• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1157-1169
• /
• 2021

Modern graphics processor unit (GPU) architectures offer significant hardware resource enhancements for parallel computing. However, without software optimization, GPUs continuously exhibit hardware resource underutilization. In this paper, we indicate the need to alter different warp scheduler schemes during different kernel execution periods to improve resource utilization. Existing warp schedulers cannot be aware of the kernel progress to provide an effective scheduling policy. In addition, we identified the potential for improving resource utilization for multiple-warp-scheduler GPUs by sharing stalling warps with selected warp schedulers. To address the efficiency issue of the present GPU, we coordinated the kernel-aware warp scheduler and warp sharing mechanism (KAWS). The proposed warp scheduler acknowledges the execution progress of the running kernel to adapt to a more effective scheduling policy when the kernel progress attains a point of resource underutilization. Meanwhile, the warp-sharing mechanism distributes stalling warps to different warp schedulers wherein the execution pipeline unit is ready. Our design achieves performance that is on an average higher than that of the traditional warp scheduler by 7.97% and employs marginal additional hardware overhead.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.2815-2839
• /
• 2020

In a cloud computing paradigm, allocation of various virtualized ICT resources is a complex problem due to the presence of heterogeneous application (MapReduce, content delivery and networks web applications) workloads having contentious allocation requirements in terms of ICT resource capacities (resource utilization, execution time, response time, etc.). This task of resource allocation becomes more challenging due to finite available resources and increasing consumer demands. Therefore, many unique models and techniques have been proposed to allocate resources efficiently. However, there is no published research available in this domain that clearly address this research problem and provides research taxonomy for classification of resource allocation techniques including strategic, target resources, optimization, scheduling and power. Hence, the main aim of this paper is to identify open challenges faced by the cloud service provider related to allocation of resource such as servers, storage and networks in cloud computing. More than 70 articles, between year 2007 and 2020, related to resource allocation in cloud computing have been shortlisted through a structured mechanism and are reviewed under clearly defined objectives. Lastly, the evolution of research in resource allocation techniques has also been discussed along with salient future directions in this area.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2233-2252
• /
• 2018

For the problem of cross-layer joint resource allocation (JRA) in the Long-Term Evolution (LTE)-Advanced standard using carrier aggregation (CA) technology, it is difficult to obtain the optimal resource allocation scheme. This paper proposes a joint resource allocation algorithm based on the weights of user's average quality of experience (JRA-WQOE). In contrast to prevalent algorithms, the proposed method can satisfy the carrier aggregation abilities of different users and consider user fairness. An optimization model is established by considering the user quality of experience (QoE) with the aim of maximizing the total user rate. In this model, user QoE is quantified by the mean opinion score (MOS) model, where the average MOS value of users is defined as the weight factor of the optimization model. The JRA-WQOE algorithm consists of the iteration of two algorithms, a component carrier (CC) and resource block (RB) allocation algorithm called DABC-CCRBA and a subgradient power allocation algorithm called SPA. The former is used to dynamically allocate CC and RB for users with different carrier aggregation capacities, and the latter, which is based on the Lagrangian dual method, is used to optimize the power allocation process. Simulation results showed that the proposed JRA-WQOE algorithm has low computational complexity and fast convergence. Compared with existing algorithms, it affords obvious advantages such as improving the average throughput and fairness to users. With varying numbers of users and signal-to-noise ratios (SNRs), the proposed algorithm achieved higher average QoE values than prevalent algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권3호
• /
• pp.819-837
• /
• 2014

Data centers, which implement cloud service, have been faced up with quick growth of energy consumption and low efficiency of energy. 60GHz wireless communication technology, as a new option to data centers, can provide feasible approach to alleviate the problems. Aiming at energy optimization in 60GHz wireless data centers (WDCs), we investigate virtualization technology to assign virtual resources to minimum number of servers, and turn off other servers or adjust them to the state of low power. By comprehensive analysis of wireless data centers, we model virtual network and physical network in WDCs firstly, and propose Virtual Resource Mapping Packing Algorithm (VRMPA) to solve energy management problems. According to VRMPA, we adopt packing algorithm and sort physical resource only once, which improves efficiency of virtual resource allocation. Simulation results show that, under the condition of guaranteeing network load, VPMPA algorithm can achieve better virtual request acceptance rate and higher utilization rate of energy consumption.

