Guosun Zeng

Cloud-DLS

Highlights? This paper proposed a novel Bayesian method based cognitive trust model. ? A trust dynamic level scheduling algorithm named Cloud-DLS is proposed. ? A benchmark is structured for evaluation of the proposed method. ? Experiments and case studies are carried out to evaluate our proposed method. Clouds are rapidly becoming an important platform for scientific applications. In the Cloud environment with uncountable numeric nodes, resource is inevitably unreliable, which has a great effect on task execution and scheduling. In this paper, inspired by Bayesian cognitive model and referring to the trust relationship models of sociology, we first propose a novel Bayesian method based cognitive trust model, and then we proposed a trust dynamic level scheduling algorithm named Cloud-DLS by integrating the existing DLS algorithm. Moreover, a benchmark is structured to span a range of Cloud computing characteristics for evaluation of the proposed method. Theoretical analysis and simulations prove that the Cloud-DLS algorithm can efficiently meet the requirement of Cloud computing workloads in trust, sacrificing fewer time costs, and assuring the execution of tasks in a security way.

Towards reliable self-clustering Mobile Ad Hoc Networks

With the introduction of Mobile Ad Hoc Networks (MANETs), nodes are able to participate in a dynamic network which lacks an underlying infrastructure. In this paper, we present a novel approach to improve the search efficiency and scalability of MANETs by clustering nodes based on trust mechanism. In our method, the trust relationship is formed by evaluating the level of trust using Bayesian statistic analysis, and clusters can be formed and maintained autonomously by nodes with only partial knowledge. Simulation results show that each node can form and join proper clusters based on their trust degree, and the cluster-based search algorithm with trust mechanism outperforms over those in current popular clustering models.

Dynamic trust evaluation and scheduling framework for cloud computing

Cloud computing has become a scalable services consumption and delivery platform in the field of computer science. As more and more consumers delegate their tasks to cloud providers, service level agreements (SLAs) between consumers and providers emerge as a key aspect. Because of the dynamic nature of the cloud, continuous monitoring on quality-of-service attributes is necessary to enforce SLAs. In this paper, we propose a trust mechanism-based task scheduling model for cloud computing. Referring to the trust relationship models of social persons, trust relationship is built among computing nodes, and the trustworthiness of nodes is evaluated by utilizing the Bayesian cognitive method. Integrating the trustworthiness of nodes into a dynamic level scheduling algorithm, the trust dynamic level scheduling algorithm for cloud computing is proposed. Theoretical analysis and simulations prove that the proposed algorithm can efficiently meet the requirement of cloud computing workloads in trust, sacrificing fewer time costs, and assuring the execution of tasks in a secure way in cloud environment. Copyright

Energy Consumption Analysis Satisfying Time–Energy–Probability Constraints for Modern DVFS Microprocessor

ABSTRACT Dynamic voltage and frequency scaling (DVFS) is a popular technique to save energy for modern microprocessor. DVFS-based energy-aware scheduling technique is a critical energy saving technology for multi-task execution on modern DVFS processor. Many DVFS-based energy-aware scheduling technologies are unsatisfying for the trade-off between optimizing scheduling length and saving energy, and most of these technologies do not consider task execution time with probability distribution in real world. In this paper, we propose an energy-aware probabilistic scheduling approach to balancing between optimizing scheduling length and saving energy in a time–energy–probability constrained multi-task uniprocessor system, and we consider that each task execution time follows a probability distribution. We first construct system models, including DVFS operating environment, task model with each task execution time following a probability distribution, and energy model. In order to balance between task scheduling length and energy consumption, we propose time–energy–probability constraints scheduling (TEPcs) problem for the DVFS processor system. To solve TEPcs problem, we use a probabilistic weighted timed automaton to model the running behaviours of the processor system. Then, we devise a polynomial time heuristic algorithm through the probabilistic weighted timed automaton to find the optimal energy path as the solution of TEPcs problem. A case study and repeated experimental analysis demonstrate that our method is feasible and effective.

Extending Parallel Computing with Constraint of Fixed Structure by Adjusting Graph

ABSTRACT Adding the number of computing nodes is a common approach to achieving higher performance in a parallel computing system. However, with constraint of fixed system architecture and fixed algorithm structure, it is difficult to improve the performance of parallel computing only by extending its scale absolutely. To realize such extension with fixed structure, we analyze key factors from architecture and parallel task, which affect the scalability, and then use the weighted graph to model architecture as well as parallel task. Especially, focusing on the case that architecture graph and parallel task graph are homogeneous, we propose the extension method of graph similarity; for the case that architecture graph and parallel task graph are heterogeneous, a critical-path-unchanged scaling method is proposed. Actually, the above two extending methods do not change the graphs structure. They only adjust the node weight and edge-weight in the relevant graph. Furthermore, through mathematical derivation, some conclusions about the new scaling methods are drawn. Finally, in order to verify the effectiveness, some simulative experiments are conducted on the platform SimGrid. The experimental results show that the proposed methods can realize iso-speed-efficiency extension, and can guide practical extensions for parallel computing.

Parallel time-space processing model based fast N -body simulation on GPUs

The N-body problems simulate the evolution of a system of N bodies where the force exerted on each body arises due to its interaction with all the other bodies in the system. In this paper, we present a novel parallel implementation of N-body gravitational simulation on GPUs. We analyze the current implementation of GPU, and give our new method on implementing N-body algorithm on HD Radeon 5870 GPU of AMD. The experimental results show that this method achieves an acceleration of 413 compared with CPU, and an acceleration up to 5.5 times compared with other GPU based methods.

Upper Limit Analysis of Scalable Parallel Computing on the Premise of Reliability Requirement

ABSTRACT The Top500 supercomputers ranking has been held twice a year according to Linpack performance for more than 20 years, which greatly stimulates the development of high-performance computing. However, it is still not clear how to determine the scale limit of supercomputers. It will undoubtedly cause a waste of resources if we build bigger and bigger supercomputers without caring about other aspects of cost, energy, reliability. Thus, this paper analyses the scalability and scale limit for parallel computing with a reliability requirement. We use a Markov chain to model the state transition process of a parallel computing system, so the probability of parallel tasks running on machines successfully can be evaluated, that is the reliability of parallel computing. When parallel computing carries out an iso-speed efficiency extension under specific reliability requirements, we present an approach to calculate the maximum number of processing nodes and the maximum workload of parallel tasks, which actually reveals the function relation between the scale limit and the speed efficiency of parallel computing. Taking “Tianhe-2”, which is the current No. 1 supercomputer, as an example, we utilize our methods to do a case study and predict its scale limit. Finally, a simulation experiment is conducted to verify our theory.