• 基于图聚类与蚁群算法的社交网络聚类算法

    Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-05-10 Cooperative journals: 《计算机应用研究》

    Abstract: Aiming at the properties of direction and diversity of social relationships in the social networks, this paper proposed a clustering algorithm of social networks based on graph clustering and ant colony optimization algorithm. Firstly, it constructed a directed and non fully connected complete graph for the social networks under constraint condition of network coverage; then, it adopted K-medoids algorithm to search the center users of all user groups, and it adopted ant colony optimization to search the similarities of each user and center users in the graph, it grouped the users satisfied the threshold condition into the same group. This paper also designed a prediction mechanism of low active degree users to resolve the sparsity problem and cold-start problem, besides, the network coverage constraint condition was set to balance the indexes of accuracy and coverage. Simulation experimental results indicate that the proposed algorithm realizes a good clustering performance of social networks, and it reduces the problems of sparsity and cold-start effectively.

  • 基于均衡数据放置策略的分布式网络存储编码缓存方案

    Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-04-01 Cooperative journals: 《计算机应用研究》

    Abstract: In order to ensure the load balance of network storage and to avoid unrecoverable loss in case of node or disk failures, this paper proposed a distributed storage and coding scheme based on balanced data placement strategy, which gave different solutions for large caches and small caches. Firstly, the Maddah scheme is extended to multi-server system, and each file is stored as a unit in the data server by combining balanced data placement strategy to solve the large-scale cache problem. Then, the interference cancellation scheme is extended to the multi-server system. The interference cancellation scheme is used to reduce the peak rate of the cache, and the linear combination of cache segments is proposed by combining balanced data placement strategy so as to solving the problem of small caching. Finally, simulation experiments are carried out in one and two parity check server systems respectively through Linux-based NS2 simulation software. The simulation results show that the proposed scheme can effectively reduce the peak transmission rate. It has achieved better performance comparing with the other two new caching schemes. In addition, although distributed storage limits the ability to combine content from different servers into a single message, resulting in performance loss of coding and caching schemes, it can make full use of the inherent redundancy in distributed storage systems, thereby improving the performance of storage systems.

  • 软件定义网络中利用IMKVS结合NFV的分布式网络负载均衡策略

    Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-19 Cooperative journals: 《计算机应用研究》

    Abstract: Social networks and other clouding applications should require fast responses from datacenter are infra- structure. One of the techniques that have been widely used for achieving such requirement is the employment of In-Memory Key-Value Storage (IMKVS) as caching mechanisms in order to improve overall user experience. Commonly IMKVS systems use Consistent Hashing to decide where to store an object, which may cause network load imbalance due to its simplistic approach. In order to improve IMKVS performance, this paper proposed a distributed network load balancing strategy using IMKVS and NFV in software defined networks. The strategy consisted of two phases. In the first phase, a generic SDN load balancer module was designed to run different load balancing algorithms. The second phase was a specialized caching based on IMKVS that enabled communication management and data replication. Simulation results show an improvement of 24% on the load of the caching servers and 7% on the load of the network compared to consistent hashing, which results in better resource usage and better user experience.