• 대한기계학회논문집A
• /
• 제27권1호
• /
• pp.158-166
• /
• 2003

The paper describes the development and application of advanced evolutionary computing techniques referred to as micro genetic algorithms ($\mu$GA) in the context of engineering design optimization. The basic concept behind $\mu$GA draws from the use of small size of population irrespective of the bit string length in the representation of design variable. Such strategies also demonstrate the faster convergence capability and more savings in computational resource requirements than simple genetic algorithms (SGA). The paper first explores ten-bar truss design problems to see the optimization performance between $\mu$GA and SGA. Subsequently, $\mu$GA is applied to a realistic engineering design problem in the injection molding process optimization.

• 한국수소및신에너지학회논문집
• /
• 제20권6호
• /
• pp.492-498
• /
• 2009

Six sigma methode was applied for optimization of flow field design of a proton exchange membrane fuel cell (PEMFC). The optimization between number of channel and channel/rib width was suggested in this paper with six sigma method. With the help of six sigma design of experiment (DOE) the number of experiments may be reduced dramatically. The fuel cell channel design optimization with results of these experiments with a 100 $cm^2$ serpentine flow field indicates a optimization data for a given constant operating conditions.

• Journal of Electrical Engineering and Technology
• /
• 제7권1호
• /
• pp.17-22
• /
• 2012

Lagrangian relaxation is the most widely adopted method for solving unit commitment (UC) problems. It consists of two steps: dual optimization and primal feasible solution construction. The dual optimization step is crucial in determining the overall performance of the solution. This paper intends to evaluate two dual optimization methods - one based on subgradient (SG) and the other based on the cutting plane. Large-scale UC problems with hundreds of thousands of variables and constraints have been generated for evaluation purposes. It is found that the evaluated SG method yields very promising results.

• International journal of advanced smart convergence
• /
• 제1권2호
• /
• pp.34-38
• /
• 2012

The recent increase in use of the IEEE 802.15.4 standard for wireless connectivity in personal area networks makes of it an important technology for low-cost low-power wireless personal area networks. Studies showed that voice communications over IEEE 802.15.4 networks is feasible by Guaranteed Time Slot (GTS) allocation; but there are some constraints to accommodate voice transmission beyond two hops due to the excessive transmission delay. In this paper, we propose a GTS allocation scheme for bidirectional voice traffic in IEEE 802.15.4 multihop networks with the goal of achieving fairness and optimization of resource allocation. The proposed scheme uses a greedy algorithm to allocate GTSs to devices for successful completion of voice transmission with efficient use of bandwidth while considering closest devices with another factor for starvation avoidance. We analyze and validate the proposed scheme in terms of fairness and resource optimization through numeral analysis.

• 대한산업공학회지
• /
• 제40권2호
• /
• pp.151-162
• /
• 2014

This study proposes an optimization model to plan the patient distribution and medical resource allocation considering the diverse characteristics of disaster. For reflecting the particularity of disaster response, we configured a few scenarios such as availability of emergency surgery of non-major medical staff and the change in number of patients estimated reflecting the uncertainty, urgency and convergence of disaster. And we finally tested the effects of the scenarios' combination on the objective function defined as maximum number of survival patients. Our experimental results are expected to highlight the significance of the proposed model as well as the applicability of scenarios under disaster response.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.565-581
• /
• 2019

This paper investigates the wireless powered two way relay network (WPTWRN), where two single-antenna users and one single-antenna relay firstly harvest energy from signals emitted by a multi-antenna power beacon (PB) and then two users exchange information with the help of the relay by using their harvested energies. In order to improve the energy transfer efficiency, energy beamforming at the PB is deployed. For such a network, to explore the performance limit of the presented WPTWRN, an optimization problem is formulated to obtain the achievable rate region bounds by jointly optimizing the time allocation and energy beamforming design. As the optimization problem is non-convex, it is first transformed to be a convex problem by using variable substitutions and semidefinite relaxation (SDR) and then solve it efficiently. It is proved that the proposed method achieves the global optimum. Simulation results show that the achievable rate region of the presented WPTWRN architecture outperforms that of wireless powered one way relay network architecture. Results also show that the relay location has significant impact on achievable rate region of the WPTWRN.