A Cloud data center is a network of virtualized resources, namely virtualized servers. They provision on-demand services to the source of requests ranging from virtual machines to virtualized storage and virtualized n...
详细信息
A Cloud data center is a network of virtualized resources, namely virtualized servers. They provision on-demand services to the source of requests ranging from virtual machines to virtualized storage and virtualized networks. The cloud data center service requests can come from different sources across the world. It is desirable for enhancing Quality of Service (QoS), which is otherwise known as a service level agreement (SLA), an agreement between cloud service requester and cloud service consumer on QoS, to allocate the cloud data center closest to the source of requests. This article models a Cloud data center network as a graph and proposes an algorithm, modified Breadth First Search where the source of requests assigned to the Cloud data centers based on a cost threshold, which limits the distance between them. Limiting the distance between Cloud data centers and the source of requests leads to faster service provisioning. The proposed algorithm is tested for various graph instances and is compared with modified Voronoi and modified graph-based K-Means algorithms that they assign source of requests to the cloud data centers without limiting the distance between them. The proposed algorithm outperforms two other algorithms in terms of average time taken to allocate the cloud data center to the source of requests, average cost and load distribution.
Efficient scheduling algorithms have been a leading research topic for heterogeneous computing systems. Although duplication-based scheduling algorithms can significantly reduce the total completion time, they are gen...
详细信息
Efficient scheduling algorithms have been a leading research topic for heterogeneous computing systems. Although duplication-based scheduling algorithms can significantly reduce the total completion time, they are generally accompanied by an exorbitant time complexity. In this paper, we propose a new task duplication-based heuristic scheduling algorithm, LDLS, that can reduce the total completion time and maintains a low time complexity. The scheduling procedure of LDLS is composed of three main phases: In the beginning phase, the maximum number of duplications per level and per task is calculated to prevent excessive duplications from blocking regular tasks. In the next phase, the optimistic cost table (OCT) and ranking of tasks are calculated with reference to PEFT. In the final phase, scheduling is conducted based on the ranking, and the duplication of each task is dynamically determined, enabling the duplicated tasks to effectively reduce the start execution time of its successor tasks. Experiments of algorithms on randomly generated graphs and real-world applications indicate that both the scheduling length and the number of better case occurrences of LDLS are better than others.
We describe two variants of a tabu search heuristic, a deterministic one and a probabilistic one, for the maximum clique problem. This heuristic may be viewed as a natural alternative implementation of tabu search for...
详细信息
LFR is a popular benchmark graphgenerator used to evaluate community detection algorithms. We present EM-LFR, the first external memory algorithm able to generate massive complex networks following the LFR benchmark....
详细信息
LFR is a popular benchmark graphgenerator used to evaluate community detection algorithms. We present EM-LFR, the first external memory algorithm able to generate massive complex networks following the LFR benchmark. Its most expensive component is the generation of randomgraphs with prescribed degree sequences which can be divided into two steps: the graphs are first materialized deterministically using the Havel-Hakimi algorithm, and then randomized. Our main contributions are EM-HH and EM-ES, two I/O-efficient external memory algorithms for these two steps. We also propose EM-CM/ES, an alternative sampling scheme using the Configuration Model and rewiring steps to obtain a random simple graph. In an experimental evaluation, we demonstrate their performance; our implementation is able to handle graphs with more than 37 billion edges on a single machine, is competitive with a massively parallel distributed algorithm, and is faster than a state-of-the-art internal memory implementation even on instances fitting in main memory. EM-LFR’s implementation is capable of generating large graph instances orders of magnitude faster than the original implementation. We give evidence that both implementations yield graphs with matching properties by applying clustering algorithms to generated instances. Similarly, we analyze the evolution of graph properties as EM-ES is executed on networks obtained with EM-CM/ES and find that the alternative approach can accelerate the sampling process.
We consider the problem of sampling from a distribution on graphs, specifically when the distribution is defined by an evolving graph model, and consider the time, space, and randomness complexities of such samplers. ...
详细信息
We consider the problem of sampling from a distribution on graphs, specifically when the distribution is defined by an evolving graph model, and consider the time, space, and randomness complexities of such samplers. In the standard approach, the whole graph is chosen randomly according to the randomized evolving process, stored in full, and then queries on the sampled graph are answered by simply accessing the stored graph. This may require prohibitive amounts of time, space, and random bits, especially when only a small number of queries are actually issued. Instead, we propose a setting where one generates parts of the sampled graph on-the-fly, in response to queries, and therefore requires amounts of time, space, and random bits that are a function of the actual number of queries. Yet, the responses to the queries correspond to a graph sampled from the distribution in question. Within this framework, we focus on two randomgraph models: the Barabasi-Albert Preferential Attachment model (BA-graphs) (Science, 286 (5439):509-512) (for the special case of out-degree 1) and the random recursive tree model (Theory of Probability and Mathematical Statistics, (51):1-28). We give on-the-fly generation algorithms for both models. With probability 1 - 1/poly(n), each and every query is answered in polylog(n) time, and the increase in space and the number of random bits consumed by any single query are both polylog(n), where n denotes the number of vertices in the graph. Our work thus proposes a new approach for the access to huge graphs sampled from a given distribution, and our results show that, although the BA randomgraph model is defined by a sequential process, efficient random access to the graph's nodes is possible. In addition to the conceptual contribution, efficient on-the-fly generation of randomgraphs can serve as a tool for the efficient simulation of sublinear algorithms over large BA-graphs, and the efficient estimation of their on such graphs.
暂无评论