TPSLE) is developed without using formal optimization. TPSLE algorithm is based on the inspiration that a near optimal Latin Hypercube design can be constructed by a simple initial block with a few points generated by algorithm SLE as a building block. In fact, TPSLE algorithm offers a balanced trade-off between the efficiency and sampling performance. The proposed algorithm is compared to two existing algorithms and is found to be much more efficient in terms of the computation time and has acceptable space-filling and projective properties.